Merge pull request #586 from mattpocock/batch-grill-me-granular-facts

batch-grill-me: granular fact-finding, don't block the round
feat(batch-grill-me): granular fact-finding, don't block the round
2026-07-29 02:52:42 +07:00 · 2026-07-16 10:03:12 +01:00 · 2026-07-16 10:01:22 +01:00 · 2026-07-16 09:41:35 +01:00 · 2026-07-14 19:32:22 +01:00 · 2026-07-14 19:31:22 +01:00
180 changed files with 6553 additions and 1024 deletions
@@ -0,0 +1,10 @@
+# Explicit `/setup-matt-pocock-skills` pointer only for hard dependencies
+
+Engineering skills depend on per-repo config (issue tracker, triage label vocabulary, domain doc layout) seeded by `/setup-matt-pocock-skills`. Some skills cannot meaningfully function without that config — they have to publish to a specific issue tracker or apply a specific label string. Others only use it to sharpen output (vocabulary, ADR awareness) and degrade gracefully without it.
+
+We split these into **hard-dependency** and **soft-dependency** skills:
+
+- **Hard dependency** (`to-tickets`, `to-spec`, `triage`) — include an explicit one-liner: _"… should have been provided to you — run `/setup-matt-pocock-skills` if not."_ Without the mapping, output is wrong, not just fuzzy.
+- **Soft dependency** (`diagnose`, `tdd`, `improve-codebase-architecture`) — reference "the project's domain glossary" and "ADRs in the area you're touching" in vague prose only. If the docs aren't there, the skill still works; output is just less sharp.
+
+The split keeps soft-dependency skills token-light and avoids cargo-culting the setup pointer into places where it isn't load-bearing.
@@ -0,0 +1,28 @@
+# Ship the skill set as a native Claude Code plugin; defer a native Codex plugin
+
+These skills have always been installable via [skills.sh](https://skills.sh/mattpocock/skills) (`npx skills add mattpocock/skills`), which copies editable skill files into a user's project across Claude Code, Codex, and other Agent-Skills-standard harnesses. A recurring request is a **plug-and-play** distribution: subscribe to the set as a read-only, always-current bundle you don't edit, rather than a fork you own. That is exactly what native plugin systems provide.
+
+We ship a native **Claude Code plugin** and, for now, **defer** a native **Codex plugin**. The split is forced by how each ecosystem's plugin manifest selects skills, against this repo's bucketed layout.
+
+## The constraint: bucketed skills vs. single-path selection
+
+Skills live in bucket folders under `skills/` — `engineering/` and `productivity/` are **promoted** (shipped); `misc/`, `personal/`, `in-progress/`, and `deprecated/` are **not**. A plugin must expose only the promoted set, which spans two of those bucket folders.
+
+- **Claude Code** — `.claude-plugin/plugin.json` accepts `skills` as an **array of explicit skill-directory paths**. We list the promoted skills one by one, exclude everything else with zero ambiguity, and add `.claude-plugin/marketplace.json` so the repo is its own single-plugin marketplace. Verified end to end: `claude plugin validate . --strict` passes, and `marketplace add` → `install` resolves all promoted skills.
+
+- **Codex** — `.codex-plugin/plugin.json` accepts `skills` only as a **single path string** (arrays are rejected with `missing or invalid plugin.json`), and Codex discovers `SKILL.md` files recursively under it. There is no way to name two bucket folders, or to curate a subset, from one path. Two escape hatches were tested and rejected:
+  - Pointing at `./skills/` would also ship `deprecated/`, `in-progress/`, `personal/`, and `misc/` — retired, draft, and personal skills we deliberately don't promote.
+  - A curated flat directory of **symlinks** into the buckets does not survive install: Codex copies the plugin tree into its cache and **drops symlinks**, so the skills arrive empty.
+
+The only robust ways to give Codex a single promoted-only path are (a) **restructure** so `skills/` contains only promoted skills (moving the non-promoted buckets out — a large blast radius across `CLAUDE.md`, `scripts/link-skills.sh`, the bucket READMEs, and the local dev workflow that relies on `in-progress/` and `personal/`), or (b) **commit duplicate copies** of promoted skills into a flat directory (a sync burden and a second source of truth). Both are structural decisions, not something to bundle into shipping the Claude plugin. This is very likely the original, half-remembered reason a plugin wasn't shipped earlier: the manifest formats didn't cleanly express a curated subset of a bucketed repo.
+
+## Decision
+
+- Ship the **Claude Code plugin** now (`.claude-plugin/plugin.json` + `.claude-plugin/marketplace.json`), curated to the promoted set, as the headline v1.2 deliverable.
+- Keep **skills.sh** as the universal installer — it already serves Codex and other harnesses today, so no Codex user is left without an install path.
+- **Defer** the native Codex plugin until we decide between restructuring `skills/` to promoted-only vs. committing a generated flat copy. Revisit when Codex either supports a `skills` array / include-list or preserves symlinks on install.
+
+## Invariants this creates
+
+- Every promoted skill has an entry in `.claude-plugin/plugin.json`'s `skills` array (this already stood as a `CLAUDE.md` rule; it now also gates the plugin's contents).
+- `.claude-plugin/plugin.json`'s `version` tracks `package.json`'s version — bump both together on release. Claude uses the plugin `version` to decide when installed users see an update.
@@ -0,0 +1,20 @@
+# Model-invoked vs user-invoked
+
+Every `SKILL.md` in this repo is a skill. The one axis that splits them is **invocation** — who can reach it:
+
+- **User-invoked** — reachable **only by the human typing its name**. Set `disable-model-invocation: true` in the frontmatter (Claude Code) and `policy.allow_implicit_invocation: false` in `agents/openai.yaml` (Codex). The `description` is **human-facing**: a one-line summary read by a person browsing slash-commands. Strip trigger lists ("Use when the user says…").
+- **Model-invoked** — reachable by **model or user**. The default: omit `disable-model-invocation` and the `policy` block from `agents/openai.yaml`. The `description` is **model-facing** and keeps rich trigger phrasing ("Use when the user wants…, mentions…, asks for…") so auto-invocation fires. The test for whether a skill should stay model-invoked: _could the model usefully reach for this autonomously?_ (Reuse is the reason to extract a skill, not the test.)
+
+Each harness excludes a user-invoked skill from the model's reach in its own way, so nothing but the human can fire it — no other skill can. A user-invoked skill may invoke model-invoked skills, but it can never reach another user-invoked skill.
+
+Every skill also carries an `agents/openai.yaml` beside its `SKILL.md`. It holds Codex UI metadata — `interface.display_name` and `interface.short_description` for the skill picker — and, for user-invoked skills, the `policy.allow_implicit_invocation: false` that pairs with `disable-model-invocation`. Keep the two in sync: a skill is user-invoked in both harnesses or neither.
+
+Bucket `README.md`s and the top-level `README.md` group entries into **User-invoked** and **Model-invoked**.
+
+## Dependencies between them
+
+Dependencies are expressed as **`/skill`-style prose invocation** ("Run the `/grilling` skill"), not deep `../other-skill/FILE.md` cross-references. Shared reference docs live inside the skill that owns them; other skills reach that material by invoking the skill, not by linking across folders.
+
+## Passive vs active domain work
+
+Merely _reading_ `CONTEXT.md` for vocabulary is a one-line prose pointer, not the `domain-modeling` skill. Only the active build/sharpen discipline (challenge terms, edge-case scenarios, write ADRs, update `CONTEXT.md` inline) is `domain-modeling`.
@@ -0,0 +1,81 @@
+# Writing docs pages
+
+Every skill in `engineering/` and `productivity/` has a human-facing **docs page** at `docs/<bucket>/<skill-name>.md` — the docs tree mirrors those two bucket folders under `skills/`. It is published at `https://aihero.dev/skills-<skill-name>`; the URL is always `skills-<skill-name>` regardless of bucket, so the docs path is repo organisation only. The page is not the skill and not a copy of `SKILL.md`. Only these two buckets are promoted; the rest (`misc/`, `personal/`, `in-progress/`, `deprecated/`) ship no docs page.
+
+Most of these skills are **user-invoked**: the agent will never fire them for you, so *you* are the index that has to remember they exist and when to reach for them. That memory is **cognitive load**. The job of a docs page is to relieve it — to orient one reader around one skill so they can hold it in their head, know when to reach for it, and see where it sits in the system. The pages are collectively a distributed router; each is a node.
+
+Act whenever a promoted skill is added, renamed, or has its behaviour changed: create or re-sync its docs page. A rename moves the file too (`docs/<bucket>/<old>.md` → `docs/<bucket>/<new>.md`), because the published URL tracks the name; a skill that moves between `engineering/` and `productivity/` moves its docs file to the matching folder. Skills in `misc/`, `personal/`, `in-progress/`, and `deprecated/` get no page — none of those buckets is promoted. A skill moving *out* of one of them into `engineering/` or `productivity/` gains a page; one moving the other way loses it.
+
+Because these pages are published on `aihero.dev`, **every link is absolute** — never a repo-relative path. A link to another skill points at `https://aihero.dev/skills-<name>`; a link into the repo points at its full `https://github.com/mattpocock/skills/...` URL. A relative link that works in the repo breaks once published.
+
+There is no H1 — the published page takes its title from the slug.
+
+## Page structure
+
+Fill the template below. The **fixed frame** (Quickstart block, source link, `## What it does`, `## When to reach for it`, `## Where it fits`) appears on every page. The **adaptable middle** — `## Prerequisites` and the free-form substance sections — carries only what this particular skill earns; delete the rest.
+
+<page-template>
+
+Quickstart:
+
+```bash
+npx skills add mattpocock/skills --skill=<name>
+```
+
+```bash
+npx skills update <name>
+```
+
+[Source](https://github.com/mattpocock/skills/tree/main/skills/<bucket>/<name>)
+
+## What it does
+
+One or two plain-language paragraphs. Lead with the skill's one-sentence job, then state the **defining constraint** — the single fact that makes this skill behave differently from the obvious default (for `to-spec`: it does not interview the user again, it synthesises what is already known). Write it as a plain declarative sentence — never a labelled aside like "The defining constraint:" or "The key thing:"; the formula reads as filler. This line is the most valuable on the page; never omit it.
+
+## When to reach for it
+
+How and when you reach for the skill — two beats, both effectively always present:
+
+- **Invocation mode.** State whether you type it or the agent fires it. A user-invoked skill: "You invoke this by typing `/<name>` — the agent won't reach for it on its own." A model-invoked skill: "Type `/<name>`, or the agent reaches for it automatically when a task fits."
+- **Trigger boundary.** The index entry: "reach for this when …". Where the skill is confusable with a sibling, add the other half — "for <X> instead, use [<sibling>](https://aihero.dev/skills-<sibling>)."
+
+## Prerequisites
+
+Optional — include only when the skill needs something in place to be functional; omit the heading entirely otherwise. Covers: a **workspace it writes into** (a stateful skill like `grill-with-docs` writes `CONTEXT.md` and ADRs; `teach` builds a whole directory — say what it writes and where), **prior setup** (`triage`/`to-spec`/`to-tickets` need `setup-matt-pocock-skills` to have configured an issue tracker), or **repo-specific tooling**. A stateless skill that runs anywhere has no prerequisites — drop the section.
+
+## <free-form middle>
+
+One to three short sections, in the skill's *own vocabulary*, that make it click — choose whatever headings fit the skill: the loop it runs, the artifact it produces, the fork it makes, the one anti-pattern it kills. There is no prescribed heading; the skills are too heterogeneous for one.
+
+The single non-negotiable: **surface the skill's leading word / defining idea** — `tight` feedback loop, `deep module`, throwaway-code-answers-a-question, red-green. It pays off twice: the reader learns what the skill *is*, and learns the word they'll later think with to *reach for* it.
+
+## It's working if
+
+Optional. A short, checkable list of the observable signals that tell the reader the skill is actually doing its job — what they should see when it fires, and by absence when it hasn't. Include it when a skill has crisp tells (e.g. `to-spec` writes without re-interviewing you; a leading word reappearing in the trace); omit the heading when the signals are vague. A few bullets, no more.
+
+## Where it fits
+
+Always present. Situate the skill in the system in a sentence or two:
+
+- **Role.** Name it: a **chain step** (`grill-with-docs → to-spec → to-tickets → implement → code-review`), a **run-once setup** (`setup-matt-pocock-skills`), **periodic maintenance** (`improve-codebase-architecture`, "every few days"), or a **reach-for-it-anytime standalone** (`diagnosing-bugs`, `prototype`, `handoff`). A standalone's map is one honest sentence — far better than omitting the section.
+- **Neighbours.** The one or two siblings that matter, each with a because-clause, linked absolutely.
+- **The map.** Point to [ask-matt](https://aihero.dev/skills-ask-matt), the router over the whole set, so this page stays a node and never has to redraw the graph.
+
+</page-template>
+
+## Conventions
+
+- Explain the **why**, not the process. The page orients and situates the skill; it never reproduces the `SKILL.md` steps or template dumps — a human choosing a tool does not need the runbook.
+- Use the skill's **leading words** (_seam_, _deep module_, _tracer bullet_) so the page and the skill speak one language.
+- Keep the page itself low-load. It is documentation *about* low-cognitive-load skills; furniture (spare headings, restated links) is the thing it is arguing against.
+
+## Done when
+
+- The page exists at `docs/<bucket>/<name>.md`, and no stale page survives a rename or bucket move.
+- The Quickstart block and source link name the correct bucket and skill; the update line names the skill.
+- `## What it does` states the defining constraint, as plain prose rather than a labelled aside.
+- `## When to reach for it` states invocation mode and the trigger boundary.
+- `## Where it fits` names the role and links to `ask-matt`.
+- A prerequisite (workspace, prior setup, tooling) is stated where one exists, and the section is absent where none does.
+- The middle surfaces the leading word.
+- Every link is absolute, and every one resolves.
@@ -0,0 +1,8 @@
+# Changesets
+
+Hello and welcome! This folder has been automatically generated by `@changesets/cli`, a build tool that works
+with multi-package repos, or single-package repos to help you version and publish your code. You can
+find the full documentation for it [in our repository](https://github.com/changesets/changesets).
+
+We have a quick list of common questions to get you started engaging with this project in
+[our documentation](https://github.com/changesets/changesets/blob/main/docs/common-questions.md).
@@ -0,0 +1,10 @@
+---
+"mattpocock-skills": patch
+---
+
+Make `/ask-matt` clued-up about `/wayfinder` — the heaviest, most cognitively demanding flow.
+
+The router now sharpens the two routing mistakes people most often make with wayfinder:
+
+- **Over-reaching for it.** It's slower and denser than a single grill, so it's flagged as the heaviest flow and reserved for the idea that genuinely won't fit one session — a well-scoped feature belongs on `/grill-with-docs`, not here.
+- **Losing the way at the handoff.** When the map clears, wayfinder hands off, it doesn't build: merge onto the main flow at `/to-spec` (which collapses the map's linked decisions into a buildable plan) rather than looping the map straight into `/implement`. Straight-to-`/implement` is only for efforts that turned out genuinely small.
@@ -0,0 +1,10 @@
+---
+"mattpocock-skills": minor
+---
+
+Add Codex metadata alongside each skill's Claude Code frontmatter so the set works in both harnesses without generated copies.
+
+- Add an `agents/openai.yaml` beside every `SKILL.md` with Codex UI metadata (`interface.display_name`, `interface.short_description`).
+- Mark every user-invoked skill with `policy.allow_implicit_invocation: false`, the Codex analog of `disable-model-invocation: true`, so Codex excludes it from implicit invocation while explicit `$skill` invocation still works.
+- Document the dual-harness invocation model in `.agents/invocation.md`, `CLAUDE.md`, and the promoted-bucket READMEs.
+- Add `AGENTS.md` as a symlink to `CLAUDE.md` so Codex reads the same repo instructions.
@@ -0,0 +1,15 @@
+{
+  "$schema": "https://unpkg.com/@changesets/config@3.1.4/schema.json",
+  "changelog": [
+    "@changesets/changelog-github",
+    { "repo": "mattpocock/skills" }
+  ],
+  "commit": false,
+  "privatePackages": { "version": true, "tag": true },
+  "fixed": [],
+  "linked": [],
+  "access": "restricted",
+  "baseBranch": "main",
+  "updateInternalDependencies": "patch",
+  "ignore": []
+}
@@ -0,0 +1,12 @@
+---
+"mattpocock-skills": patch
+---
+
+Make `/setup-matt-pocock-skills` friendlier and align the local-markdown tracker with the current spec.
+
+- **Triage labels** are now asked about only when the `triage` skill is installed, and then as a single recommended-yes question ("keep the default triage labels?") instead of an override interrogation. When `triage` isn't installed, the section — and `docs/agents/triage-labels.md` — are skipped.
+- **External PRs as a request surface** is no longer a setup question. The GitHub/GitLab templates still carry the flag, defaulted off; a user can flip it in `docs/agents/issue-tracker.md` later.
+- **Domain docs** default to single-context without asking; multi-context is only offered when the repo shows monorepo signals.
+- **Local-markdown tickets** are now one file per ticket under `.scratch/<feature>/issues/<NN>-<slug>.md` — never a single combined `tickets.md`. `/to-tickets` and the local issue-tracker template now agree, and the spec file is `spec.md` (not `PRD.md`) to match `/to-spec`.
+
+Docs pages for `setup-matt-pocock-skills` and `to-tickets` re-synced.
@@ -0,0 +1,5 @@
+---
+"mattpocock-skills": patch
+---
+
+Reword **`grilling`** for general use. Its description and body no longer scope the interview to a software plan: "this plan" → "this", "enact the plan" → "act on it", and "exploring the codebase" → "exploring the environment". The technique is unchanged; it now reads as a stress-test of any plan, decision, or idea.
@@ -0,0 +1,5 @@
+---
+"mattpocock-skills": minor
+---
+
+Reword how the **`prototype`** skill handles its artifacts around a single idea: **the prototype is a primary source**. Rather than being deleted once it's answered its question, the prototype is captured as runnable evidence on a throwaway branch (`prototype/<name>`) out of main, with a context pointer to it left on the implementation issue — so the main branch keeps only the validated decision while the exploration stays findable. The answer (verdict + question) is still captured durably in an issue/ADR/commit.
@@ -0,0 +1,12 @@
+---
+"mattpocock-skills": minor
+---
+
+Ship the skill set as a native **Claude Code plugin**. The repo is now its own single-plugin marketplace, so you can subscribe to the promoted skills as a managed, read-only bundle instead of copying editable files:
+
+```
+/plugin marketplace add mattpocock/skills
+/plugin install mattpocock-skills@mattpocock
+```
+
+`.claude-plugin/plugin.json` gains full marketplace metadata (version, description, author, license, keywords) and a sibling `.claude-plugin/marketplace.json` lists the plugin. `skills.sh` remains the universal installer (and the path for Codex and other harnesses today); a native Codex plugin is deferred — see `.agents/adr/0002-ship-as-a-claude-code-plugin.md` for why.
@@ -0,0 +1,7 @@
+---
+"mattpocock-skills": patch
+---
+
+Name the `/wayfinder` unit a **decision ticket**.
+
+People kept reading a wayfinder ticket as an ordinary *implementation* ticket — a slice of a build to execute — when wayfinder uses them as **decision tickets**: questions whose resolution is a decision. The skill description and its opening line now introduce "decision ticket" (and say what makes it one), and the `ask-matt` / engineering README wayfinder blurbs and the docs page match — while "ticket" stays the everyday word once the term is established. `CONTEXT.md` records **Decision ticket** as a domain term so the "avoid: ticket" guidance no longer contradicts wayfinder's deliberate use of the word.
@@ -0,0 +1,7 @@
+---
+"mattpocock-skills": minor
+---
+
+Wayfinder now burns research tickets down with subagents instead of leaving them parked for a separately-launched session.
+
+Research stays a real ticket type — it's a genuine shared blocker that downstream decisions hang on, and that dependency is exactly what the frontier's blocking edges exist to render. What changes is how it's resolved: because research is AFK, charting doesn't stop and read it. After creating the tickets, the charting session fires a `/research` subagent for each research ticket to burn it down in parallel, capturing the findings on a throwaway `research/<name>` branch with a context pointer. Research tickets are the one exception to *one ticket per session*.
@@ -0,0 +1,5 @@
+---
+"mattpocock-skills": minor
+---
+
+Add a YAGNI scoping filter to the **`improve-codebase-architecture`** skill's Explore step. Instead of scanning the whole repo evenly, it now scopes to where change is actually landing: if you name a direction it takes it, otherwise it reads the last ~20 commit messages to bias exploration toward actively-developed paths. A deepening opportunity in code nobody touches is a refactor you'll never cash in — the leverage only pays off where you keep editing — so the report stops tidying dormant corners of the repo.
@@ -0,0 +1,23 @@
+{
+  "name": "mattpocock",
+  "owner": {
+    "name": "Matt Pocock",
+    "url": "https://www.aihero.dev"
+  },
+  "description": "Matt Pocock's skills for real engineering, as an installable Claude Code plugin.",
+  "plugins": [
+    {
+      "name": "mattpocock-skills",
+      "source": "./",
+      "description": "Matt Pocock's agent skills for real engineering — grilling, spec/ticket flows, TDD, code review, domain modelling and more.",
+      "category": "engineering",
+      "keywords": [
+        "engineering",
+        "skills",
+        "tdd",
+        "code-review",
+        "grilling"
+      ]
+    }
+  ]
+}
@@ -0,0 +1,45 @@
+{
+  "name": "mattpocock-skills",
+  "version": "1.2.0",
+  "description": "Matt Pocock's agent skills for real engineering — grilling, spec/ticket flows, TDD, code review, domain modelling and more. Plug-and-play, not vibe coding.",
+  "author": {
+    "name": "Matt Pocock",
+    "url": "https://www.aihero.dev"
+  },
+  "homepage": "https://www.aihero.dev/s/skills-newsletter",
+  "repository": "https://github.com/mattpocock/skills",
+  "license": "MIT",
+  "keywords": [
+    "engineering",
+    "skills",
+    "tdd",
+    "code-review",
+    "grilling",
+    "domain-modeling",
+    "productivity"
+  ],
+  "skills": [
+    "./skills/engineering/ask-matt",
+    "./skills/engineering/diagnosing-bugs",
+    "./skills/engineering/grill-with-docs",
+    "./skills/engineering/triage",
+    "./skills/engineering/improve-codebase-architecture",
+    "./skills/engineering/setup-matt-pocock-skills",
+    "./skills/engineering/tdd",
+    "./skills/engineering/to-spec",
+    "./skills/engineering/to-tickets",
+    "./skills/engineering/wayfinder",
+    "./skills/engineering/implement",
+    "./skills/engineering/prototype",
+    "./skills/engineering/research",
+    "./skills/engineering/domain-modeling",
+    "./skills/engineering/codebase-design",
+    "./skills/engineering/code-review",
+    "./skills/engineering/resolving-merge-conflicts",
+    "./skills/productivity/grill-me",
+    "./skills/productivity/grilling",
+    "./skills/productivity/handoff",
+    "./skills/productivity/teach",
+    "./skills/productivity/writing-great-skills"
+  ]
+}
@@ -0,0 +1,37 @@
+name: Release
+
+on:
+  push:
+    branches:
+      - main
+
+concurrency: ${{ github.workflow }}-${{ github.ref }}
+
+jobs:
+  release:
+    name: Version
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+      pull-requests: write
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: 22
+
+      - name: Install dependencies
+        run: npm ci
+
+      - name: Create Version Pull Request
+        uses: changesets/action@v1
+        with:
+          version: npx changeset version
+          publish: npx changeset tag
+          commit: "chore: version skills"
+          title: "chore: version skills"
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
@@ -0,0 +1 @@
+node_modules
@@ -0,0 +1,25 @@
+# Issue tracker integrations are limited to mainstream tools
+
+`setup-matt-pocock-skills` only offers first-class support for **mainstream** issue trackers. Requests to add support for niche, new, or single-vendor experimental trackers are out of scope.
+
+## Why this is out of scope
+
+Every issue-tracker backend hard-codes a CLI shape into the skills (commands, flags, output parsing). Each new backend is permanent maintenance surface — it has to keep working as the tool's CLI evolves, and it has to keep being tested against `/to-spec`, `/to-tickets`, `/triage`, and friends. That cost is only worth paying for trackers a meaningful fraction of users actually have.
+
+"Mainstream" is a judgment call, not a numeric bar:
+
+- GitHub, GitLab, and Backlog.md are the kind of tools we'd consider mainstream — broadly known, widely used, well past the experimental phase.
+- A brand-new agent-focused tool with a few hundred GitHub stars is not, no matter how interesting the design.
+
+Stars, age, and download counts are useful signals when making the call but none of them is the rule. The rule is: would a typical engineer recognise this tool and have plausibly chosen it for their team?
+
+The escape hatches for non-mainstream trackers already exist:
+
+- `local markdown` for lightweight in-repo tracking.
+- `other/custom` for users who want to wire something up themselves.
+
+Neither requires the core skills to know about the specific tool.
+
+## Prior requests
+
+- #99 — "Add dex as an issue tracker backend" (dex was ~3 months old and ~300 stars at the time of the request)
@@ -0,0 +1,18 @@
+# Hard limits on the number of questions during grilling
+
+The `/grill-me` skill (and grilling sessions inside other skills) does not enforce a maximum number of questions. Requests to add a configurable cap or hard ceiling are out of scope.
+
+## Why this is out of scope
+
+Grilling is intentionally open-ended. The point is to keep digging until each branch of the decision tree is resolved — some plans need three questions, some need fifty. A fixed cap would either cut off useful exploration on hard problems or feel arbitrary on easy ones.
+
+If a session feels too long, the right escape hatches already exist:
+
+- The user can stop the session at any time and accept the current state of the plan.
+- The user can tell the model to wrap up, summarise, and move on — natural-language steering is the intended control surface, not a numeric limit.
+
+Adding a hard cap would also conflate two different failure modes: a model that asks too many questions because the plan is genuinely under-specified (working as intended) vs. a model that asks redundant or low-value questions (a prompt-quality issue, not a quantity issue). The fix for the latter belongs in the skill prompt, not in a counter.
+
+## Prior requests
+
+- #44 — "Codex just asked me 200 questions"
@@ -0,0 +1,15 @@
+# Verify/Check Mode for `setup-matt-pocock-skills`
+
+This project will not add a dedicated verify/check mode (or a separate verify skill) for `setup-matt-pocock-skills`.
+
+## Why this is out of scope
+
+A second skill — or a `--verify` flag — for checking whether `docs/agents/*.md` artifacts still match the seed-template schema would duplicate work the existing setup skill already handles in conversation.
+
+The intended workflow is: **run `/setup-matt-pocock-skills` and tell it to verify your current setup.** The skill is prompt-driven, so the maintainer can scope it to a verification pass ("don't rewrite anything, just check my existing files against the current seed templates and report drift") without needing a separate code path. Adding a flag or a sibling skill would split the surface area of a feature that's already expressible through the natural-language entry point.
+
+Keeping configuration management to a single skill also avoids the maintenance cost of two skills drifting from each other when seed templates evolve.
+
+## Prior requests
+
+- #106 — Feature request: verify/check mode for setup-matt-pocock-skills
@@ -0,0 +1 @@
+CLAUDE.md
@@ -0,0 +1,116 @@
+# mattpocock-skills
+
+## 1.1.0
+
+### Minor Changes
+
+- [#406](https://github.com/mattpocock/skills/pull/406) [`930a450`](https://github.com/mattpocock/skills/commit/930a450089f77a49af09001d955db8452a4b867d) Thanks [@mattpocock](https://github.com/mattpocock)! - Bring the **`ask-matt`** router up to date with the full skill set. It now maps five skills it was missing: **`tdd`** (woven into the main flow as the red-green engine `implement` drives), **`diagnosing-bugs`** (a new "Something's broken" on-ramp — there was previously no route for a bug), **`domain-modeling`** and **`codebase-design`** (a new "Vocabulary underneath" section), and **`grilling`** (the shared interview primitive). `prototype` is fleshed out as a standalone and the description broadens from "user-invoked skills" to "the skills". A maintenance rule is added to `CLAUDE.md` so any future skill add/rename/remove or flow change triggers an `ask-matt` re-check, beside the existing docs-page re-sync rule.
+
+- [#464](https://github.com/mattpocock/skills/pull/464) [`639df6e`](https://github.com/mattpocock/skills/commit/639df6e7386dfddc739b2aecdeff37a876f2483b) Thanks [@mattpocock](https://github.com/mattpocock)! - Promote and harden **`code-review`**. The in-progress **`review`** skill is renamed to **`code-review`** and moved from `in-progress/` into `engineering/`: it now ships in the plugin, is listed in the top-level and Engineering READMEs (Model-invoked), and has a docs page at `docs/engineering/code-review.md`. The `/implement` skill and docs point at `/code-review`.
+
+  It also gains an always-on **Fowler smell baseline** on its Standards axis — a curated ~12 high-signal "Bad Smells in Code" (Mysterious Name, Duplicated Code, Feature Envy, Data Clumps, Primitive Obsession, Repeated Switches, Shotgun Surgery, Divergent Change, Speculative Generality, Message Chains, Middle Man, Refused Bequest) inlined into `SKILL.md` as a fixed baseline alongside whatever the repo documents, not a new third axis. Two binding rules keep it safe: a documented repo standard overrides the baseline, and every smell is reported as a judgement call, never a hard violation.
+
+- [#464](https://github.com/mattpocock/skills/pull/464) [`639df6e`](https://github.com/mattpocock/skills/commit/639df6e7386dfddc739b2aecdeff37a876f2483b) Thanks [@mattpocock](https://github.com/mattpocock)! - Sharpen **`grilling`** on two fronts.
+
+  **A confirmation gate.** The agent won't enact the plan until you confirm the shared understanding has been reached — turning the skill's existing "shared understanding" completion criterion into an explicit stop-gate. The `description` also recruits the pretrained **`grill`** leading word ("Grill the user relentlessly") to sharpen invocation, and the docs page is re-synced.
+
+  **Facts vs. decisions.** Grilling now splits _facts_ (look them up — explore the codebase) from _decisions_ (put each one to the human and wait for their answer). The old blanket line — "if a question can be answered by exploring the codebase, explore the codebase instead" — was written for the live-human case, but once another skill runs grilling inside a resolve-the-ticket frame it read as license to answer _decisions_ autonomously too. Separating the two keeps a grilling agent from racing ahead and answering its own questions.
+
+- [#463](https://github.com/mattpocock/skills/pull/463) [`af6d692`](https://github.com/mattpocock/skills/commit/af6d6922c3e2b5288eef155346cbe319e4ed3bd0) Thanks [@mattpocock](https://github.com/mattpocock)! - Add two adjacent Steering failure modes to **`writing-great-skills`**, both about how language you think of as "off" still steers the agent. **Negation** — the _elephant_ — is steering by prohibition: naming what _not_ to do drags the forbidden behaviour into context and makes it _more_ available, not less (_don't think of an elephant_), so the cure is to prompt the **positive**. **Negative Space** — the void — is blindness to the steering done by what you leave _out_: every decision a skill declines is delegated to the agent's priors rather than left neutral, so the cure is to read a draft for its silences and decide each omission deliberately (fill it, or leave it open as a real **branch**). Kept as two entries, not one — they carry different diagnostics and different cures — each a full `GLOSSARY.md` entry plus a `SKILL.md` failure-mode bullet, matching how every other failure mode is carried.
+
+- [`850873c`](https://github.com/mattpocock/skills/commit/850873cd73d5f81826ebf512ad35d2b1e113001f) Thanks [@mattpocock](https://github.com/mattpocock)! - Make the **`prototype`** skill model-invoked, so the agent can reach for it autonomously (and other skills can too). Its description is rewritten around the leading word _prototype_ — throwaway code that answers a design question — with one trigger per branch (state/logic sanity-check, or UI exploration).
+
+- [#409](https://github.com/mattpocock/skills/pull/409) [`0d74d01`](https://github.com/mattpocock/skills/commit/0d74d01cbc64ca27778a49b38599f70c534e76a0) Thanks [@mattpocock](https://github.com/mattpocock)! - Add the **`research`** skill — a small, model-invoked skill that spins up a **background agent** to investigate a question against **primary sources** (official docs, source code, specs, first-party APIs), then leaves a single cited Markdown file wherever the repo keeps such notes. It's delegable reading legwork: you keep working while it reads, and get back a document to grill, plan, or design against. Listed in the top-level and Engineering READMEs (Model-invoked), added to `.claude-plugin/plugin.json`, given a docs page at `docs/engineering/research.md`, and routed as a Standalone in `ask-matt`.
+
+- [#469](https://github.com/mattpocock/skills/pull/469) [`a0329ba`](https://github.com/mattpocock/skills/commit/a0329ba95751f58566ed7ab484475917a68f1629) Thanks [@mattpocock](https://github.com/mattpocock)! - Split the **`to-issues`** skill into a lean **Process** and a **Reference** section, and teach it to handle a **wide refactor** — a single mechanical change (like renaming a column) whose **blast radius** fans across the whole codebase, breaking thousands of call sites at once so no vertical slice can land green. The drafting step now points at two co-located reference blocks: the **Vertical slice rules** for ordinary tracer bullets, and **Wide refactors**, which slices the change by **expand–contract** (expand the new form beside the old, migrate call sites in batches sized by blast radius, then contract the old form away) so CI stays green batch to batch — or, when it can't, only at a final integrate-and-verify issue. The issue body template moves into Reference too.
+
+- [#464](https://github.com/mattpocock/skills/pull/464) [`386d4ff`](https://github.com/mattpocock/skills/commit/386d4ff719a7c420ad1454232d0436b01f1b8c17) Thanks [@mattpocock](https://github.com/mattpocock)! - Unify the planning skills. **`to-prd` is renamed to `to-spec`** — "spec" is now the single through-line term (it still opens with "you may know this document as a PRD" for discoverability). **`to-plan` and `to-issues` are merged into one `to-tickets` skill, and `to-issues` is deleted.**
+
+  `to-tickets` breaks a plan, spec, or conversation into a set of **tickets** — tracer-bullet vertical slices, each declaring its **blocking edges**. That one artifact reads two ways depending on the tracker `/setup-matt-pocock-skills` configured: a **local file** (`tickets.md`) writes the edges as text and you work it top-to-bottom by hand; a **real tracker** writes them as native blocking links, so any ticket whose blockers are done is on the frontier and several agents can run at once. The edges live in the ticket either way — the medium only decides whether anything acts on them in parallel.
+
+  Publishing prefers the tracker's **native sub-issues** for parent → slice and **native blocking edges** for `Blocked by` where the tracker supports them, keeping the `## Parent` / `## Blocked by` body sections as the fallback. The "What to build" template points at where a `/prototype`'s code lives rather than inlining a snippet from it.
+
+  `ask-matt`'s main flow now routes `idea → /to-spec → /to-tickets → /implement`, and there are human-facing docs pages at `docs/engineering/to-spec.md` and `docs/engineering/to-tickets.md`.
+
+- [#464](https://github.com/mattpocock/skills/pull/464) [`0557d57`](https://github.com/mattpocock/skills/commit/0557d57579d9b3d39839fdaf8d4a6542b17539ce) Thanks [@mattpocock](https://github.com/mattpocock)! - Settle wayfinder's place in the docs as a **situational on-ramp**, not the new main entry flow — the grill-led _idea → ship_ chain stays the front door (crowning wayfinder as the default spine is a v2-sized move, not a 1.1). The **`ask-matt`** router now names wayfinder's concrete triggers — a greenfield project or a huge feature build, too big for one session — and the two grill front doors (**`grill-me`**, **`grill-with-docs`**) signpost _up_ to wayfinder for the effort that's too big to hold in one session, so the on-ramp is discoverable from where a reader actually starts.
+
+- [#464](https://github.com/mattpocock/skills/pull/464) [`639df6e`](https://github.com/mattpocock/skills/commit/639df6e7386dfddc739b2aecdeff37a876f2483b) Thanks [@mattpocock](https://github.com/mattpocock)! - Graduate and reframe **`wayfinder`** — the skill for planning a huge chunk of work, more than one agent session can hold. It moves out of `in-progress/` into `engineering/` (plugin entry, top-level + Engineering READMEs under **User-invoked**, a docs page at `docs/engineering/wayfinder.md`, and a route in `ask-matt`), landing as a mature skill. The rename and reframe that got it there:
+
+  - **`decision-mapping` is renamed to `wayfinder`**, invoked as `/wayfinder`. "Decision map" was jargony and inaccurate — only one ticket type is actually a decision. The reframe charts a route through a foggy problem instead, giving one coherent leading-word frame — **fog of war**, **frontier**, **the map** — rather than an invented term layered on top.
+  - **Destination as the leading word.** Wayfinding finds the _way_ to a destination; it doesn't charge at building it. Naming the destination is the first act of charting — it fixes the scope and shapes every ticket — so the map gains a `## Destination` field every session orients to, and triage pins it before any ticket exists.
+  - **Plan, don't do.** The map produces **decisions, not deliverables**; it's done when nothing is left to decide before someone builds the thing. An effort can override this in its Notes.
+  - **The map is an index, not a store.** A decision lives in exactly one place — its ticket — so the map only gists and links, never restates; graduating fog into a ticket clears the graduated patch so nothing lingers in two places.
+  - **Collaborative by default.** The map moves off a local Markdown file onto the repo's issue tracker: a single `wayfinder:map` issue whose tickets are its child issues — one shared URL the team can watch. Sessions load the map at low resolution and zoom into tickets on demand. Wayfinder stays tracker-agnostic (GitHub, GitLab, local-markdown) behind a pointer in `docs/agents/issue-tracker.md`, and `setup-matt-pocock-skills` seeds the "Wayfinding operations" section.
+  - **Claim by assignment, not a label.** A session claims a ticket by assigning it to the driving dev — the assignee _is_ the claim — freeing the label vocabulary to `wayfinder:<type>` alone.
+  - **Native blocking.** Blocking prefers the tracker's native dependency relationship, which renders the frontier visually in the tracker's own UI so the human sees what's takeable without opening the map. GitHub and GitLab templates spell out the native recipe, with a body-convention fallback.
+  - **Fog vs. out of scope, split.** Two plainly-named map sections — `## Not yet specified` (in-scope fog that graduates as the frontier advances) and `## Out of scope` (work ruled beyond the destination, closed, never graduating) — so beyond-destination work no longer reads as takeable frontier.
+  - **A fourth `task` ticket type.** For literal manual work that blocks a decision (provisioning access, moving data, signing up for a service) — the one type that _does_ rather than decides, earning its place by unblocking a decision.
+  - **HITL / AFK ticket classification.** Every ticket type is **HITL** (human in the loop — grilling, prototype) or **AFK** (agent alone — research; task is either). A HITL ticket only resolves through the live exchange, so "wait for the human" falls out of the label — a grilling agent that answers its own questions has, by definition, broken HITL. (This fixes students' reports of `/wayfinder` grilling _itself_ instead of the human.)
+  - **No-fog early exit restored.** If the opening breadth-first grilling surfaces no fog, the journey is small enough for one session — so it stops and asks how you'd like to proceed rather than building a map nobody needs.
+
+### Patch Changes
+
+- [#464](https://github.com/mattpocock/skills/pull/464) [`639df6e`](https://github.com/mattpocock/skills/commit/639df6e7386dfddc739b2aecdeff37a876f2483b) Thanks [@mattpocock](https://github.com/mattpocock)! - Reshape **`tdd`** into a reference-only skill and add a missing anti-pattern.
+
+  **Reference-only.** The red → green → refactor loop is anchored by leading words the model already holds, so the step-by-step Workflow was largely restating the loop. Dropped the Workflow and per-cycle checklist; folded their one durable idea — vertical slices / tracer bullets — into the Anti-patterns section and a short Rules-of-the-loop list. Introduced **seam** as the leading word for where tests go: test only at pre-agreed seams, confirmed with the user before any test is written. Also dropped the refactor stage — TDD is now red → green; refactoring belongs to the review stage, so the refactor rule and `refactoring.md` moved out (its home is `code-review`).
+
+  **Tautological tests.** Added the tautological-test anti-pattern: a test whose assertion is recomputed the way the code computes it passes by construction and gives zero confidence — distinct from the implementation-coupling anti-pattern already covered. Added as a peer at the same sites: a Philosophy principle (expected values must come from an independent source of truth), a checklist gate, and a BAD/GOOD example pair in `tests.md`.
+
+- [`e00eadb`](https://github.com/mattpocock/skills/commit/e00eadb4bb32c3d5a631ead1a5ed5d6a7c5f74e2) Thanks [@mattpocock](https://github.com/mattpocock)! - Extend the **`triage`** skill to triage external pull requests, treating a PR as an issue with attached code that runs through the same roles and state machine. PRs flow inline alongside issues (gated by a per-repo setup toggle), discovery surfaces only external PRs, the bug-only "reproduce" step is generalized into a single "verify the claim" step, and a redundancy check resolves already-implemented requests to `wontfix` without polluting the out-of-scope knowledge base. `setup-matt-pocock-skills` gains the PRs-as-a-request-surface toggle for GitHub/GitLab.
+
+- [#472](https://github.com/mattpocock/skills/pull/472) [`d869d45`](https://github.com/mattpocock/skills/commit/d869d45afc32beab1c2d1350f8de5e81589512cd) Thanks [@mattpocock](https://github.com/mattpocock)! - Fix **`wayfinder`** hardcoding the issue-tracker doc path, which broke the indirection the rest of the suite relies on.
+
+  `to-issues`, `to-prd`, and `triage` never name a path — they resolve the tracker through the `### Issue tracker` block that `setup-matt-pocock-skills` writes into `CLAUDE.md` / `AGENTS.md`, which points at the tracker doc wherever it lives. Wayfinder instead pinned the literal `docs/agents/issue-tracker.md`, so in a repo that keeps its agent docs elsewhere it silently fell back to the local-markdown tracker — even one whose `CLAUDE.md` clearly declares GitHub issues. It now resolves the doc via that same pointer and reads its "Wayfinding operations" section by name, keeping the indirection consistent across the suite.
+
+## 1.0.1
+
+### Patch Changes
+
+- [`d20ee26`](https://github.com/mattpocock/skills/commit/d20ee2684e2a9442698ac3c1e0f2c5b68c4cf296) Thanks [@mattpocock](https://github.com/mattpocock)! - Make the **`teach`** skill reuse-first. Lessons are now built from reusable **components** in `./assets/` — stylesheets, quiz widgets, simulators, diagram helpers. Reuse is the default: the agent reads `./assets/` before authoring a lesson, builds from what's there, and extracts anything new and reusable into a component rather than inlining it.
+
+## 1.0.0
+
+### Major Changes
+
+- [`47bde84`](https://github.com/mattpocock/skills/commit/47bde84da032afb2e5058f997f3bbca47d321dbd) Thanks [@mattpocock](https://github.com/mattpocock)! - Add the **`ask-matt`** skill — a user-invoked router that points you at the right skill or flow for your situation.
+
+  **Breaking:** `ask-matt` routes over the other user-invoked skills in this repo, so it expects them to be installed.
+
+- [`47bde84`](https://github.com/mattpocock/skills/commit/47bde84da032afb2e5058f997f3bbca47d321dbd) Thanks [@mattpocock](https://github.com/mattpocock)! - Add the shared design skills and rewire existing skills onto them.
+
+  - New **`codebase-design`** skill — the deep-module vocabulary (module, interface, depth, seam, adapter) and the principles for putting a lot of behaviour behind a small interface. The language that previously lived in `improve-codebase-architecture/LANGUAGE.md` now lives here, generalized for reuse across skills.
+  - New **`domain-modeling`** skill — actively build and sharpen a project's domain model, stress-testing terms against the glossary and keeping `CONTEXT.md` and ADRs current.
+  - `improve-codebase-architecture` now draws its architecture vocabulary from `/codebase-design` and its domain model from `/domain-modeling`.
+  - `tdd` now leans on `/codebase-design` for interface-design guidance — its inline `deep-modules.md` / `interface-design.md` notes were removed in favour of the shared skill.
+  - `grill-with-docs` now builds the domain model inline via `/domain-modeling`.
+
+  **Breaking:** these skills now depend on the new `codebase-design` / `domain-modeling` skills, so you must install them too.
+
+- [`47bde84`](https://github.com/mattpocock/skills/commit/47bde84da032afb2e5058f997f3bbca47d321dbd) Thanks [@mattpocock](https://github.com/mattpocock)! - Remove the **`caveman`** and **`zoom-out`** skills.
+
+  - `caveman` was a duplicate of another skill I was testing and was never meant to be public.
+  - `zoom-out` went unused in practice, so it's been removed from the repo.
+
+  **Breaking:** both skills have been removed.
+
+- [`47bde84`](https://github.com/mattpocock/skills/commit/47bde84da032afb2e5058f997f3bbca47d321dbd) Thanks [@mattpocock](https://github.com/mattpocock)! - Rename the **`diagnose`** skill to **`diagnosing-bugs`**.
+
+  **Breaking:** invoke it as `/diagnosing-bugs` — the old `/diagnose` name no longer exists.
+
+- [`47bde84`](https://github.com/mattpocock/skills/commit/47bde84da032afb2e5058f997f3bbca47d321dbd) Thanks [@mattpocock](https://github.com/mattpocock)! - Replace **`write-a-skill`** with **`writing-great-skills`**.
+
+  - Removed `write-a-skill`.
+  - Added `writing-great-skills` (plus its `GLOSSARY.md`) — a reference for writing and editing skills well: the vocabulary and principles that make a skill predictable, hunting no-ops down to the sentence level.
+  - Exposed `grilling` as a model-invoked skill — the reusable interview loop behind `grill-me` and `grill-with-docs`.
+
+  **Breaking:** `write-a-skill` has been removed; use `writing-great-skills` instead.
+
+### Minor Changes
+
+- [`47bde84`](https://github.com/mattpocock/skills/commit/47bde84da032afb2e5058f997f3bbca47d321dbd) Thanks [@mattpocock](https://github.com/mattpocock)! - Add the **`resolving-merge-conflicts`** skill — a loop for resolving an in-progress git merge or rebase conflict. Standalone, with no dependencies on other skills.
+
+- [`47bde84`](https://github.com/mattpocock/skills/commit/47bde84da032afb2e5058f997f3bbca47d321dbd) Thanks [@mattpocock](https://github.com/mattpocock)! - Rename the skill taxonomy from **Commands / Skills** to **User-invoked / Model-invoked** across the docs, and add `docs/invocation.md` defining the split: user-invoked skills are reachable only when you type them and exist to orchestrate; model-invoked skills can also be reached automatically when the task fits. A user-invoked skill may invoke model-invoked skills, but never another user-invoked one.
+
+### Patch Changes
+
+- [`47bde84`](https://github.com/mattpocock/skills/commit/47bde84da032afb2e5058f997f3bbca47d321dbd) Thanks [@mattpocock](https://github.com/mattpocock)! - Tighten the **`review`** skill: fail-fast ref check, single-sourced rules, and no-op cuts.
@@ -0,0 +1,24 @@
+Skills are organized into bucket folders under `skills/`:
+
+- `engineering/` — daily code work
+- `productivity/` — daily non-code workflow tools
+- `misc/` — kept around but rarely used, not promoted
+- `personal/` — tied to my own setup, not promoted
+- `in-progress/` — drafts not yet ready to ship
+- `deprecated/` — no longer used
+
+Every skill in `engineering/` or `productivity/` (the **promoted** buckets) must have a reference in the top-level `README.md` and an entry in `.claude-plugin/plugin.json`'s `skills` array (the Claude Code plugin ships exactly the promoted set). Skills in `misc/`, `personal/`, `in-progress/`, and `deprecated/` must not appear in either.
+
+The repo is also its own single-plugin Claude Code marketplace: `.claude-plugin/marketplace.json` lists the one `mattpocock-skills` plugin. When bumping the release version, keep `.claude-plugin/plugin.json`'s `version` in sync with `package.json`'s — Claude uses the plugin `version` to decide when installed users see an update. Run `claude plugin validate . --strict` after touching either manifest. Why a Claude plugin but not (yet) a Codex one lives in [.agents/adr/0002-ship-as-a-claude-code-plugin.md](./.agents/adr/0002-ship-as-a-claude-code-plugin.md).
+
+Each skill entry in the top-level `README.md` must link the skill name to its `SKILL.md`.
+
+Each bucket folder has a `README.md` that lists every skill in the bucket with a one-line description, with the skill name linked to its `SKILL.md`. The promoted buckets' `README.md`s and the top-level `README.md` group entries into **User-invoked** and **Model-invoked**; non-promoted bucket `README.md`s (`misc/`, `personal/`) use a flat list.
+
+Skills in `engineering/` and `productivity/` also have a human-facing docs page at `docs/<bucket>/<skill-name>.md` (the docs tree mirrors those two bucket folders under `skills/`). The published URL is `https://aihero.dev/skills-<skill-name>` regardless of bucket — the docs path is repo organisation only. When you add, rename, or change the behaviour of a skill in `engineering/` or `productivity/`, create or re-sync its docs page following [.agents/writing-docs.md](./.agents/writing-docs.md). Skills in the non-promoted buckets (`misc/`, `personal/`, `in-progress/`, `deprecated/`) get **no** docs page.
+
+Every `SKILL.md` is either user-invoked (`disable-model-invocation: true` plus `policy.allow_implicit_invocation: false` in `agents/openai.yaml`, reachable only by the human) or model-invoked (model- or user-reachable). See [.agents/invocation.md](./.agents/invocation.md).
+
+[`ask-matt`](./skills/engineering/ask-matt/SKILL.md) is the router that maps every user-reachable skill and how they relate. The same trigger that re-syncs a docs page applies to it: whenever you add, rename, remove, or change how a user-reachable skill fits the flows, re-read `ask-matt`'s `SKILL.md` and update it so the map stays accurate — a new skill it never mentions, or a stale one it still routes to, is a router that lies.
+
+To (re)link every skill into the local harness skill directories (`~/.claude/skills`, `~/.agents/skills`), run `scripts/link-skills.sh`. Each entry is a symlink into this repo, so a `git pull` keeps installed skills current; re-run the script after adding, removing, or renaming a skill.
@@ -0,0 +1,30 @@
+# Matt Pocock Skills
+
+A collection of agent skills (slash commands and behaviors) loaded by Claude Code. Skills are organized into buckets and consumed by per-repo configuration emitted by `/setup-matt-pocock-skills`.
+
+## Language
+
+**Issue tracker**:
+The tool that hosts a repo's issues — GitHub Issues, Linear, a local `.scratch/` markdown convention, or similar. Skills like `to-tickets`, `to-spec`, `triage`, and `qa` read from and write to it.
+_Avoid_: backlog manager, backlog backend, issue host
+
+**Issue**:
+A single tracked unit of work inside an **Issue tracker** — a bug, task, spec, or slice produced by `to-tickets`.
+_Avoid_: ticket (use only when quoting external systems that call them tickets, or for a **Decision ticket** — see below)
+
+**Decision ticket**:
+A `wayfinder` unit — a child **Issue** of a `wayfinder:map` holding a *question* whose resolution is a decision, not a slice of a build to execute. The **decision** qualifier is what keeps it distinct from an implementation ticket; `wayfinder` introduces the term, then uses "ticket".
+
+**Triage role**:
+A canonical state-machine label applied to an **Issue** during triage (e.g. `needs-triage`, `ready-for-afk`). Each role maps to a real label string in the **Issue tracker** via `docs/agents/triage-labels.md`.
+
+## Relationships
+
+- An **Issue tracker** holds many **Issues**
+- An **Issue** carries one **Triage role** at a time
+- A **Decision ticket** is an **Issue** (a child of a `wayfinder:map`)
+
+## Flagged ambiguities
+
+- "backlog" was previously used to mean both the *tool* hosting issues and the *body of work* inside it — resolved: the tool is the **Issue tracker**; "backlog" is no longer used as a domain term.
+- "backlog backend" / "backlog manager" — resolved: collapsed into **Issue tracker**.
@@ -1,115 +1,213 @@
-# Agent Skills For Real Engineers
+<p>
+  <a href="https://www.aihero.dev/s/skills-newsletter">
+    <picture>
+      <source media="(prefers-color-scheme: dark)" srcset="https://res.cloudinary.com/total-typescript/image/upload/v1777382277/skills-repo-dark_2x.png">
+      <source media="(prefers-color-scheme: light)" srcset="https://res.cloudinary.com/total-typescript/image/upload/v1777382277/skill-repo-light_2x.png">
+      <img alt="Skills" src="https://res.cloudinary.com/total-typescript/image/upload/v1777382277/skill-repo-light_2x.png" width="369">
+    </picture>
+  </a>
+</p>
+
+# Skills For Real Engineers
+
+[![skills.sh](https://skills.sh/b/mattpocock/skills)](https://skills.sh/mattpocock/skills)

 My agent skills that I use every day to do real engineering - not vibe coding.

+Developing real applications is hard. Approaches like GSD, BMAD, and Spec-Kit try to help by owning the process. But while doing so, they take away your control and make bugs in the process hard to resolve.
+
+These skills are designed to be small, easy to adapt, and composable. They work with any model. They're based on decades of engineering experience. Hack around with them. Make them your own. Enjoy.
+
 If you want to keep up with changes to these skills, and any new ones I create, you can join ~60,000 other devs on my newsletter:

 [Sign Up To The Newsletter](https://www.aihero.dev/s/skills-newsletter)

-## Planning & Design
+## Quickstart (30-second setup)

-These skills help you think through problems before writing code.
+1. Run the skills.sh installer:

- **to-prd** — Turn the current conversation context into a PRD and submit it as a GitHub issue. No interview — just synthesizes what you've already discussed.
+```bash
+npx skills@latest add mattpocock/skills
+```

-  ```
-  npx skills@latest add mattpocock/skills/to-prd
-  ```
+2. Pick the skills you want, and which coding agents you want to install them on. **Make sure you select `/setup-matt-pocock-skills`**.

- **to-issues** — Break any plan, spec, or PRD into independently-grabbable GitHub issues using vertical slices.
+3. Run `/setup-matt-pocock-skills` in your agent. It will:
+   - Ask you which issue tracker you want to use (GitHub, Linear, or local files)
+   - Ask you what labels you apply to tickets when you triage them (`/triage` uses labels)
+   - Ask you where you want to save any docs we create

-  ```
-  npx skills@latest add mattpocock/skills/to-issues
-  ```
+4. Bam - you're ready to go.

- **grill-me** — Get relentlessly interviewed about a plan or design until every branch of the decision tree is resolved.
+## Install as a Claude Code plugin

-  ```
-  npx skills@latest add mattpocock/skills/grill-me
-  ```
+Prefer a plug-and-play install you don't maintain by hand? These skills also ship as a native [Claude Code plugin](https://code.claude.com/docs/en/plugins). Instead of copying editable files into your repo, the plugin installs the whole skill set as a managed bundle that updates when I ship a new version — you subscribe rather than fork.

- **design-an-interface** — Generate multiple radically different interface designs for a module using parallel sub-agents.
+Inside Claude Code:

-  ```
-  npx skills@latest add mattpocock/skills/design-an-interface
-  ```
+```
+/plugin marketplace add mattpocock/skills
+/plugin install mattpocock-skills@mattpocock
+```

- **request-refactor-plan** — Create a detailed refactor plan with tiny commits via user interview, then file it as a GitHub issue.
+Or from your shell:

-  ```
-  npx skills@latest add mattpocock/skills/request-refactor-plan
-  ```
+```bash
+claude plugin marketplace add mattpocock/skills
+claude plugin install mattpocock-skills@mattpocock
+```

-## Development
+Then run `/setup-matt-pocock-skills` once per repo, exactly as in the quickstart above.

-These skills help you write, refactor, and fix code.
+Two ways to install, two philosophies:

- **tdd** — Test-driven development with a red-green-refactor loop. Builds features or fixes bugs one vertical slice at a time.
+- **[skills.sh](https://skills.sh/mattpocock/skills)** copies the skills into your project so you can hack on them and make them your own.
+- **The plugin** keeps them as a read-only, always-current bundle you don't edit — best when you just want my set to work and follow along as it evolves.

-  ```
-  npx skills@latest add mattpocock/skills/tdd
-  ```
+> Using Codex or another agent? The [skills.sh installer](https://skills.sh/mattpocock/skills) already installs these skills into Codex and other Agent-Skills-standard harnesses today. A native Codex plugin is on the roadmap — see [`.agents/adr/0002-ship-as-a-claude-code-plugin.md`](./.agents/adr/0002-ship-as-a-claude-code-plugin.md).

- **triage-issue** — Investigate a bug by exploring the codebase, identify the root cause, and file a GitHub issue with a TDD-based fix plan.
+## Why These Skills Exist

-  ```
-  npx skills@latest add mattpocock/skills/triage-issue
-  ```
+I built these skills as a way to fix common failure modes I see with Claude Code, Codex, and other coding agents.

- **improve-codebase-architecture** — Find deepening opportunities in a codebase, informed by the domain language in `CONTEXT.md` and the decisions in `docs/adr/`.
+### #1: The Agent Didn't Do What I Want

-  ```
-  npx skills@latest add mattpocock/skills/improve-codebase-architecture
-  ```
+> "No-one knows exactly what they want"
+>
+> David Thomas & Andrew Hunt, [The Pragmatic Programmer](https://www.amazon.co.uk/Pragmatic-Programmer-Anniversary-Journey-Mastery/dp/B0833F1T3V)

- **migrate-to-shoehorn** — Migrate test files from `as` type assertions to @total-typescript/shoehorn.
+**The Problem**. The most common failure mode in software development is misalignment. You think the dev knows what you want. Then you see what they've built - and you realize it didn't understand you at all.

-  ```
-  npx skills@latest add mattpocock/skills/migrate-to-shoehorn
-  ```
+This is just the same in the AI age. There is a communication gap between you and the agent. The fix for this is a **grilling session** - getting the agent to ask you detailed questions about what you're building.

- **scaffold-exercises** — Create exercise directory structures with sections, problems, solutions, and explainers.
+**The Fix** is to use:

-  ```
-  npx skills@latest add mattpocock/skills/scaffold-exercises
-  ```
+- [`/grill-me`](./skills/productivity/grill-me/SKILL.md) - for non-code uses
+- [`/grill-with-docs`](./skills/engineering/grill-with-docs/SKILL.md) - same as [`/grill-me`](./skills/productivity/grill-me/SKILL.md), but adds more goodies (see below)

-## Tooling & Setup
+These are my most popular skills. They help you align with the agent before you get started, and think deeply about the change you're making. Use them _every_ time you want to make a change.

- **setup-pre-commit** — Set up Husky pre-commit hooks with lint-staged, Prettier, type checking, and tests.
+### #2: The Agent Is Way Too Verbose

-  ```
-  npx skills@latest add mattpocock/skills/setup-pre-commit
-  ```
+> With a ubiquitous language, conversations among developers and expressions of the code are all derived from the same domain model.
+>
+> Eric Evans, [Domain-Driven-Design](https://www.amazon.co.uk/Domain-Driven-Design-Tackling-Complexity-Software/dp/0321125215)

- **git-guardrails-claude-code** — Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, etc.) before they execute.
+**The Problem**: At the start of a project, devs and the people they're building the software for (the domain experts) are usually speaking different languages.

-  ```
-  npx skills@latest add mattpocock/skills/git-guardrails-claude-code
-  ```
+I felt the same tension with my agents. Agents are usually dropped into a project and asked to figure out the jargon as they go. So they use 20 words where 1 will do.

-## Writing & Knowledge
+**The Fix** for this is a shared language. It's a document that helps agents decode the jargon used in the project.

- **write-a-skill** — Create new skills with proper structure, progressive disclosure, and bundled resources.
+<details>
+<summary>
+Example
+</summary>

-  ```
-  npx skills@latest add mattpocock/skills/write-a-skill
-  ```
+Here's an example [`CONTEXT.md`](https://github.com/mattpocock/course-video-manager/blob/076a5a7a182db0fe1e62971dd7a68bcadf010f1c/CONTEXT.md), from my `course-video-manager` repo. Which one is easier to read?

- **edit-article** — Edit and improve articles by restructuring sections, improving clarity, and tightening prose.
+- **BEFORE**: "There's a problem when a lesson inside a section of a course is made 'real' (i.e. given a spot in the file system)"
+- **AFTER**: "There's a problem with the materialization cascade"

-  ```
-  npx skills@latest add mattpocock/skills/edit-article
-  ```
+This concision pays off session after session.

- **ubiquitous-language** — Extract a DDD-style ubiquitous language glossary from the current conversation.
+</details>

-  ```
-  npx skills@latest add mattpocock/skills/ubiquitous-language
-  ```
+This is built into [`/grill-with-docs`](./skills/engineering/grill-with-docs/SKILL.md). It's a grilling session, but that helps you build a shared language with the AI, and document hard-to-explain decisions in ADR's.

- **obsidian-vault** — Search, create, and manage notes in an Obsidian vault with wikilinks and index notes.
+It's hard to explain how powerful this is. It might be the single coolest technique in this repo. Try it, and see.

-  ```
-  npx skills@latest add mattpocock/skills/obsidian-vault
-  ```
+> [!TIP]
+> A shared language has many other benefits than reducing verbosity:
+>
+> - **Variables, functions and files are named consistently**, using the shared language
+> - As a result, the **codebase is easier to navigate** for the agent
+> - The agent also **spends fewer tokens on thinking**, because it has access to a more concise language
+
+### #3: The Code Doesn't Work
+
+> "Always take small, deliberate steps. The rate of feedback is your speed limit. Never take on a task that’s too big."
+>
+> David Thomas & Andrew Hunt, [The Pragmatic Programmer](https://www.amazon.co.uk/Pragmatic-Programmer-Anniversary-Journey-Mastery/dp/B0833F1T3V)
+
+**The Problem**: Let's say that you and the agent are aligned on what to build. What happens when the agent _still_ produces crap?
+
+It's time to look at your feedback loops. Without feedback on how the code it produces actually runs, the agent will be flying blind.
+
+**The Fix**: You need the usual tranche of feedback loops: static types, browser access, and automated tests.
+
+For automated tests, a red-green-refactor loop is critical. This is where the agent writes a failing test first, then fixes the test. This helps give the agent a consistent level of feedback that results in far better code.
+
+I've built a **[`/tdd`](./skills/engineering/tdd/SKILL.md) skill** you can slot into any project. It encourages red-green-refactor and gives the agent plenty of guidance on what makes good and bad tests.
+
+For debugging, I've also built a **[`/diagnosing-bugs`](./skills/engineering/diagnosing-bugs/SKILL.md)** skill that wraps best debugging practices into a simple loop.
+
+### #4: We Built A Ball Of Mud
+
+> "Invest in the design of the system _every day_."
+>
+> Kent Beck, [Extreme Programming Explained](https://www.amazon.co.uk/Extreme-Programming-Explained-Embrace-Change/dp/0321278658)
+
+> "The best modules are deep. They allow a lot of functionality to be accessed through a simple interface."
+>
+> John Ousterhout, [A Philosophy Of Software Design](https://www.amazon.co.uk/Philosophy-Software-Design-2nd/dp/173210221X)
+
+**The Problem**: Most apps built with agents are complex and hard to change. Because agents can radically speed up coding, they also accelerate software entropy. Codebases get more complex at an unprecedented rate.
+
+**The Fix** for this is a radical new approach to AI-powered development: caring about the design of the code.
+
+This is built in to every layer of these skills:
+
+- [`/to-spec`](./skills/engineering/to-spec/SKILL.md) quizzes you about which modules you're touching before creating a spec
+
+And crucially, [`/improve-codebase-architecture`](./skills/engineering/improve-codebase-architecture/SKILL.md) helps you rescue a codebase that has become a ball of mud. I recommend running it on your codebase once every few days.
+
+### Summary
+
+Software engineering fundamentals matter more than ever. These skills are my best effort at condensing these fundamentals into repeatable practices, to help you ship the best apps of your career. Enjoy.
+
+## Reference
+
+These split on one axis — who can invoke them. **User-invoked** skills are reachable only when you type them (e.g. `/grill-me`); their job is to orchestrate. **Model-invoked** skills can be invoked by you _or_ reached for automatically by the agent when the task fits; they hold the reusable discipline. A user-invoked skill may invoke model-invoked skills, but never another user-invoked one.
+
+### Engineering
+
+Skills I use daily for code work.
+
+**User-invoked**
+
+- **[ask-matt](./skills/engineering/ask-matt/SKILL.md)** — Ask which skill or flow fits your situation. A router over the user-invoked skills in this repo.
+- **[grill-with-docs](./skills/engineering/grill-with-docs/SKILL.md)** — Grilling session that also builds your project's domain model, sharpening terminology and updating `CONTEXT.md` and ADRs inline.
+- **[triage](./skills/engineering/triage/SKILL.md)** — Move issues through a state machine of triage roles.
+- **[improve-codebase-architecture](./skills/engineering/improve-codebase-architecture/SKILL.md)** — Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
+- **[setup-matt-pocock-skills](./skills/engineering/setup-matt-pocock-skills/SKILL.md)** — Configure this repo for the engineering skills (issue tracker, triage labels, domain doc layout). Run once per repo before using the other engineering skills.
+- **[to-spec](./skills/engineering/to-spec/SKILL.md)** — Turn the current conversation into a spec and publish it to the issue tracker. No interview — just synthesizes what you've already discussed.
+- **[to-tickets](./skills/engineering/to-tickets/SKILL.md)** — Break any plan, spec, or conversation into a set of tracer-bullet tickets, each declaring its blocking edges — written as text in a local file, or as native blocking links on a real tracker.
+- **[implement](./skills/engineering/implement/SKILL.md)** — Build the work described by a spec or set of tickets, driving `/tdd` at pre-agreed seams and closing out with `/code-review` before committing.
+- **[wayfinder](./skills/engineering/wayfinder/SKILL.md)** — Plan a huge chunk of work, more than one agent session can hold, as a shared map of investigation tickets on the issue tracker — resolve them one at a time until the way to the destination is clear.
+
+**Model-invoked**
+
+- **[prototype](./skills/engineering/prototype/SKILL.md)** — Build a throwaway prototype to answer a design question — a runnable terminal app for state/logic questions, or several radically different UI variations toggleable from one route.
+- **[diagnosing-bugs](./skills/engineering/diagnosing-bugs/SKILL.md)** — Disciplined diagnosis loop for hard bugs and performance regressions: reproduce → minimise → hypothesise → instrument → fix → regression-test.
+- **[research](./skills/engineering/research/SKILL.md)** — Investigate a question against high-trust primary sources and capture the findings as a cited Markdown file in the repo, run as a background agent.
+- **[tdd](./skills/engineering/tdd/SKILL.md)** — Test-driven development with a red-green-refactor loop. Builds features or fixes bugs one vertical slice at a time.
+- **[domain-modeling](./skills/engineering/domain-modeling/SKILL.md)** — Actively build and sharpen a project's domain model — challenge terms against the glossary, stress-test with edge-case scenarios, and update `CONTEXT.md` and ADRs inline.
+- **[codebase-design](./skills/engineering/codebase-design/SKILL.md)** — Shared discipline and vocabulary for designing deep modules: a lot of behaviour behind a small interface, placed at a clean seam, testable through that interface.
+- **[code-review](./skills/engineering/code-review/SKILL.md)** — Two-axis review of the diff since a fixed point: **Standards** (does it follow the repo's coding standards, plus a Fowler smell baseline?) and **Spec** (does it faithfully implement the originating issue/PRD?), run as parallel sub-agents so neither pollutes the other.
+- **[resolving-merge-conflicts](./skills/engineering/resolving-merge-conflicts/SKILL.md)** — Work through an in-progress git merge or rebase conflict hunk by hunk, resolving by intent traced to each side's primary source, then finish the operation — never `--abort`.
+
+### Productivity
+
+General workflow tools, not code-specific.
+
+**User-invoked**
+
+- **[grill-me](./skills/productivity/grill-me/SKILL.md)** — Get relentlessly interviewed about a plan or design until every branch of the decision tree is resolved.
+- **[handoff](./skills/productivity/handoff/SKILL.md)** — Compact the current conversation into a handoff document so another agent can continue the work.
+- **[teach](./skills/productivity/teach/SKILL.md)** — Teach the user a new skill or concept over multiple sessions, using the current directory as a stateful teaching workspace.
+- **[writing-great-skills](./skills/productivity/writing-great-skills/SKILL.md)** — Reference for writing and editing skills well: the vocabulary and principles that make a skill predictable.
+
+**Model-invoked**
+
+- **[grilling](./skills/productivity/grilling/SKILL.md)** — Interview the user relentlessly about a plan, decision, or idea until every branch of the decision tree is resolved. The reusable loop behind `grill-me` and `grill-with-docs`.
@@ -1,49 +0,0 @@
---
-name: caveman
-description: >
-  Ultra-compressed communication mode. Cuts token usage ~75% by dropping
-  filler, articles, and pleasantries while keeping full technical accuracy.
-  Use when user says "caveman mode", "talk like caveman", "use caveman",
-  "less tokens", "be brief", or invokes /caveman.
---
-
-Respond terse like smart caveman. All technical substance stay. Only fluff die.
-
-## Persistence
-
-ACTIVE EVERY RESPONSE once triggered. No revert after many turns. No filler drift. Still active if unsure. Off only when user says "stop caveman" or "normal mode".
-
-## Rules
-
-Drop: articles (a/an/the), filler (just/really/basically/actually/simply), pleasantries (sure/certainly/of course/happy to), hedging. Fragments OK. Short synonyms (big not extensive, fix not "implement a solution for"). Abbreviate common terms (DB/auth/config/req/res/fn/impl). Strip conjunctions. Use arrows for causality (X -> Y). One word when one word enough.
-
-Technical terms stay exact. Code blocks unchanged. Errors quoted exact.
-
-Pattern: `[thing] [action] [reason]. [next step].`
-
-Not: "Sure! I'd be happy to help you with that. The issue you're experiencing is likely caused by..."
-Yes: "Bug in auth middleware. Token expiry check use `<` not `<=`. Fix:"
-
-### Examples
-
-**"Why React component re-render?"**
-
-> Inline obj prop -> new ref -> re-render. `useMemo`.
-
-**"Explain database connection pooling."**
-
-> Pool = reuse DB conn. Skip handshake -> fast under load.
-
-## Auto-Clarity Exception
-
-Drop caveman temporarily for: security warnings, irreversible action confirmations, multi-step sequences where fragment order risks misread, user asks to clarify or repeats question. Resume caveman after clear part done.
-
-Example -- destructive op:
-
-> **Warning:** This will permanently delete all rows in the `users` table and cannot be undone.
->
-> ```sql
-> DROP TABLE users;
-> ```
->
-> Caveman resume. Verify backup exist first.
@@ -0,0 +1,31 @@
+Quickstart:
+
+```bash
+npx skills add mattpocock/skills --skill=ask-matt
+```
+
+```bash
+npx skills update ask-matt
+```
+
+[Source](https://github.com/mattpocock/skills/tree/main/skills/engineering/ask-matt)
+
+## What it does
+
+`ask-matt` is the router over the skills in this repo. You describe the situation you're in; it tells you which skill or flow fits and in what order to run them.
+
+It **does no work itself**. It doesn't grill, write a spec, or fix anything — it only orients. It exists for the **user-invoked** skills above all: nothing fires those for you, so *you* have to remember they exist, and `ask-matt` is the memory you offload that to. It also points at the model-invoked skills you'd reach for by name — `/tdd`, `/diagnosing-bugs`, `/prototype`, `/code-review`, and the two vocabulary references, `/domain-modeling` and `/codebase-design`. It answers "which one, and when", then hands you off to the skill that actually does the job.
+
+## When to reach for it
+
+You invoke this by typing `/ask-matt` — the agent won't reach for it on its own.
+
+Reach for it whenever you're unsure which skill or flow a situation calls for: you have an idea and don't know where to start, a pile of bug reports and don't know if they're for `/triage`, or two skills that look interchangeable and you can't tell them apart. If you already know the skill you want, skip the router and invoke it directly.
+
+## Flows, not just skills
+
+The idea `ask-matt` gives you to think with is the **flow** — a path *through* the skills rather than a single one. Most work runs along one **main flow** (idea → ship: grill → spec → tickets → implement → review), two **on-ramps** merge onto it (a triage lane for incoming bugs and requests; a codebase-health lane that generates ideas), and everything else is a **standalone** you reach for on its own. Ask a question and you get placed on the right flow, at the right step — not just handed a tool.
+
+## Where it fits
+
+`ask-matt` is the **router** — the standalone map that sits over the whole set. It is the node every other docs page links back to as [ask-matt](https://aihero.dev/skills-ask-matt), so it never sits *in* a chain; it points *into* every chain. From here you'll most often land on [grill-with-docs](https://aihero.dev/skills-grill-with-docs), the head of the main flow, or [triage](https://aihero.dev/skills-triage), the on-ramp for work you didn't create. When even the router's own picture is stale, its [Source](https://github.com/mattpocock/skills/tree/main/skills/engineering/ask-matt) is the map of record.
@@ -0,0 +1,47 @@
+Quickstart:
+
+```bash
+npx skills add mattpocock/skills --skill=code-review
+```
+
+```bash
+npx skills update code-review
+```
+
+[Source](https://github.com/mattpocock/skills/tree/main/skills/engineering/code-review)
+
+## What it does
+
+`code-review` reviews the diff between `HEAD` and a fixed point you supply — a commit, branch, tag, or merge-base — along two separate axes: **Standards** (does the code follow this repo's documented conventions?) and **Spec** (does it implement what the originating issue or spec asked for?). It runs each axis as its own parallel sub-agent and reports them side by side. It never merges or re-ranks the two sets of findings — keeping them separate is the whole point, because a change can pass one axis and fail the other, and a single blended verdict lets one mask the other.
+
+## When to reach for it
+
+Type `/code-review`, or the agent reaches for it automatically when you ask to review a branch, a PR, work-in-progress changes, or anything "since X".
+
+Reach for this when there is a diff to judge against a known-good point and you want the two questions — *is it built right?* and *is it the right thing?* — answered independently. It runs at the end of the build loop; for actually writing the code test-first, use [tdd](https://aihero.dev/skills-tdd), and for building a whole spec into code use [implement](https://aihero.dev/skills-implement), which runs its own `/code-review` pass before committing.
+
+## Prerequisites
+
+The **Spec** axis needs somewhere to find the originating spec — an issue reference in the commit messages, a path you pass in, or a spec under `docs/`/`specs/`. That issue-tracker wiring comes from [setup-matt-pocock-skills](https://aihero.dev/skills-setup-matt-pocock-skills); without a spec the Spec axis simply skips and says so. The **Standards** axis needs nothing set up — it always carries a built-in Fowler smell baseline even in a repo that documents no conventions.
+
+## Two axes, never merged
+
+The defining idea is the **two axes**. **Standards** asks whether the diff conforms to how this repo writes code — its `CODING_STANDARDS.md` or `CONTRIBUTING.md`, plus a fixed baseline of ~12 Fowler code smells (Mysterious Name, Duplicated Code, Feature Envy, Data Clumps, …). Two rules keep the baseline safe: a documented repo standard always overrides it, and every smell is a judgement call, never a hard violation. **Spec** asks the orthogonal question — does the code do what the issue or spec actually asked, without missing requirements or smuggling in scope creep?
+
+They run as parallel sub-agents so neither pollutes the other's context, and the final report presents them under separate `## Standards` and `## Spec` headings with a per-axis summary. There is deliberately no single winner across axes.
+
+## It's working if
+
+- It pins and confirms the fixed point first (`git rev-parse`), failing fast on a bad ref or empty diff rather than inside the sub-agents.
+- Standards and Spec findings arrive in two distinct blocks, each citing its source — a repo standard or baseline smell for one, a quoted spec line for the other.
+- When no spec can be found, the Spec axis reports "no spec available" instead of inventing requirements.
+
+## Where it fits
+
+`code-review` is the review step at the tail of the main build chain:
+
+```txt
+grill-with-docs → to-spec → to-tickets → implement → code-review
+```
+
+Its closest neighbour is [implement](https://aihero.dev/skills-implement), which drives the build and calls this as its own review pass before committing; upstream, the spec it checks against is produced by [to-spec](https://aihero.dev/skills-to-spec) and [to-tickets](https://aihero.dev/skills-to-tickets). When you're unsure which skill or flow fits, [ask-matt](https://aihero.dev/skills-ask-matt) routes you.
@@ -0,0 +1,43 @@
+Quickstart:
+
+```bash
+npx skills add mattpocock/skills --skill=codebase-design
+```
+
+```bash
+npx skills update codebase-design
+```
+
+[Source](https://github.com/mattpocock/skills/tree/main/skills/engineering/codebase-design)
+
+## What it does
+
+`codebase-design` gives you a shared, precise vocabulary for designing **deep modules** — a lot of behaviour hidden behind a small interface, placed at a clean seam, testable through that interface.
+
+It is a **language, not a procedure**. It doesn't restructure your code or hand you a refactor plan — it fixes the words (module, interface, depth, seam, adapter, leverage, locality) so that every design conversation and every other skill that touches design speaks the same way. Consistent language is the whole point; "component," "service," "API," and "boundary" are deliberately banned because they blur the distinctions that matter.
+
+## When to reach for it
+
+Type `/codebase-design`, or the agent reaches for it automatically when a task fits.
+
+Reach for it when you're designing or improving a module's interface, hunting for deepening opportunities, deciding where a seam goes, or making code more testable and AI-navigable. Other skills pull it in whenever they need the deep-module vocabulary. If you want to sharpen the project's *domain* terms rather than its module design, use [domain-modeling](https://aihero.dev/skills-domain-modeling) instead; to run a whole architecture pass over an existing codebase, use [improve-codebase-architecture](https://aihero.dev/skills-improve-codebase-architecture).
+
+## Deep, not shallow
+
+A module is **deep** when a large amount of behaviour sits behind a small interface, and **shallow** when the interface is nearly as complex as the implementation. Depth is measured as **leverage** — how much a caller (or a test) can exercise per unit of interface they have to learn. Crucially, depth is a property of the *interface*, not the implementation: a deep module can be internally composed of small, swappable parts that just never surface to callers.
+
+Two checks do most of the work. The **deletion test**: imagine deleting the module — if complexity vanishes, it was a pass-through; if it reappears across N callers, it was earning its keep. And **one adapter means a hypothetical seam; two adapters means a real one** — don't cut a seam until something actually varies across it.
+
+## The interface is the test surface
+
+Callers and tests cross the same seam, so a well-placed interface gives tests something durable to aim at while the code underneath moves freely. That's why the vocabulary insists on **seam** (Feathers' term — a place you can change behaviour without editing there) over the overloaded "boundary," and why "interface" here means *every fact a caller must know*: signatures, yes, but also invariants, ordering, error modes, and performance — not just the type-level surface.
+
+## Pulled out on purpose
+
+`codebase-design` is the **single source of truth** for the deep-module vocabulary, split out as its own model-invoked skill so anything can reach it. Other skills point at it rather than restating the words: [tdd](https://aihero.dev/skills-tdd) borrows it to place a seam before writing the test, [improve-codebase-architecture](https://aihero.dev/skills-improve-codebase-architecture) leans on it while restructuring existing code, and [to-spec](https://aihero.dev/skills-to-spec) speaks it when it sketches seams and deepening opportunities before writing a spec.
+
+The point of keeping it standalone is that you can also reach for it on its own — as a **reference** for how to think about module design — without triggering the larger process any of those skills mandate. Fix the words once, in one place, and every design conversation inherits them.
+
+## Where it fits
+
+`codebase-design` is a **reach-for-it-anytime standalone** — the shared vocabulary layer under the engineering skills. Its closest neighbour is [domain-modeling](https://aihero.dev/skills-domain-modeling), the parallel vocabulary skill for the problem domain rather than the module structure. When you're unsure which skill or flow fits, [ask-matt](https://aihero.dev/skills-ask-matt) routes you.
@@ -0,0 +1,40 @@
+Quickstart:
+
+```bash
+npx skills add mattpocock/skills --skill=diagnosing-bugs
+```
+
+```bash
+npx skills update diagnosing-bugs
+```
+
+[Source](https://github.com/mattpocock/skills/tree/main/skills/engineering/diagnosing-bugs)
+
+## What it does
+
+`diagnosing-bugs` runs a disciplined diagnosis loop for hard bugs and performance regressions — building a repro, minimising it, ranking hypotheses, instrumenting, then fixing with a regression test.
+
+It refuses to hypothesise before you have a **tight feedback loop** — one runnable command that already goes red on *this* bug. Reading code to build a theory before that command exists is the exact failure this skill prevents. No red-capable loop, no diagnosis.
+
+## When to reach for it
+
+Type `/diagnosing-bugs`, or the agent reaches for it automatically when a task fits — it fires on "diagnose" / "debug this", or when you report something broken, throwing, failing, or slow.
+
+Reach for it on the hard ones: the bug that resists a first glance, the intermittent flake, the regression that crept in between two known-good states. For a quick throwaway to sanity-check a design question rather than chase a defect, use [prototype](https://aihero.dev/skills-prototype) instead.
+
+## The tight loop is the skill
+
+Everything else — bisection, hypothesis-testing, instrumentation — is mechanical once you have the signal. So the skill spends disproportionate effort on Phase 1: constructing a pass/fail command that drives the actual bug code path and asserts the user's exact symptom, then **tightening** it until it is fast, deterministic, and agent-runnable. A 30-second flaky loop is barely better than none; a 2-second deterministic one is a debugging superpower.
+
+It gives you a ladder of ways to build that loop — failing test, curl script, CLI diff, headless browser, replayed trace, throwaway harness, fuzz loop, `git bisect run`, differential run — and, only as a last resort, a human-in-the-loop bash script. For non-deterministic bugs the goal isn't a clean repro but a **higher reproduction rate**: loop the trigger, parallelise, add stress until the flake is debuggable.
+
+## It's working if
+
+- It builds and runs a repro command *before* theorising — and pastes the invocation and its red output.
+- The loop asserts the symptom you actually reported, not a nearby failure.
+- Hypotheses arrive as a ranked, falsifiable list shown to you before any are tested.
+- Debug instrumentation is tagged (`[DEBUG-...]`) and grepped away before it declares done.
+
+## Where it fits
+
+`diagnosing-bugs` is a reach-for-it-anytime standalone — you drop into it the moment something is broken, and drop out once the fix and its regression test are in. Its post-mortem hands off to [improve-codebase-architecture](https://aihero.dev/skills-improve-codebase-architecture) when the real finding is that there's no good seam to lock the bug down — the code, not the bug, is the problem. When you're unsure which skill fits, [ask-matt](https://aihero.dev/skills-ask-matt) routes you.
@@ -0,0 +1,46 @@
+Quickstart:
+
+```bash
+npx skills add mattpocock/skills --skill=domain-modeling
+```
+
+```bash
+npx skills update domain-modeling
+```
+
+[Source](https://github.com/mattpocock/skills/tree/main/skills/engineering/domain-modeling)
+
+## What it does
+
+`domain-modeling` builds and sharpens a project's **ubiquitous language** as you design — challenging fuzzy terms, stress-testing relationships with concrete scenarios, and writing the glossary and decisions down the moment they crystallise.
+
+This is the **active** discipline, not the passive one. Merely reading `CONTEXT.md` to borrow its vocabulary is a one-line habit any skill can do; this skill is for when you are *changing* the model — coining a canonical term, catching a contradiction between the code and what you just said, recording a hard-to-reverse decision. And it keeps the glossary clean: `CONTEXT.md` is a glossary and nothing else — no implementation details, no spec, no scratch pad.
+
+## When to reach for it
+
+Type `/domain-modeling`, or the agent reaches for it automatically when a task fits — when you are pinning down terminology, resolving an overloaded word, or recording an architectural decision.
+
+Reach for it when the *words* are the problem: two people mean different things by "cancellation", "account" is doing three jobs, or a design conversation keeps snagging on a concept that has never been named precisely. If instead the module's *shape* is the problem — where the seam goes, how deep the interface is — use [codebase-design](https://aihero.dev/skills-codebase-design). If you want the plan itself interrogated before you build, use [grilling](https://aihero.dev/skills-grilling).
+
+## Prerequisites
+
+The skill writes into two places, both created lazily — only once there is something to record. Resolved terms go into `CONTEXT.md` at the root (or, in a multi-context repo flagged by a `CONTEXT-MAP.md`, into the per-context `CONTEXT.md`). Decisions go into `docs/adr/`. Nothing needs to exist up front; the first resolved term creates the glossary, the first real trade-off creates the ADR.
+
+## Glossary vs. ADR
+
+Two artifacts, two different bars:
+
+- **The glossary** (`CONTEXT.md`) captures language. Every time a vague term is made canonical, it's written down inline — not batched — so the shared vocabulary stays current with the conversation. It stays ruthlessly free of implementation detail.
+- **An ADR** captures a decision, and the bar is high: offered only when the choice is **hard to reverse**, **surprising without context**, and **the result of a real trade-off**. Miss any one of the three and there is no ADR. This is what keeps `docs/adr/` a record of consequential forks rather than a diary.
+
+The move that makes it click: when you state how something works, the skill cross-references the code and surfaces the contradiction — "your code cancels entire Orders, but you just said partial cancellation is possible — which is right?" The language and the code are forced to agree.
+
+## Pulled out on purpose
+
+`domain-modeling` is the **single source of truth** for building the project's ubiquitous language, split out as its own model-invoked skill so any other skill can reach it. [grill-with-docs](https://aihero.dev/skills-grill-with-docs) leans on it to record terms and decisions as a grilling session runs, [triage](https://aihero.dev/skills-triage) uses it to keep tickets in the project's own words, and [improve-codebase-architecture](https://aihero.dev/skills-improve-codebase-architecture) reaches for it while it works.
+
+Keeping it standalone means you can also reach for it directly — as a **reference** for how to sharpen a model — without committing to the steps any of those skills mandate. The language lives in one place, and everything that needs it points there.
+
+## Where it fits
+
+`domain-modeling` is a **reach-for-it-anytime standalone** that runs *underneath* other skills as often as at a fixed step. Its closest neighbour is [codebase-design](https://aihero.dev/skills-codebase-design), because a shared language is what lets you name a deep module and its seam precisely; downstream, a settled glossary is exactly what [to-spec](https://aihero.dev/skills-to-spec) synthesises into a spec written in the project's own words. When you're unsure which skill or flow fits, [ask-matt](https://aihero.dev/skills-ask-matt) routes you.
@@ -0,0 +1,50 @@
+Quickstart:
+
+```bash
+npx skills add mattpocock/skills --skill=grill-with-docs
+```
+
+```bash
+npx skills update grill-with-docs
+```
+
+[Source](https://github.com/mattpocock/skills/tree/main/skills/engineering/grill-with-docs)
+
+## What it does
+
+`grill-with-docs` interviews you relentlessly about a plan or design, one question at a time, until you and the agent reach a shared understanding — and it writes the vocabulary and decisions down as you go.
+
+The grilling **leaves a paper trail**. A plain interview sharpens your thinking and then evaporates when the session ends; this one captures each term the moment it's resolved into a `CONTEXT.md` glossary, and records the hard, one-way decisions as ADRs. The alignment survives the conversation instead of living only in your head.
+
+## When to reach for it
+
+You invoke this by typing `/grill-with-docs` — the agent won't reach for it on its own.
+
+Reach for it at the very start of a change, when the plan is still fuzzy and the domain language isn't settled, and you want to stress-test both before any code exists. If you only want the interview and don't need the artifacts, use [grilling](https://aihero.dev/skills-grilling); if the plan is already clear and you just need to pin down or record terminology, use [domain-modeling](https://aihero.dev/skills-domain-modeling). And if the change is too big to hold in one session and its route is still foggy — a greenfield project, a huge feature build — start upstream with [wayfinder](https://aihero.dev/skills-wayfinder): it charts the effort as a map of decisions, then hands back to this main flow once the way is clear.
+
+## Prerequisites
+
+This skill is stateful — it writes into your repo as it grills. Resolved terms land in a `CONTEXT.md` glossary at the root (or the relevant context's `CONTEXT.md` if a `CONTEXT-MAP.md` marks a multi-context repo), and genuinely hard-to-reverse decisions land as ADRs under `docs/adr/`. Both are created lazily — nothing exists until the first term or decision crystallises — so you don't need to scaffold anything up front, but you do need to be somewhere it's safe to write these files.
+
+## The grill
+
+The engine is a **grill**: a relentless, one-question-at-a-time walk down the decision tree, resolving dependencies between decisions before moving on, with a recommended answer offered for every question. Questions the codebase can answer are answered by reading the codebase, not by asking you.
+
+What makes this variant its own skill is where the answers go. As the grill runs, fuzzy language gets sharpened into canonical terms and written to the glossary inline — not batched at the end. The glossary stays a glossary: pure vocabulary, no implementation details, no spec. ADRs are offered sparingly, only when a decision is hard to reverse, surprising without context, and the result of a real trade-off. Most sessions produce a sharper glossary and few or no ADRs, and that's the intended shape.
+
+## It's working if
+
+- It asks one question at a time and waits, rather than dumping a questionnaire.
+- Terms get written to `CONTEXT.md` the moment they resolve, in your project's own words.
+- It reaches into the codebase to answer its own questions where it can.
+- ADRs stay rare — you're not asked to rubber-stamp reversible choices.
+
+## Where it fits
+
+`grill-with-docs` is the opening step of the main build chain:
+
+```txt
+grill-with-docs → to-spec → to-tickets → implement → code-review
+```
+
+It comes first, before anything is written down as a spec: it produces the shared understanding and settled vocabulary that [to-spec](https://aihero.dev/skills-to-spec) then synthesises into a spec without re-interviewing you. Its close neighbours are [grilling](https://aihero.dev/skills-grilling), the same interview without the docs, and [domain-modeling](https://aihero.dev/skills-domain-modeling), the glossary-and-ADR discipline it drives. When you're unsure which skill or flow fits, [ask-matt](https://aihero.dev/skills-ask-matt) routes you.
@@ -0,0 +1,39 @@
+Quickstart:
+
+```bash
+npx skills add mattpocock/skills --skill=implement
+```
+
+```bash
+npx skills update implement
+```
+
+[Source](https://github.com/mattpocock/skills/tree/main/skills/engineering/implement)
+
+## What it does
+
+`implement` builds the work described in a spec or a set of tickets — driving it through test-driven development, typechecking, and the full test suite, then handing off to review and committing to the current branch.
+
+It does **not** decide what to build. The spec is already settled and the seams are already agreed; `implement` executes that plan rather than reopening it. It is the hands, not the head — the thinking happened upstream.
+
+## When to reach for it
+
+You invoke this by typing `/implement` — the agent won't reach for it on its own.
+
+Reach for it once the work is written down as a spec or split into tickets and you're ready to turn that into code. If the spec doesn't exist yet, write it first — for that, use [to-spec](https://aihero.dev/skills-to-spec), or [to-tickets](https://aihero.dev/skills-to-tickets) to break a spec into tickets. If you just want to build something test-first without a full spec, drop to [tdd](https://aihero.dev/skills-tdd) directly.
+
+## Pre-agreed seams
+
+The idea `implement` runs on is the **seam** — the stable interface a feature is tested at, chosen before any code is written. It doesn't invent seams mid-build; it uses the ones already picked (during [to-spec](https://aihero.dev/skills-to-spec)) and writes tests against them via [tdd](https://aihero.dev/skills-tdd). Working at pre-agreed seams is what keeps the implementation honest: the tests target something durable, so the code underneath can move without the tests moving.
+
+Around that core it keeps the loop tight — typecheck often, run single test files as it goes, run the whole suite once at the end — then closes out with a review pass and a commit to the current branch.
+
+## Where it fits
+
+`implement` is the build step near the end of the main chain, just before the review:
+
+```txt
+grill-with-docs → to-spec → to-tickets → implement → code-review
+```
+
+Reach for it after the work has been specced and sequenced, not before. Its key neighbours are [to-tickets](https://aihero.dev/skills-to-tickets), which produces the tickets — each declaring its blocking edges — that it works through, and [tdd](https://aihero.dev/skills-tdd), which it drives internally to write the tests at each seam before running its own [code-review](https://aihero.dev/skills-code-review) pass and committing. When you're unsure which skill or flow fits, [ask-matt](https://aihero.dev/skills-ask-matt) routes you.
@@ -0,0 +1,41 @@
+Quickstart:
+
+```bash
+npx skills add mattpocock/skills --skill=improve-codebase-architecture
+```
+
+```bash
+npx skills update improve-codebase-architecture
+```
+
+[Source](https://github.com/mattpocock/skills/tree/main/skills/engineering/improve-codebase-architecture)
+
+## What it does
+
+`improve-codebase-architecture` scans a codebase for **deepening opportunities** — places where a shallow module (an interface nearly as complex as the thing it hides) could become a deep one — presents them as a self-contained visual HTML report, then grills through whichever one you pick.
+
+It does **not** hand you a flat list of refactors. Every candidate has to pass the **deletion test** — would removing this module *concentrate* complexity behind a smaller interface, or just move it around? Only the "concentrates" cases earn a card. That filter is what stops the report from becoming generic cleanup advice.
+
+Unless you point it at a specific area, it also scopes itself to where development is actually landing — reading the recent commits to bias toward the code you're still changing. Deepening a module pays off by making future changes to it easier, so it puts extra weight on the parts of the repo that have recently changed.
+
+## When to reach for it
+
+You invoke this by typing `/improve-codebase-architecture` — the agent won't reach for it on its own.
+
+Reach for it as a periodic health check: every few days, or whenever a codebase has started to feel like it takes too much bouncing between small modules to understand one concept. It reads the existing architecture and proposes where to deepen it. If you already know the module you want to redesign and just need the vocabulary to think it through, use [codebase-design](https://aihero.dev/skills-codebase-design) instead — this skill is the survey that finds the candidates; that one is the design bench.
+
+## Deepening opportunities
+
+The whole skill turns on one idea: **depth**. A deep module hides a lot of functionality behind a small, stable interface; a shallow one leaks its implementation through an interface almost as wide as the code beneath it. The report hunts for shallowness — pure functions extracted only for testability while the real bugs hide in how they're called (no **locality**), modules that leak across their **seams**, concepts you can't understand without opening five files — and proposes the deepening that would fix it.
+
+It speaks in the shared design vocabulary (**module**, **interface**, **depth**, **seam**, **adapter**, **leverage**, **locality**) and in your project's own domain language from `CONTEXT.md`, so a candidate reads as "deepen the Order intake module," never "refactor the FooBarHandler."
+
+## The report, then the grill
+
+The output is a browser-ready HTML file written to your OS temp directory — nothing lands in the repo. Each candidate is a card with the files involved, the friction, a plain-English solution, the benefit in terms of locality and leverage, a before/after diagram, and a `Strong` / `Worth exploring` / `Speculative` badge. It closes with the one it would tackle first.
+
+Then it stops and asks which one you want to explore. Pick one and it runs the [grilling](https://aihero.dev/skills-grilling) loop over that design — constraints, what sits behind the seam, which tests survive — updating the domain model inline as decisions crystallise.
+
+## Where it fits
+
+`improve-codebase-architecture` is **periodic maintenance** — run it every few days, not as a step in a chain. Its neighbours are [codebase-design](https://aihero.dev/skills-codebase-design), which owns the depth-and-seam vocabulary every candidate is written in, [grilling](https://aihero.dev/skills-grilling), which walks the decision tree once you've chosen a candidate, and [domain-modeling](https://aihero.dev/skills-domain-modeling), which keeps `CONTEXT.md` and the ADRs current as the redesign settles. When you're unsure which skill or flow fits, [ask-matt](https://aihero.dev/skills-ask-matt) routes you.
@@ -0,0 +1,42 @@
+Quickstart:
+
+```bash
+npx skills add mattpocock/skills --skill=prototype
+```
+
+```bash
+npx skills update prototype
+```
+
+[Source](https://github.com/mattpocock/skills/tree/main/skills/engineering/prototype)
+
+## What it does
+
+`prototype` builds a small, disposable program whose only job is to answer one design question — does this state model feel right, or what should this UI look like.
+
+The code is **throwaway from day one**, and marked as such. It carries no tests, no error handling beyond what makes it run, no abstractions, and no persistence. The point is to learn something fast and then delete it — so the moment you start hardening it, you've stopped prototyping.
+
+## When to reach for it
+
+Type `/prototype`, or the agent reaches for it automatically when a task fits.
+
+Reach for it when you have a design question that's hard to settle on paper — a state machine with cases you can't hold in your head, or a screen you can't picture until you see a few versions side by side. If instead something already built is misbehaving and you need to find out why, use [diagnosing-bugs](https://aihero.dev/skills-diagnosing-bugs); prototyping explores what to build, not why the built thing is broken.
+
+## Two branches
+
+The question decides the shape, and there are two shapes:
+
+- **"Does this logic / state model feel right?"** — a tiny interactive terminal app that pushes the state machine through the awkward cases, printing the full state after every action so you can watch what changes.
+- **"What should this look like?"** — several radically different UI variations on one route, switchable from a floating bar, so you compare real renders instead of imagining them.
+
+Picking the wrong branch wastes the whole prototype, so the question comes first. Both branches keep state in memory, run from one command, and surface the full state on every step.
+
+## Keep the prototype as a primary source
+
+A finished prototype leaves two things. The **answer** — the verdict plus the question it settled — is what you capture durably (a commit message, an ADR, an issue). The **prototype itself is a primary source** — the runnable evidence the answer came from.
+
+The prototype doesn't belong in the main branch: no tests, no error handling, nothing to maintain. But that's not a reason to destroy it. Once the answer is captured, fold any validated decision into the real code, then capture the prototype on a throwaway branch — out of main, never merged — and leave a context pointer to it on the implementation issue. The main branch stays clean; the raw exploration stays one click away for anyone who wants to re-run it. A prototype left rotting in the main branch has outlived its purpose — a prototype captured as a primary source on a side branch hasn't.
+
+## Where it fits
+
+`prototype` is a reach-for-it-anytime standalone: you drop into it to resolve a design question, then drop back out. Its answer often feeds the next step — a validated state model or UI direction becomes settled input for [to-spec](https://aihero.dev/skills-to-spec) to write up, or an architectural decision worth recording via [domain-modeling](https://aihero.dev/skills-domain-modeling). When you're unsure which skill or flow fits, [ask-matt](https://aihero.dev/skills-ask-matt) routes you.
@@ -0,0 +1,29 @@
+Quickstart:
+
+```bash
+npx skills add mattpocock/skills --skill=research
+```
+
+```bash
+npx skills update research
+```
+
+[Source](https://github.com/mattpocock/skills/tree/main/skills/engineering/research)
+
+## What it does
+
+`research` answers a question by reading the sources that own the answer and leaving a cited Markdown file behind. It works only from **primary sources** — official docs, source code, specs, first-party APIs — never a secondary write-up of them, so what it saves is traceable back to something authoritative rather than a summary of a summary.
+
+## When to reach for it
+
+Type `/research`, or the agent reaches for it automatically when a task turns into reading legwork.
+
+Reach for it when the next step is *finding something out* — how an API behaves, what a spec actually says, whether a claim holds — and you'd rather not stall your own thread doing the reading. For sharpening a plan by interview instead of by reading, use [grilling](https://aihero.dev/skills-grilling); for exploring what to build with throwaway code, use [prototype](https://aihero.dev/skills-prototype).
+
+## Delegated legwork
+
+The defining move is that the reading runs as a **background agent**. You keep working; it goes off, follows each claim back to its primary source, and drops a single cited Markdown file into wherever the repo keeps such notes. Research is legwork you delegate, not thinking you outsource — you get back a document to react to, with its sources attached.
+
+## Where it fits
+
+A reach-for-it-anytime standalone that feeds the thinking skills: the file it produces is something to grill, plan, or design against, so it sits upstream of work like [grilling](https://aihero.dev/skills-grilling) and [to-prd](https://aihero.dev/skills-to-prd) rather than in the build chain. For the whole map, see [ask-matt](https://aihero.dev/skills-ask-matt).
@@ -0,0 +1,40 @@
+Quickstart:
+
+```bash
+npx skills add mattpocock/skills --skill=resolving-merge-conflicts
+```
+
+```bash
+npx skills update resolving-merge-conflicts
+```
+
+[Source](https://github.com/mattpocock/skills/tree/main/skills/engineering/resolving-merge-conflicts)
+
+## What it does
+
+`resolving-merge-conflicts` works through an in-progress git merge or rebase conflict, hunk by hunk, and finishes the operation — resolved, checked, and committed.
+
+It resolves by **intent**, not by text. Before touching a hunk it traces each side back to its **primary source** — the commit message, the PR, the original issue — to understand why the change was made, then preserves both intents where they're compatible. It never invents new behaviour to paper over a clash, and it never reaches for `--abort`: the merge always gets finished.
+
+## When to reach for it
+
+Type `/resolving-merge-conflicts`, or the agent reaches for it automatically when a task fits.
+
+Reach for this when you're mid-merge or mid-rebase and git has stopped on conflicts it can't resolve itself. It's for the conflict in front of you — not for planning the merge or for debugging behaviour that broke afterwards. If the merge is done but something's now failing for reasons you can't see, use [diagnosing-bugs](https://aihero.dev/skills-diagnosing-bugs) instead.
+
+## Resolving by intent
+
+The trap in a conflict is treating it as a text problem — picking "ours" or "theirs" to make the markers go away. This skill treats it as an **intent** problem. Each side of a hunk exists because someone wanted something; the resolution has to honour both wants where it can, and where they're genuinely incompatible, pick the one that matches the merge's stated goal and note the trade-off out loud.
+
+That's why the primary sources matter. You can't preserve an intent you haven't read, so the work starts in the history — commits, PRs, tickets — not in the diff.
+
+## It's working if
+
+- Each resolved hunk keeps both sides' behaviour, or names the trade-off where it couldn't.
+- No new behaviour appears that wasn't on either branch.
+- The project's own checks — typecheck, tests, format — are found and run green before the commit.
+- The merge or rebase is carried all the way to a finished commit, never aborted.
+
+## Where it fits
+
+A reach-for-it-anytime standalone: you invoke it at the moment a merge or rebase stalls, and it hands you back a clean, committed tree. Its natural neighbour is [diagnosing-bugs](https://aihero.dev/skills-diagnosing-bugs), because a merge that resolves cleanly but misbehaves afterwards is a diagnosis problem, not a conflict one. When you're unsure which skill fits, [ask-matt](https://aihero.dev/skills-ask-matt) routes you.
@@ -0,0 +1,43 @@
+Quickstart:
+
+```bash
+npx skills add mattpocock/skills --skill=setup-matt-pocock-skills
+```
+
+```bash
+npx skills update setup-matt-pocock-skills
+```
+
+[Source](https://github.com/mattpocock/skills/tree/main/skills/engineering/setup-matt-pocock-skills)
+
+## What it does
+
+`setup-matt-pocock-skills` teaches one repo how the engineering skills should behave in it — where issues live, what the triage labels are called, and where the domain docs sit — and records those answers as **config** the other skills read.
+
+It writes config, it does not hard-code behaviour. The engineering chain assumes three files under `docs/agents/` exist; this skill is the one-time bootstrap that produces them, discovered from your actual repo (`git remote`, existing labels, existing `CONTEXT.md`) and confirmed with you rather than guessed. It is prompt-driven — explore, present what it found, confirm, then write — not a deterministic scaffold.
+
+## When to reach for it
+
+You invoke this by typing `/setup-matt-pocock-skills` — the agent won't reach for it on its own.
+
+Reach for it **once per repo, before the first use of any other engineering skill**. If [triage](https://aihero.dev/skills-triage), [to-spec](https://aihero.dev/skills-to-spec), or [to-tickets](https://aihero.dev/skills-to-tickets) start guessing where your issues live or applying labels that don't exist, they haven't been set up here yet. Re-run it only to switch issue trackers or start over — day-to-day tweaks are just edits to `docs/agents/*.md`.
+
+## The three decisions
+
+It leads each with a recommended answer you can accept in a word, and skips whatever it can already infer — so most runs are a couple of quick confirmations:
+
+- **Issue tracker** — where work is tracked, so `triage`/`to-spec`/`to-tickets` know whether to call `gh`, `glab`, write markdown under `.scratch/`, or follow a workflow you describe. GitHub, GitLab, local markdown, or other. (It proposes the one that matches your `git remote`.)
+- **Triage labels** — asked only if the `triage` skill is installed, and then just: keep the default labels (`needs-triage`, `needs-info`, `ready-for-agent`, `ready-for-human`, `wontfix`)? Say no only if your tracker already uses other names, so `triage` applies real ones instead of creating duplicates.
+- **Domain docs** — assumed single-context (one `CONTEXT.md` + `docs/adr/` at the root), which fits almost every repo; it only raises a multi-context map when it spots monorepo signals.
+
+The output is a set of files under `docs/agents/` — `issue-tracker.md`, `domain.md`, and `triage-labels.md` when `triage` is installed — plus an `## Agent skills` block pointing to them in whichever of `CLAUDE.md` / `AGENTS.md` the repo already uses. Those files are the shared substrate the rest of the toolkit stands on.
+
+## It's working if
+
+- `issue-tracker.md` and `domain.md` land under `docs/agents/` (plus `triage-labels.md` when `triage` is installed), and an `## Agent skills` section appears in your `CLAUDE.md` or `AGENTS.md`.
+- The tracker it proposes matches your real `git remote`, and the labels match strings that already exist in your repo.
+- Afterwards, `triage` and `to-tickets` act on the right place with the right labels instead of asking or guessing.
+
+## Where it fits
+
+`setup-matt-pocock-skills` is a **run-once setup** — the foundation the whole engineering set stands on, not a step you repeat. Its neighbours are the skills that read what it writes: [triage](https://aihero.dev/skills-triage), because it applies the label vocabulary configured here, and [to-spec](https://aihero.dev/skills-to-spec) / [to-tickets](https://aihero.dev/skills-to-tickets), because they publish into the issue tracker configured here. Run it first; everything downstream assumes it has. When you're unsure which skill or flow fits, [ask-matt](https://aihero.dev/skills-ask-matt) routes you.
@@ -0,0 +1,47 @@
+Quickstart:
+
+```bash
+npx skills add mattpocock/skills --skill=tdd
+```
+
+```bash
+npx skills update tdd
+```
+
+[Source](https://github.com/mattpocock/skills/tree/main/skills/engineering/tdd)
+
+## What it does
+
+`tdd` builds a feature or fixes a bug test-first, one behaviour at a time, driving the code out through a red-green loop.
+
+It will **not** write all the tests up front. Batching the tests first ("horizontal slicing") produces tests of _imagined_ behaviour — they check the shape of things and go numb to real changes. `tdd` instead takes vertical slices: one test, then just enough code to pass it, then the next test, each cycle informed by what the last one taught you. Tests target public interfaces only, so the implementation underneath can change without the tests moving.
+
+## When to reach for it
+
+Type `/tdd`, or the agent reaches for it automatically when a task fits — building a feature or fixing a bug test-first, or when you say "red-green-refactor".
+
+Reach for it when there's a concrete behaviour to build and you want tests that survive a refactor. If the behaviour isn't pinned down yet, settle the spec first — for that, use [to-spec](https://aihero.dev/skills-to-spec). When the work is really about the shape of the interface rather than the tests, use [codebase-design](https://aihero.dev/skills-codebase-design); `tdd` calls into it for the deep-module vocabulary during planning.
+
+## Red-green, one slice at a time
+
+The leading idea is the **red-green loop**: write one failing test (red), add just enough code to pass it (green), then repeat for the next behaviour — each cycle informed by what the last one taught you. The very first cycle is a **tracer bullet**: one test that proves a single path works end-to-end, before you build outward from it. Because you just wrote the code, you know exactly which behaviour matters and how to verify it — you never outrun your headlights by committing to test structure you don't yet understand.
+
+Two rules keep the tests honest. A good test reads like a specification ("user can checkout with valid cart") and exercises real code paths through the public API, so renaming an internal function never breaks it. And expected values come from an independent source of truth — a known-good literal, a worked example, the spec — never recomputed the way the code computes them, which is how a **tautological** test passes by construction and tells you nothing.
+
+Refactoring only happens once the suite is green; never while red.
+
+## It's working if
+
+- It writes one test, gets it passing, and only then writes the next — not a batch of tests followed by a batch of code.
+- The tests name behaviours, not internals, and would survive an internal rename.
+- Expected values are literals from the spec, not figures derived the same way the code derives them.
+
+## Where it fits
+
+`tdd` is the red-green loop the main build chain runs to write code:
+
+```txt
+grill-with-docs → to-spec → to-tickets → implement → code-review
+```
+
+[implement](https://aihero.dev/skills-implement) is the chain's build step, and it drives `tdd` internally to build each ticket test-first before handing off to [code-review](https://aihero.dev/skills-code-review) — so `tdd` is the engine inside that step rather than a step of its own. You can also reach for it directly, whenever there's a concrete behaviour to build without a full spec. Its other neighbour is [codebase-design](https://aihero.dev/skills-codebase-design), which it leans on to find deep-module seams worth testing at. When you're unsure which skill or flow fits, [ask-matt](https://aihero.dev/skills-ask-matt) routes you.
@@ -0,0 +1,59 @@
+Quickstart:
+
+```bash
+npx skills add mattpocock/skills --skill=to-spec
+```
+
+```bash
+npx skills update to-spec
+```
+
+[Source](https://github.com/mattpocock/skills/tree/main/skills/engineering/to-spec)
+
+## What it does
+
+`to-spec` turns the current conversation and your codebase understanding into a spec (you may know this document as a PRD), then publishes it to your issue tracker.
+
+It does **not** interview you again. By the time you reach for it, the alignment work is done — `to-spec` synthesises what is already known rather than asking a fresh round of questions.
+
+## When to reach for it
+
+You invoke this by typing `/to-spec` — the agent won't reach for it on its own.
+
+Reach for it once a change has been talked through and the domain language is settled, and you want that shared understanding written down before any code is written. If you *haven't* aligned yet, grill first — for that, use [grill-with-docs](https://aihero.dev/skills-grill-with-docs). To split the finished spec into tickets, use [to-tickets](https://aihero.dev/skills-to-tickets).
+
+## Prerequisites
+
+`to-spec` publishes into your issue tracker, so [setup-matt-pocock-skills](https://aihero.dev/skills-setup-matt-pocock-skills) must have configured the tracker and triage labels for this repo first. It applies the `ready-for-agent` label itself — no separate triage pass needed.
+
+## What the spec includes
+
+- **Problem statement** — what is broken or missing, and why it's worth solving, in the project's own vocabulary.
+- **Solution** — the shape of the fix at a high level, before any implementation detail.
+- **User stories** — an extensive, numbered list of the concrete behaviours the change must support, each one independently checkable.
+- **Implementation decisions** — the choices already settled during the conversation, so they aren't relitigated later.
+- **Testing decisions** — the seams the feature will be tested at, and what "done" looks like.
+- **Out-of-scope items** — what this change deliberately does *not* cover, to keep the ticket bounded.
+- **Further notes** — anything else worth carrying forward that doesn't fit the sections above.
+
+## Deep modules
+
+Before writing the spec, `to-spec` sketches the **seams** at which the feature will be tested and looks for **deep module** opportunities — a lot of functionality hidden behind a small, stable interface. It prefers existing seams to new ones and the highest seam possible, ideally just one across the whole change.
+
+That matters for agentic development: a good interface gives tests something durable to target, so the code underneath can change without the tests moving.
+
+## It's working if
+
+- It starts writing the spec instead of asking you a fresh round of questions.
+- It checks the seams with you before writing, and proposes as few as possible.
+- The spec comes back in your project's domain vocabulary, not generic boilerplate.
+
+## Where it fits
+
+`to-spec` is a step in the main build chain:
+
+```txt
+grill-with-docs → to-spec → to-tickets → implement → code-review
+```
+
+Reach for it after the plan and domain language are resolved, and before you break the work into implementation tickets. Its key neighbours are [grill-with-docs](https://aihero.dev/skills-grill-with-docs), which sharpens the context so the spec is precise, and [to-tickets](https://aihero.dev/skills-to-tickets), which turns the spec into a set of tickets for [implement](https://aihero.dev/skills-implement) to build. When you're unsure which skill or flow fits, [ask-matt](https://aihero.dev/skills-ask-matt) routes you.
@@ -0,0 +1,56 @@
+Quickstart:
+
+```bash
+npx skills add mattpocock/skills --skill=to-tickets
+```
+
+```bash
+npx skills update to-tickets
+```
+
+[Source](https://github.com/mattpocock/skills/tree/main/skills/engineering/to-tickets)
+
+## What it does
+
+`to-tickets` breaks a plan, spec, or the current conversation into a set of **tickets** — each a tracer-bullet vertical slice — and publishes them to your configured tracker, with every ticket declaring the tickets that block it.
+
+Every ticket is a **tracer bullet** — a thin *vertical* slice that cuts through all integration layers end-to-end (schema, API, UI, tests), never a horizontal slice of one layer. A completed slice is demoable or verifiable on its own, which is what makes each ticket safe to hand to an agent.
+
+## When to reach for it
+
+You invoke this by typing `/to-tickets` — the agent won't reach for it on its own.
+
+Reach for it once you have an agreed plan or a written spec and you want it split into tickets. Point it at the conversation, or pass a spec or issue reference and it fetches the body and comments first. If the change hasn't been written up as a spec yet, produce one first — for that, use [to-spec](https://aihero.dev/skills-to-spec).
+
+## Prerequisites
+
+`to-tickets` publishes into your issue tracker, so [setup-matt-pocock-skills](https://aihero.dev/skills-setup-matt-pocock-skills) must have configured the tracker and its triage label vocabulary for this repo first. On a real tracker it applies the ready-for-agent label as it publishes.
+
+## One artifact, two readings
+
+The blocking edges are the whole point. They make one set of tickets read two ways, depending on the tracker:
+
+- **Local files** → one file per ticket under `.scratch/<feature>/issues/`, numbered blockers-first, the edges written as text. You work them top-to-bottom, by hand, staying in the loop.
+- **A real tracker (GitHub, Linear)** → one issue per ticket, the edges as native blocking links (or sub-issues). Any ticket whose blockers are all done is on the **frontier** and can be grabbed — so several agents can run at once.
+
+The edges live in the ticket regardless of medium; the medium only decides whether anything acts on them in parallel. `to-tickets` produces the artifact — how you run it (sequential by hand, or a parallel fleet) is up to you.
+
+## Vertical slices, not horizontal ones
+
+The whole skill turns on one distinction. A **horizontal** slice ships one layer of the change — all the schema, or all the API — and nothing works until every layer lands. A **vertical** slice, the tracer bullet, ships one narrow path through *every* layer at once, so it can be demoed the moment it's done.
+
+Before slicing, `to-tickets` looks for prefactoring — "make the change easy, then make the easy change" — and orders that work first. It then quizzes you on the breakdown (granularity, blocking edges, what to merge or split) before publishing anything, and publishes blockers first so each ticket's "Blocked by" can reference a real ticket.
+
+## The wide-refactor exception
+
+One shape breaks the tracer-bullet rule: a **wide refactor** — a single mechanical change (rename a column, retype a shared symbol) whose **blast radius** fans across the whole codebase, so one edit breaks thousands of call sites at once and no vertical slice can land green. `to-tickets` slices it as **expand–contract** instead: expand (add the new form beside the old so nothing breaks), migrate (move call sites over in batches sized by blast radius, one ticket per batch, CI green throughout because the old form still exists), then contract (delete the old form once no caller remains). When even the batches can't stay green alone, they share an integration branch that all block a final integrate-and-verify ticket, and green is promised only there.
+
+## Where it fits
+
+`to-tickets` is a step in the main build chain:
+
+```txt
+grill-with-docs → to-spec → to-tickets → implement → code-review
+```
+
+It sits between [to-spec](https://aihero.dev/skills-to-spec), which hands it a settled spec with user stories to slice against, and [implement](https://aihero.dev/skills-implement), which builds each ticket, driving [tdd](https://aihero.dev/skills-tdd) internally to write the tests test-first, before its [code-review](https://aihero.dev/skills-code-review) pass. Work the frontier one ticket per fresh context, clearing between them. When you're unsure which skill or flow fits, [ask-matt](https://aihero.dev/skills-ask-matt) routes you.
@@ -0,0 +1,46 @@
+Quickstart:
+
+```bash
+npx skills add mattpocock/skills --skill=triage
+```
+
+```bash
+npx skills update triage
+```
+
+[Source](https://github.com/mattpocock/skills/tree/main/skills/engineering/triage)
+
+## What it does
+
+`triage` moves issues on your project's tracker through a small **state machine** of triage roles — categorise them, verify the claim, grill them into shape if needed, and leave a ready-for-agent brief.
+
+It never labels blind. Every triaged item carries exactly one **category** role (`bug` / `enhancement`) and one **state** role (`needs-triage`, `needs-info`, `ready-for-agent`, `ready-for-human`, `wontfix`), and it *recommends and waits* — it tells you its category and state call with reasoning, then acts only on your direction. Before anything is promoted to `ready-for-agent`, it verifies the claim first: a bug gets reproduced, a PR gets checked out and run.
+
+## When to reach for it
+
+You invoke this by typing `/triage` and describing what you want in natural language — the agent won't reach for it on its own. "Show me anything that needs my attention", "let's look at #42", "move #42 to ready-for-agent".
+
+Reach for it when your issue tracker has raw, unevaluated reports and you want them sorted, verified, and turned into work an agent or human can pick up. To turn a settled conversation into a fresh spec instead, use [to-spec](https://aihero.dev/skills-to-spec); to split an existing spec into tickets, use [to-tickets](https://aihero.dev/skills-to-tickets). `triage` is the reverse direction — it processes what's *already* landed in the tracker.
+
+## Prerequisites
+
+`triage` reads and writes your issue tracker, so [setup-matt-pocock-skills](https://aihero.dev/skills-setup-matt-pocock-skills) must have configured the tracker and the label mapping first. The role names above are **canonical** — the actual label strings in your tracker may differ, and that mapping is what setup provides. The config also decides whether external PRs count as a request surface, and who counts as external.
+
+## A PR is an issue with attached code
+
+Where the tracker treats external pull requests as a request surface, `triage` runs them through the *same* machine: same category roles, same states, same transitions — the states just read against the diff instead of a report. `ready-for-agent` means a brief is attached and an agent should take the next step on the code; `ready-for-human` means it's ready to merge. Discovery surfaces only external PRs, but an explicitly named PR is always triaged regardless of author.
+
+## Verify before you brief
+
+The step that separates `triage` from ad-hoc labelling is verification. It reproduces the bug from the reporter's steps, or checks out the PR and runs the tests, and reports back: confirmed with a code path, failed, or insufficient detail (which is itself a strong `needs-info` signal). It also runs two codebase checks — **redundancy** (is this already implemented? then it's a `wontfix`) and **prior rejection** (does `.out-of-scope/` already say no?). A confirmed verification makes a far stronger agent brief; guessing does not.
+
+## It's working if
+
+- Every item it touches ends with exactly one category role and one state role — never zero, never two conflicting states.
+- It hands you a recommendation with reasoning and waits, rather than relabelling on its own.
+- Bugs get reproduced and PRs get run before anything reaches `ready-for-agent`.
+- Every comment it posts to the tracker opens with the `> *This was generated by AI during triage.*` disclaimer.
+
+## Where it fits
+
+`triage` is the **periodic maintenance** pass over your issue tracker — run it whenever reports pile up, to keep the queue sorted and the `ready-for-agent` column trustworthy. It sits at the front of the tracker, upstream of the build chain: the briefs it writes are what [tdd](https://aihero.dev/skills-tdd) later picks up to implement. When a request needs sharpening it leans on [grilling](https://aihero.dev/skills-grilling) and [domain-modeling](https://aihero.dev/skills-domain-modeling) to grill it into shape one question at a time. Its close neighbour is [to-spec](https://aihero.dev/skills-to-spec), which populates the tracker from a fresh conversation where `triage` processes what's already there. When you're unsure which skill or flow fits, [ask-matt](https://aihero.dev/skills-ask-matt) routes you.
@@ -0,0 +1,44 @@
+Quickstart:
+
+```bash
+npx skills add mattpocock/skills --skill=wayfinder
+```
+
+```bash
+npx skills update wayfinder
+```
+
+[Source](https://github.com/mattpocock/skills/tree/main/skills/engineering/wayfinder)
+
+## What it does
+
+`wayfinder` takes an effort too big for one agent session — wrapped in fog, where the way from here to the goal isn't visible yet — and charts it as a **shared map** of **decision tickets** on your issue tracker, then resolves them one at a time until the way is clear. It **plans, it doesn't do**: every ticket resolves a decision — a question to settle, not a slice of a build to execute — and the map is done when nothing is left to decide before someone goes and builds the thing — so it produces decisions, not deliverables.
+
+## When to reach for it
+
+You invoke this by typing `/wayfinder` — the agent won't reach for it on its own.
+
+Reach for it when an effort is **more than one agent session can hold** and the route to its **destination** is still foggy — you can feel the shape of the work but can't yet write it down as a spec or a plan. For turning an *already-clear* thread into a spec, use [to-spec](https://aihero.dev/skills-to-spec); for slicing an already-understood plan into buildable tickets, use [to-tickets](https://aihero.dev/skills-to-tickets). Wayfinder sits upstream of both: it's what you run when there's too much fog to spec directly.
+
+## Prerequisites
+
+The map and its tickets live on the repo's issue tracker, so wayfinder needs the tracker wiring that [setup-matt-pocock-skills](https://aihero.dev/skills-setup-matt-pocock-skills) lays down — it seeds a "Wayfinding operations" section describing how the map, child tickets, blocking, and frontier queries are expressed for GitHub, GitLab, or local-markdown. Absent that doc, wayfinder defaults to a local-markdown map.
+
+## The map is an index, fog is the frontier
+
+The **map** is a single `wayfinder:map` issue whose tickets are its child issues — one shared URL the whole team can watch. It's an **index, not a store**: each decision lives in exactly one place (its ticket), and the map only gists and links, never restates. A session loads the map at low resolution and zooms into individual tickets on demand.
+
+Beyond the live tickets lies the **fog of war** — decisions you can tell are coming but can't yet pin down. The test for whether something is a ticket or still fog is whether you can *state the question precisely now*, not whether you can answer it. Resolving a ticket clears the fog ahead of it, **graduating** whatever's now specifiable into fresh tickets. The **frontier** is the open, unblocked, unclaimed tickets — the edge of the known — and it's what the tracker's native blocking renders visually, so you see what's takeable without opening the map. Fog only gathers *toward* the **destination**; work past it is ruled **out of scope**, closed, never graduating.
+
+Every ticket is **HITL** (human in the loop — grilling, prototype) or **AFK** (agent alone — research); a HITL ticket only resolves through a live exchange, so the agent never answers its own questions. Research stays a real ticket — a shared blocker downstream decisions hang on — but because it's AFK, a session doesn't stop and read: it fires a `/research` **subagent** to burn the ticket down in parallel, keeping the frontier fast, and captures the findings on a throwaway `research/<name>` branch.
+
+## It's working if
+
+- Naming the **destination** is the first act — before any ticket exists — because it fixes the scope every ticket is measured against.
+- One map is one `wayfinder:map` issue; tickets are its child issues, referred to by **name**, never a bare `#42`.
+- A session resolves **at most one ticket** (research tickets excepted), records the answer as a resolution comment, closes the ticket, and appends a one-line pointer to *Decisions so far*.
+- If the opening grill surfaces **no fog**, it stops and tells you the journey is small enough to skip the map.
+
+## Where it fits
+
+`wayfinder` is a big-idea **on-ramp**: an effort too large and foggy to spec in one sitting generates a cleared map of decisions, which then merges onto the main build flow. When the fog is pushed back and the way is clear, hand off to [to-spec](https://aihero.dev/skills-to-spec) to schedule the multi-session build (or, if the effort turned out small, implement directly). It leans on [grilling](https://aihero.dev/skills-grilling) and [domain-modeling](https://aihero.dev/skills-domain-modeling) to resolve individual tickets, and on [prototype](https://aihero.dev/skills-prototype) and [research](https://aihero.dev/skills-research) for the ticket types that need them. When you're unsure which skill or flow fits, [ask-matt](https://aihero.dev/skills-ask-matt) routes you.
@@ -0,0 +1,33 @@
+Quickstart:
+
+```bash
+npx skills add mattpocock/skills --skill=grill-me
+```
+
+```bash
+npx skills update grill-me
+```
+
+[Source](https://github.com/mattpocock/skills/tree/main/skills/productivity/grill-me)
+
+## What it does
+
+`grill-me` runs a relentless interview about a plan or design, walking every branch of the decision tree until you and the agent reach a **shared understanding**.
+
+It asks **one question at a time** and waits. It never dumps a batch of questions at you — that is bewildering — and where a question can be answered by reading the codebase, it goes and reads rather than asking. Each question comes with the agent's own recommended answer, so you are reacting to a proposal, not staring at a blank prompt.
+
+## When to reach for it
+
+You invoke this by typing `/grill-me` — the agent won't reach for it on its own.
+
+Reach for it before you build, when a plan feels roughly right but you can sense unresolved decisions hiding in it — the moment you want the soft spots found and forced into the open. If you want that same interrogation to also leave a paper trail of ADRs and a glossary behind, use [grill-with-docs](https://aihero.dev/skills-grill-with-docs) instead. And if the effort is too big to hold in one session and the route to the goal is still foggy — a greenfield project, a huge feature build — start further upstream with [wayfinder](https://aihero.dev/skills-wayfinder), which charts it as a map of decisions first and then merges back into this flow.
+
+## The decision tree
+
+The session walks the plan as a tree of decisions, resolving dependencies between them one by one — a parent decision settled before the choices that hang off it. The point is not to reach agreement quickly; it is to make every implicit call explicit, so nothing important is left silently assumed. You come out the other side with a plan whose branches have all been visited.
+
+`grill-me` is **stateless**: it writes nothing and leaves no workspace behind. It runs anywhere, and the only artifact is the sharpened understanding in the conversation itself. That is the deliberate contrast with [grill-with-docs](https://aihero.dev/skills-grill-with-docs), which captures the same interview as durable ADRs and a glossary.
+
+## Where it fits
+
+`grill-me` is a reach-for-it-anytime standalone — the pre-build stress test you run whenever a plan needs hardening. It is the stateless, user-invoked front door to the [grilling](https://aihero.dev/skills-grilling) primitive; its closest neighbour is [grill-with-docs](https://aihero.dev/skills-grill-with-docs), the stateful sibling that runs the same interview but additionally records the decisions as ADRs and a glossary. If the outcome is a spec you want written down, hand off to [to-spec](https://aihero.dev/skills-to-spec), which synthesises the settled understanding into a spec without re-interviewing you. When you're unsure which flow fits, [ask-matt](https://aihero.dev/skills-ask-matt) routes you.
@@ -0,0 +1,37 @@
+Quickstart:
+
+```bash
+npx skills add mattpocock/skills --skill=grilling
+```
+
+```bash
+npx skills update grilling
+```
+
+[Source](https://github.com/mattpocock/skills/tree/main/skills/productivity/grilling)
+
+## What it does
+
+`grilling` is the relentless interview that stress-tests a plan or design before you build it. It walks down the decision tree branch by branch, resolving the dependencies between decisions one at a time until you and the agent share the same understanding.
+
+It asks **one question at a time** and waits for your answer before the next — never a bulk list, which is bewildering. Each question comes with the agent's own recommended answer, and any question the codebase can settle it explores instead of asking you. It won't start enacting the plan until you confirm the shared understanding has been reached.
+
+## When to reach for it
+
+Type `/grilling`, or the agent reaches for it automatically when a task fits — this is the underlying primitive, not a user-only entry point.
+
+Reach for it when a plan or design still has soft spots and you want them surfaced before code is written. In practice you usually invoke it through one of its two wrappers rather than by name: for a plain grilling session use [grill-me](https://aihero.dev/skills-grill-me); to have the session also write ADRs and a glossary as it goes, use [grill-with-docs](https://aihero.dev/skills-grill-with-docs).
+
+## The decision tree
+
+The mental model is a **decision tree**: every plan branches into decisions, and decisions depend on each other. `grilling` descends that tree one node at a time, so an early answer can reshape which questions come next. That is why the questions arrive singly and in dependency order — a firehose of parallel questions loses the structure that makes the interview converge on a shared understanding.
+
+## Pulled out on purpose
+
+`grilling` is the **single source of truth** for the interview technique, split out as a model-invoked **primitive** so every skill that needs an interview can reach it instead of reinventing one. [grill-me](https://aihero.dev/skills-grill-me) and [grill-with-docs](https://aihero.dev/skills-grill-with-docs) are its two user-invoked front doors, but [improve-codebase-architecture](https://aihero.dev/skills-improve-codebase-architecture) and [triage](https://aihero.dev/skills-triage) also lean on it to pressure-test their own decisions.
+
+Keeping the technique in one place means you can also reach for it directly when you just want the interview — without the ADR-writing or ticket-shaping that its wrappers add on top.
+
+## Where it fits
+
+`grilling` is the interview **primitive** under the main build chain: [grill-with-docs](https://aihero.dev/skills-grill-with-docs) runs it to sharpen context before [to-spec](https://aihero.dev/skills-to-spec) writes the spec. When you're unsure which entry point fits, [ask-matt](https://aihero.dev/skills-ask-matt) routes you.
@@ -0,0 +1,36 @@
+Quickstart:
+
+```bash
+npx skills add mattpocock/skills --skill=handoff
+```
+
+```bash
+npx skills update handoff
+```
+
+[Source](https://github.com/mattpocock/skills/tree/main/skills/productivity/handoff)
+
+## What it does
+
+`handoff` compacts the current conversation into a **handoff document** — a single write-up a fresh agent can read to pick up the work where you left off.
+
+It does **not** re-state what already lives elsewhere. Anything captured in a spec, plan, ADR, issue, commit, or diff is referenced by path or URL, never copied. The document carries only the live thread — what you were doing, why, and what's next — and it's saved to your OS's temporary directory, not into the workspace, so it never becomes another artifact to maintain.
+
+## When to reach for it
+
+You invoke this by typing `/handoff` — the agent won't reach for it on its own. Pass a note about what the next session is for and the document is tailored to it.
+
+Reach for this when a conversation has gone long enough that its context is at risk — you're near a context limit, wrapping for the day, or deliberately handing the work to another agent — and you want the thread preserved without dragging the whole transcript along.
+
+## What the document carries
+
+- **The live thread** — what's in flight and why, in the conversation's own terms, minus anything already written down elsewhere.
+- **Suggested skills** — a pointer to the skills the next agent should reach for to continue.
+- **References, not copies** — links and paths to the specs, plans, ADRs, issues, and diffs that hold the settled detail.
+- **Redacted secrets** — API keys, passwords, and PII stripped before the document is written.
+
+The idea to hold onto is **compaction**: a handoff is the conversation squeezed down to just its resumable core, so a fresh agent inherits the momentum, not the noise.
+
+## Where it fits
+
+`handoff` is a reach-for-it-anytime standalone — it sits at the seam between two sessions rather than inside a build chain. It pairs naturally with the artifact-producing skills whose output it points at: [to-spec](https://aihero.dev/skills-to-spec), because a finished spec is exactly the kind of settled detail a handoff references instead of repeating. When you're unsure which skill fits the moment, [ask-matt](https://aihero.dev/skills-ask-matt) routes you.
@@ -0,0 +1,47 @@
+Quickstart:
+
+```bash
+npx skills add mattpocock/skills --skill=teach
+```
+
+```bash
+npx skills update teach
+```
+
+[Source](https://github.com/mattpocock/skills/tree/main/skills/productivity/teach)
+
+## What it does
+
+`teach` turns the current directory into a standing teaching workspace and teaches you one topic across many sessions — devising short, beautiful, interactive lessons tied to *why* you want to learn.
+
+It does **not** teach from the model's own memory. Parametric knowledge is treated as untrusted; before it can teach, it gathers high-trust resources and grounds every claim in a citation. And it is stateful — the workspace remembers what you've learned, so each session picks up where the last left off rather than starting from scratch.
+
+## When to reach for it
+
+You invoke this by typing `/teach` — the agent won't reach for it on its own.
+
+Reach for it when you want to *learn* a topic over time — a language, a framework, yoga, theoretical physics — and want the sessions to accumulate rather than evaporate. It is not for a one-off explanation; if you just need something clarified in the moment, ask directly. Reach for `teach` when the learning is a project.
+
+## Prerequisites
+
+`teach` builds a whole directory in place, so run it somewhere you're happy to keep as a dedicated workspace. Over time it writes:
+
+- `MISSION.md` — the reason you're learning this, which grounds everything else. If it's empty, `teach`'s first job is to question you until it isn't.
+- `RESOURCES.md` — the vetted, high-trust sources it teaches from.
+- `./lessons/*.html` — the numbered, self-contained lessons (the primary unit of teaching).
+- `./reference/*.html` — compressed cheat-sheets, algorithms, glossaries you'll return to.
+- `./learning-records/*.md` — what you've learned, ADR-style, used to judge what to teach next.
+- `./assets/*` — reusable components (a shared stylesheet first) so the lessons look like one course.
+- `NOTES.md` — your teaching preferences.
+
+## Mission, and the zone of proximal development
+
+Every lesson hangs off the **mission**. Without it, knowledge has nothing to attach to and lessons feel abstract — so the mission is the first thing `teach` pins down and keeps updating as you grow. From the mission and your learning records it computes your **zone of proximal development**: the next lesson should challenge you *just enough*, no more.
+
+## Storage strength, not fluency
+
+The word to think with is **storage strength** — long-term retention — as opposed to **fluency**, the in-the-moment recall that feels like mastery but isn't. `teach` deliberately builds the former through desirable difficulty: retrieval practice, spacing, and interleaving. Knowledge is taught first (where difficulty is the enemy), then skills are drilled through a tight feedback loop (where difficulty is the tool).
+
+## Where it fits
+
+`teach` is a reach-for-it-anytime standalone — a long-running learning project you drive session by session, not a step in a build chain. It shares no workflow with the other productivity skills; it simply owns its workspace directory and lives there. When you're unsure which skill or flow fits, [ask-matt](https://aihero.dev/skills-ask-matt) routes you.
@@ -0,0 +1,45 @@
+Quickstart:
+
+```bash
+npx skills add mattpocock/skills --skill=writing-great-skills
+```
+
+```bash
+npx skills update writing-great-skills
+```
+
+[Source](https://github.com/mattpocock/skills/tree/main/skills/productivity/writing-great-skills)
+
+## What it does
+
+`writing-great-skills` is the reference you write and edit skills against — the shared vocabulary and principles that make a skill predictable.
+
+A skill's job is to wrangle determinism out of a stochastic system, so the goal is not the same *output* every run but the same *process*. **Predictability** is the root virtue, and every design choice is judged against it — not against how clever, complete, or exhaustive the skill reads.
+
+## When to reach for it
+
+You invoke this by typing `/writing-great-skills` — the agent won't reach for it on its own.
+
+Reach for it whenever you're authoring a new skill or editing an existing one and want it to behave the same way every time: deciding invocation mode, writing a description, choosing what lives in `SKILL.md` versus a linked file, or diagnosing why a skill misfires.
+
+## Cognitive load
+
+The concept the whole reference turns on is **cognitive load** — and its counterpart, **context load**. Every skill spends one or the other:
+
+- A **model-invoked** skill keeps a description in the window every turn, so it costs **context load** but fires on its own.
+- A **user-invoked** skill strips that description; it costs zero context load, but now *you* are the index that has to remember it exists — that's **cognitive load**.
+
+Most of these skills are user-invoked, which is why cognitive load is the pressure the whole system is built to manage: when user-invoked skills multiply past what you can hold in your head, the cure is a **router skill** that names the others and when to reach for each. Once you're thinking in these two loads, most authoring decisions — split or don't, inline or disclose, model- or user-invoked — become the same trade made in different places.
+
+## The other levers
+
+The rest of the reference is the toolkit for spending those loads well:
+
+- **Leading words** — a compact concept already in the model's pretraining (_tight_, _red_, _tracer bullet_) that the agent thinks with while running the skill. It anchors execution *and* invocation in the fewest tokens; hunt restatements that a single word can retire.
+- **Information hierarchy** — the ladder from in-skill step, to in-skill reference, to external reference behind a **context pointer**. **Progressive disclosure** is the move down that ladder so the top stays legible.
+- **Pruning** — single source of truth, relevance, and the no-op test applied sentence by sentence, against **sediment** and **sprawl**.
+- **Failure modes** — **premature completion**, **duplication**, **sediment**, **sprawl**, **no-op** — to diagnose a skill that isn't behaving.
+
+## Where it fits
+
+This is a reach-for-it-anytime standalone reference — the meta-skill you consult while building the rest of the set, not a step in a chain. Its natural neighbour is any router you maintain, because a router is the direct cure for the cognitive load that user-invoked skills pile up; when you're unsure which skill or flow fits a task, [ask-matt](https://aihero.dev/skills-ask-matt) routes you over the whole set.
@@ -1,168 +0,0 @@
---
-name: github-triage
-description: Triage GitHub issues through a label-based state machine. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.
---
-
-# GitHub Issue Triage
-
-Triage issues in the current repo using a label-based state machine. Infer the repo from `git remote`. Use `gh` for all GitHub operations.
-
-## AI Disclaimer
-
-Every comment or issue posted to GitHub during triage **must** include the following disclaimer at the top of the comment body, before any other content:
-
-```
-> *This was generated by AI during triage.*
-```
-
-## Reference docs
-
- [AGENT-BRIEF.md](AGENT-BRIEF.md) — how to write durable agent briefs
- [OUT-OF-SCOPE.md](OUT-OF-SCOPE.md) — how the `.out-of-scope/` knowledge base works
-
-## Labels
-
-| Label             | Type     | Description                              |
-| ----------------- | -------- | ---------------------------------------- |
-| `bug`             | Category | Something is broken                      |
-| `enhancement`     | Category | New feature or improvement               |
-| `needs-triage`    | State    | Maintainer needs to evaluate this issue  |
-| `needs-info`      | State    | Waiting on reporter for more information |
-| `ready-for-agent` | State    | Fully specified, ready for AFK agent     |
-| `ready-for-human` | State    | Requires human implementation            |
-| `wontfix`         | State    | Will not be actioned                     |
-
-Every issue should have exactly **one** state label and **one** category label. If an issue has conflicting state labels (e.g. both `needs-triage` and `ready-for-agent`), flag the conflict and ask the maintainer which state is correct before doing anything else. Provide a recommendation.
-
-## State Machine
-
-| Current State  | Can transition to | Who triggers it        | What happens                                                                                                         |
-| -------------- | ----------------- | ---------------------- | -------------------------------------------------------------------------------------------------------------------- |
-| `unlabeled`    | `needs-triage`    | Skill (on first look)  | Issue needs maintainer evaluation. Skill applies label after presenting recommendation.                              |
-| `unlabeled`    | `ready-for-agent` | Maintainer (via skill) | Issue is already well-specified and agent-suitable. Skill writes agent brief comment, applies label.                 |
-| `unlabeled`    | `ready-for-human` | Maintainer (via skill) | Issue requires human implementation. Skill writes a brief comment summarizing the task, applies label.               |
-| `unlabeled`    | `wontfix`         | Maintainer (via skill) | Issue is spam, duplicate, or out of scope. Skill closes with comment (and writes `.out-of-scope/` for enhancements). |
-| `needs-triage` | `needs-info`      | Maintainer (via skill) | Issue is underspecified. Skill posts triage notes capturing progress so far + questions for reporter.                |
-| `needs-triage` | `ready-for-agent` | Maintainer (via skill) | Grilling session complete, agent-suitable. Skill writes agent brief comment, applies label.                          |
-| `needs-triage` | `ready-for-human` | Maintainer (via skill) | Grilling session complete, needs human. Skill writes a brief comment summarizing the task, applies label.            |
-| `needs-triage` | `wontfix`         | Maintainer (via skill) | Maintainer decides not to action. Skill closes with comment (and writes `.out-of-scope/` for enhancements).          |
-| `needs-info`   | `needs-triage`    | Skill (detects reply)  | Reporter has replied. Skill surfaces to maintainer for re-evaluation.                                                |
-
-An issue can only move along these transitions. The maintainer can override any state directly (see Quick State Override below), but the skill should flag if the transition is unusual.
-
-## Invocation
-
-The maintainer invokes `/github-triage` then describes what they want in natural language. The skill interprets the request and takes the appropriate action.
-
-Example requests:
-
- "Show me anything that needs my attention"
- "Let's look at #42"
- "Move #42 to ready-for-agent"
- "What's ready for agents to pick up?"
- "Are there any unlabeled issues?"
-
-## Workflow: Show What Needs Attention
-
-When the maintainer asks for an overview, query GitHub and present a summary grouped into three buckets:
-
-1. **Unlabeled issues** — new, no labels at all. These have never been triaged.
-2. **`needs-triage` issues** — maintainer needs to evaluate or continue evaluating.
-3. **`needs-info` issues with new activity** — the reporter has commented since the last triage notes comment. Check comment timestamps to determine this.
-
-Display counts per group. Within each group, show issues oldest first (longest-waiting gets attention first). For each issue, show: number, title, age, and a one-line summary of the issue body.
-
-Let the maintainer pick which issue to dive into.
-
-## Workflow: Triage a Specific Issue
-
-### Step 1: Gather context
-
-Before presenting anything to the maintainer:
-
- Read the full issue: body, all comments, all labels, who reported it, when
- If there are prior triage notes comments (from previous sessions), parse them to understand what has already been established
- Explore the codebase to build context — understand the domain, relevant interfaces, and existing behavior related to the issue
- Read `.out-of-scope/*.md` files and check if this issue matches or is similar to a previously rejected concept
-
-### Step 2: Present a recommendation
-
-Tell the maintainer:
-
- **Category recommendation:** bug or enhancement, with reasoning
- **State recommendation:** where this issue should go, with reasoning
- If it matches a prior out-of-scope rejection, surface that: "This is similar to `.out-of-scope/concept-name.md` — we rejected this before because X. Do you still feel the same way?"
- A brief summary of what you found in the codebase that's relevant
-
-Then wait for the maintainer's direction. They may:
-
- Agree and ask you to apply labels → do it
- Want to flesh it out → start a /domain-model session
- Override with a different state → apply their choice
- Want to discuss → have a conversation
-
-### Step 3: Bug reproduction (bugs only)
-
-If the issue is categorized as a bug, attempt to reproduce it before starting a /domain-model session. This will vary by codebase, but do your best:
-
- Read the reporter's reproduction steps (if provided)
- Explore the codebase to understand the relevant code paths
- Try to reproduce the bug: run tests, execute commands, or trace the logic to confirm the reported behavior
- If reproduction succeeds, report what you found to the maintainer — include the specific behavior you observed and where in the code it originates
- If reproduction fails, report that too — the bug may be environment-specific, already fixed, or the report may be inaccurate
- If the report lacks enough detail to attempt reproduction, note that — this is a strong signal the issue should move to `needs-info`
-
-The reproduction attempt informs the /domain-model session and the agent brief. A confirmed reproduction with a known code path makes for a much stronger brief.
-
-### Step 4: /domain-model session (if needed)
-
-If the issue needs to be fleshed out before it's ready for an agent, interview the maintainer to build a complete specification. Use the /domain-model skill.
-
-### Step 5: Apply the outcome
-
-Depending on the outcome:
-
- **ready-for-agent** — post an agent brief comment (see [AGENT-BRIEF.md](AGENT-BRIEF.md))
- **ready-for-human** — post a comment summarizing the task, what was established during triage, and why it needs human implementation. Use the same structure as an agent brief but note the reason it can't be delegated to an agent (e.g. requires judgment calls, external system access, design decisions, or manual testing).
- **needs-info** — post triage notes with progress so far and questions for the reporter (see Needs Info Output below)
- **wontfix (bug)** — post a polite comment explaining why, then close the issue
- **wontfix (enhancement)** — write to `.out-of-scope/`, post a comment linking to it, then close the issue (see [OUT-OF-SCOPE.md](OUT-OF-SCOPE.md))
- **needs-triage** — apply the label. Optionally leave a comment if there's partial progress to capture.
-
-## Workflow: Quick State Override
-
-When the maintainer explicitly tells you to move an issue to a specific state (e.g. "move #42 to ready-for-agent"), trust their judgment and apply the label directly.
-
-Still show a confirmation of what you're about to do: which labels will be added/removed, and whether you'll post a comment or close the issue. But skip the /domain-model session entirely.
-
-If moving to `ready-for-agent` without a /domain-model session, ask the maintainer if they want to write a brief agent brief comment or skip it.
-
-## Needs Info Output
-
-When moving an issue to `needs-info`, post a comment that captures the interview progress and tells the reporter what's needed:
-
-```markdown
-## Triage Notes
-
-**What we've established so far:**
-
- point 1
- point 2
-
-**What we still need from you (@reporter):**
-
- question 1
- question 2
-```
-
-Include everything resolved during the /domain-model session in "established so far" — this work should not be lost. The questions for the reporter should be specific and actionable, not vague ("please provide more info").
-
-## Resuming Previous Sessions
-
-When triaging an issue that already has triage notes from a previous session:
-
-1. Read all comments to find prior triage notes
-2. Parse what was already established
-3. Check if the reporter has answered any outstanding questions
-4. Present the maintainer with an updated picture: "Here's where we left off, and here's what the reporter has said since"
-5. Continue the /domain-model session from where it stopped — do not re-ask resolved questions
@@ -1,10 +0,0 @@
---
-name: grill-me
-description: Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
---
-
-Interview me relentlessly about every aspect of this plan until we reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one. For each question, provide your recommended answer.
-
-Ask the questions one at a time.
-
-If a question can be answered by exploring the codebase, explore the codebase instead.
@@ -1,53 +0,0 @@
-# Language
-
-Shared vocabulary for every suggestion this skill makes. Use these terms exactly — don't substitute "component," "service," "API," or "boundary." Consistent language is the whole point.
-
-## Terms
-
-**Module**
-Anything with an interface and an implementation. Deliberately scale-agnostic — applies equally to a function, class, package, or tier-spanning slice.
-_Avoid_: unit, component, service.
-
-**Interface**
-Everything a caller must know to use the module correctly. Includes the type signature, but also invariants, ordering constraints, error modes, required configuration, and performance characteristics.
-_Avoid_: API, signature (too narrow — those refer only to the type-level surface).
-
-**Implementation**
-What's inside a module — its body of code. Distinct from **Adapter**: a thing can be a small adapter with a large implementation (a Postgres repo) or a large adapter with a small implementation (an in-memory fake). Reach for "adapter" when the seam is the topic; "implementation" otherwise.
-
-**Depth**
-Leverage at the interface — the amount of behaviour a caller (or test) can exercise per unit of interface they have to learn. A module is **deep** when a large amount of behaviour sits behind a small interface. A module is **shallow** when the interface is nearly as complex as the implementation.
-
-**Seam** _(from Michael Feathers)_
-A place where you can alter behaviour without editing in that place. The *location* at which a module's interface lives. Choosing where to put the seam is its own design decision, distinct from what goes behind it.
-_Avoid_: boundary (overloaded with DDD's bounded context).
-
-**Adapter**
-A concrete thing that satisfies an interface at a seam. Describes *role* (what slot it fills), not substance (what's inside).
-
-**Leverage**
-What callers get from depth. More capability per unit of interface they have to learn. One implementation pays back across N call sites and M tests.
-
-**Locality**
-What maintainers get from depth. Change, bugs, knowledge, and verification concentrate at one place rather than spreading across callers. Fix once, fixed everywhere.
-
-## Principles
-
- **Depth is a property of the interface, not the implementation.** A deep module can be internally composed of small, mockable, swappable parts — they just aren't part of the interface. A module can have **internal seams** (private to its implementation, used by its own tests) as well as the **external seam** at its interface.
- **The deletion test.** Imagine deleting the module. If complexity vanishes, the module wasn't hiding anything (it was a pass-through). If complexity reappears across N callers, the module was earning its keep.
- **The interface is the test surface.** Callers and tests cross the same seam. If you want to test *past* the interface, the module is probably the wrong shape.
- **One adapter means a hypothetical seam. Two adapters means a real one.** Don't introduce a seam unless something actually varies across it.
-
-## Relationships
-
- A **Module** has exactly one **Interface** (the surface it presents to callers and tests).
- **Depth** is a property of a **Module**, measured against its **Interface**.
- A **Seam** is where a **Module**'s **Interface** lives.
- An **Adapter** sits at a **Seam** and satisfies the **Interface**.
- **Depth** produces **Leverage** for callers and **Locality** for maintainers.
-
-## Rejected framings
-
- **Depth as ratio of implementation-lines to interface-lines** (Ousterhout): rewards padding the implementation. We use depth-as-leverage instead.
- **"Interface" as the TypeScript `interface` keyword or a class's public methods**: too narrow — interface here includes every fact a caller must know.
- **"Boundary"**: overloaded with DDD's bounded context. Say **seam** or **interface**.
@@ -1,76 +0,0 @@
---
-name: improve-codebase-architecture
-description: Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
---
-
-# Improve Codebase Architecture
-
-Surface architectural friction and propose **deepening opportunities** — refactors that turn shallow modules into deep ones. The aim is testability and AI-navigability.
-
-## Glossary
-
-Use these terms exactly in every suggestion. Consistent language is the point — don't drift into "component," "service," "API," or "boundary." Full definitions in [LANGUAGE.md](LANGUAGE.md).
-
- **Module** — anything with an interface and an implementation (function, class, package, slice).
- **Interface** — everything a caller must know to use the module: types, invariants, error modes, ordering, config. Not just the type signature.
- **Implementation** — the code inside.
- **Depth** — leverage at the interface: a lot of behaviour behind a small interface. **Deep** = high leverage. **Shallow** = interface nearly as complex as the implementation.
- **Seam** — where an interface lives; a place behaviour can be altered without editing in place. (Use this, not "boundary.")
- **Adapter** — a concrete thing satisfying an interface at a seam.
- **Leverage** — what callers get from depth.
- **Locality** — what maintainers get from depth: change, bugs, knowledge concentrated in one place.
-
-Key principles (see [LANGUAGE.md](LANGUAGE.md) for the full list):
-
- **Deletion test**: imagine deleting the module. If complexity vanishes, it was a pass-through. If complexity reappears across N callers, it was earning its keep.
- **The interface is the test surface.**
- **One adapter = hypothetical seam. Two adapters = real seam.**
-
-This skill is _informed_ by the project's domain model — `CONTEXT.md` and any `docs/adr/`. The domain language gives names to good seams; ADRs record decisions the skill should not re-litigate. See [CONTEXT-FORMAT.md](../domain-model/CONTEXT-FORMAT.md) and [ADR-FORMAT.md](../domain-model/ADR-FORMAT.md).
-
-## Process
-
-### 1. Explore
-
-Read existing documentation first:
-
- `CONTEXT.md` (or `CONTEXT-MAP.md` + each `CONTEXT.md` in a multi-context repo)
- Relevant ADRs in `docs/adr/` (and any context-scoped `docs/adr/` directories)
-
-If any of these files don't exist, proceed silently — don't flag their absence or suggest creating them upfront.
-
-Then use the Agent tool with `subagent_type=Explore` to walk the codebase. Don't follow rigid heuristics — explore organically and note where you experience friction:
-
- Where does understanding one concept require bouncing between many small modules?
- Where are modules **shallow** — interface nearly as complex as the implementation?
- Where have pure functions been extracted just for testability, but the real bugs hide in how they're called (no **locality**)?
- Where do tightly-coupled modules leak across their seams?
- Which parts of the codebase are untested, or hard to test through their current interface?
-
-Apply the **deletion test** to anything you suspect is shallow: would deleting it concentrate complexity, or just move it? A "yes, concentrates" is the signal you want.
-
-### 2. Present candidates
-
-Present a numbered list of deepening opportunities. For each candidate:
-
- **Files** — which files/modules are involved
- **Problem** — why the current architecture is causing friction
- **Solution** — plain English description of what would change
- **Benefits** — explained in terms of locality and leverage, and also in how tests would improve
-
-**Use CONTEXT.md vocabulary for the domain, and [LANGUAGE.md](LANGUAGE.md) vocabulary for the architecture.** If `CONTEXT.md` defines "Order," talk about "the Order intake module" — not "the FooBarHandler," and not "the Order service."
-
-**ADR conflicts**: if a candidate contradicts an existing ADR, only surface it when the friction is real enough to warrant revisiting the ADR. Mark it clearly (e.g. _"contradicts ADR-0007 — but worth reopening because…"_). Don't list every theoretical refactor an ADR forbids.
-
-Do NOT propose interfaces yet. Ask the user: "Which of these would you like to explore?"
-
-### 3. Grilling loop
-
-Once the user picks a candidate, drop into a grilling conversation. Walk the design tree with them — constraints, dependencies, the shape of the deepened module, what sits behind the seam, what tests survive.
-
-Side effects happen inline as decisions crystallize:
-
- **Naming a deepened module after a concept not in `CONTEXT.md`?** Add the term to `CONTEXT.md` — same discipline as `/domain-model` (see [CONTEXT-FORMAT.md](../domain-model/CONTEXT-FORMAT.md)). Create the file lazily if it doesn't exist.
- **Sharpening a fuzzy term during the conversation?** Update `CONTEXT.md` right there.
- **User rejects the candidate with a load-bearing reason?** Offer an ADR, framed as: _"Want me to record this as an ADR so future architecture reviews don't re-suggest it?"_ Only offer when the reason would actually be needed by a future explorer to avoid re-suggesting the same thing — skip ephemeral reasons ("not worth it right now") and self-evident ones. See [ADR-FORMAT.md](../domain-model/ADR-FORMAT.md).
- **Want to explore alternative interfaces for the deepened module?** See [INTERFACE-DESIGN.md](INTERFACE-DESIGN.md).
@@ -0,0 +1,20 @@
+{
+  "name": "mattpocock-skills",
+  "version": "1.1.0",
+  "private": true,
+  "description": "Matt Pocock's agent skills for real engineering",
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/mattpocock/skills"
+  },
+  "license": "MIT",
+  "scripts": {
+    "changeset": "changeset",
+    "version": "changeset version"
+  },
+  "devDependencies": {
+    "@changesets/changelog-github": "^0.7.0",
+    "@changesets/cli": "^2.30.0"
+  },
+  "packageManager": "npm@10.9.4"
+}
@@ -0,0 +1,56 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# NOTE: This is a dev-only script, intended for use by maintainers of this repo.
+# It is not a supported installer. Modifications to it — or requests for
+# modifications — will not be approved.
+#
+# Links all skills in the repository into the local skill directories used by
+# each agent harness:
+#   - ~/.claude/skills  — Claude Code
+#   - ~/.agents/skills  — Codex and other Agent Skills-compatible harnesses
+# Each entry is a symlink into this repo, so a `git pull` is all that's needed
+# to keep installed skills up to date.
+
+REPO="$(cd "$(dirname "$0")/.." && pwd)"
+DESTS=("$HOME/.claude/skills" "$HOME/.agents/skills")
+
+# Collect the repo's skills once, link into every destination.
+names=()
+srcs=()
+while IFS= read -r -d '' skill_md; do
+  src="$(dirname "$skill_md")"
+  names+=("$(basename "$src")")
+  srcs+=("$src")
+done < <(find "$REPO/skills" -name SKILL.md -not -path '*/node_modules/*' -not -path '*/deprecated/*' -print0)
+
+for DEST in "${DESTS[@]}"; do
+  # If $DEST is a symlink that resolves into this repo, we'd end up writing the
+  # per-skill symlinks back into the repo's own skills/ tree. Detect and bail
+  # out instead of polluting the working copy.
+  if [ -L "$DEST" ]; then
+    resolved="$(readlink -f "$DEST")"
+    case "$resolved" in
+      "$REPO"|"$REPO"/*)
+        echo "error: $DEST is a symlink into this repo ($resolved)." >&2
+        echo "Remove it (rm \"$DEST\") and re-run; the script will recreate it as a real dir." >&2
+        exit 1
+        ;;
+    esac
+  fi
+
+  mkdir -p "$DEST"
+
+  for i in "${!names[@]}"; do
+    name="${names[$i]}"
+    src="${srcs[$i]}"
+    target="$DEST/$name"
+
+    if [ -e "$target" ] && [ ! -L "$target" ]; then
+      rm -rf "$target"
+    fi
+
+    ln -sfn "$src" "$target"
+    echo "linked $name -> $src ($DEST)"
+  done
+done
@@ -0,0 +1,7 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+REPO="$(cd "$(dirname "$0")/.." && pwd)"
+
+cd "$REPO"
+find . -name SKILL.md -not -path '*/node_modules/*' | sed 's|^\./||' | sort
@@ -0,0 +1,8 @@
+# Deprecated
+
+Skills I no longer use.
+
+- **[design-an-interface](./design-an-interface/SKILL.md)** — Generate multiple radically different interface designs for a module using parallel sub-agents.
+- **[qa](./qa/SKILL.md)** — Interactive QA session where user reports bugs conversationally and the agent files GitHub issues.
+- **[request-refactor-plan](./request-refactor-plan/SKILL.md)** — Create a detailed refactor plan with tiny commits via user interview, then file it as a GitHub issue.
+- **[ubiquitous-language](./ubiquitous-language/SKILL.md)** — Extract a DDD-style ubiquitous language glossary from the current conversation.
@@ -0,0 +1,3 @@
+interface:
+  display_name: "Design an Interface"
+  short_description: "Explore alternative module interfaces"
@@ -0,0 +1,3 @@
+interface:
+  display_name: "QA"
+  short_description: "Conversational QA that files issues"
@@ -0,0 +1,3 @@
+interface:
+  display_name: "Request Refactor Plan"
+  short_description: "Plan a safe incremental refactor"
@@ -0,0 +1,5 @@
+interface:
+  display_name: "Ubiquitous Language"
+  short_description: "Build a shared domain glossary"
+policy:
+  allow_implicit_invocation: false
@@ -0,0 +1,31 @@
+# Engineering
+
+Skills I use daily for code work.
+
+## User-invoked
+
+Reachable only when you type them (Claude Code: `disable-model-invocation: true`; Codex: `policy.allow_implicit_invocation: false` in `agents/openai.yaml`).
+
+- **[ask-matt](./ask-matt/SKILL.md)** — Ask which skill or flow fits your situation. A router over the user-invoked skills in this repo.
+- **[grill-with-docs](./grill-with-docs/SKILL.md)** — Grilling session that also builds your project's domain model, sharpening terminology and updating `CONTEXT.md` and ADRs inline.
+- **[triage](./triage/SKILL.md)** — Move issues through a state machine of triage roles.
+- **[improve-codebase-architecture](./improve-codebase-architecture/SKILL.md)** — Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
+- **[setup-matt-pocock-skills](./setup-matt-pocock-skills/SKILL.md)** — Configure this repo for the engineering skills (issue tracker, triage labels, domain doc layout). Run once per repo.
+- **[to-spec](./to-spec/SKILL.md)** — Turn the current conversation into a spec and publish it to the issue tracker.
+- **[to-tickets](./to-tickets/SKILL.md)** — Break any plan, spec, or conversation into a set of tracer-bullet tickets, each declaring its blocking edges — text in a local file, or native blocking links on a real tracker.
+- **[implement](./implement/SKILL.md)** — Build the work described by a spec or set of tickets, driving `/tdd` at pre-agreed seams and closing out with `/code-review` before committing.
+- **[wayfinder](./wayfinder/SKILL.md)** — Plan a huge chunk of work — more than one agent session can hold — as a shared map of decision tickets on the issue tracker, resolved one at a time until the way to the destination is clear.
+
+## Model-invoked
+
+Model- or user-reachable (rich trigger phrasing so the model can reach for them).
+
+- **[prototype](./prototype/SKILL.md)** — Build a throwaway prototype to answer a design question: a runnable terminal app for state/logic, or several toggleable UI variations.
+
+- **[diagnosing-bugs](./diagnosing-bugs/SKILL.md)** — Disciplined diagnosis loop for hard bugs and performance regressions: reproduce → minimise → hypothesise → instrument → fix → regression-test.
+- **[research](./research/SKILL.md)** — Investigate a question against high-trust primary sources and capture the findings as a cited Markdown file in the repo, run as a background agent.
+- **[tdd](./tdd/SKILL.md)** — Test-driven development with a red-green-refactor loop. Builds features or fixes bugs one vertical slice at a time.
+- **[domain-modeling](./domain-modeling/SKILL.md)** — Actively build and sharpen a project's domain model — challenge terms, stress-test with scenarios, update `CONTEXT.md` and ADRs inline.
+- **[codebase-design](./codebase-design/SKILL.md)** — Shared discipline and vocabulary for designing deep modules: small interfaces, clean seams, testable through the interface.
+- **[code-review](./code-review/SKILL.md)** — Two-axis review of the diff since a fixed point: **Standards** (does it follow the repo's coding standards, plus a Fowler smell baseline?) and **Spec** (does it faithfully implement the originating issue/PRD?), run as parallel sub-agents.
+- **[resolving-merge-conflicts](./resolving-merge-conflicts/SKILL.md)** — Work through an in-progress git merge or rebase conflict hunk by hunk, resolving by intent traced to each side's primary source, then finish the operation — never `--abort`.
@@ -0,0 +1,78 @@
+---
+name: ask-matt
+description: Ask which skill or flow fits your situation. A router over the skills in this repo.
+disable-model-invocation: true
+---
+
+# Ask Matt
+
+You don't remember every skill, so ask.
+
+A **flow** is a path through the skills. Most paths run along one **main flow**, and two **on-ramps** merge onto it. Everything else is standalone, or a vocabulary layer that runs underneath.
+
+## The main flow: idea → ship
+
+The route most work travels. You have an idea and want it built.
+
+1. **`/grill-with-docs`** — sharpen the idea by interview. Start here when you **have a codebase**: it's stateful, retaining what it learns in `CONTEXT.md` and ADRs. (No codebase? Use `/grill-me` — see Standalone. Both run the same `/grilling` primitive; `grill-with-docs` is the one that leaves a paper trail.)
+2. **Branch — can you settle every question in conversation?** If a question needs a runnable answer (state, business logic, a UI you have to see), detour through a prototype, bridged by **`/handoff`** in both directions (see Crossing sessions):
+   - **`/handoff`** out, then open a fresh session against that file,
+   - **`/prototype`** to answer the question with throwaway code,
+   - **`/handoff`** back what you learned, and reference it from the original idea thread.
+3. **Branch — is this a multi-session build?**
+   - **Yes** → **`/to-spec`** (turn the thread into a spec), then **`/to-tickets`** to split it into tracer-bullet tickets, each declaring its **blocking edges**. On a local tracker that's one file per ticket under `.scratch/<feature>/issues/`, worked blockers-first by hand; on a real tracker the edges become native blocking links, so any ticket whose blockers are done can be grabbed — kick off **`/implement`** per ticket, **clearing context between each one**.
+   - **No** → **`/implement`** right here, in the same context window.
+
+   Either way, **`/implement`** builds each issue by driving **`/tdd`** internally — one red-green slice at a time — then closes out by running **`/code-review`**, a two-axis review (Standards + Spec) of the diff, before committing. Reach for **`/tdd`** on its own when you just want to build a concrete behaviour test-first without a full spec, and **`/code-review`** on its own whenever you want to review a branch or PR against a fixed point.
+
+### Context hygiene
+
+Keep steps 1–3 in **one unbroken context window** — don't compact or clear until after `/to-tickets` — so the grilling, spec, and tickets all build on the same thinking. Each `/implement` then starts fresh, working from the ticket.
+
+The limit on this is the **[smart zone](https://www.aihero.dev/ai-coding-dictionary/smart-zone)**: the window (~120k tokens on state-of-the-art models) within which the model still reasons sharply. If a session approaches it before `/to-tickets`, don't push on degraded — `/handoff` and continue in a fresh thread.
+
+## On-ramps
+
+A starting situation that generates work, then merges onto the main flow.
+
+- **Bugs and requests piling up** → **`/triage`**. It moves issues through triage roles and produces agent-ready issues, which **`/implement`** later picks up.
+
+  Triage is only for issues **you didn't create** — bug reports, incoming feature requests, anything that arrives raw. Tickets that `/to-tickets` produced are already agent-ready, so **don't triage them**.
+
+- **Something's broken** → **`/diagnosing-bugs`**. For the hard ones: the bug that resists a first glance, the intermittent flake, the regression that crept in between two known-good states. It refuses to theorise until it has a **tight feedback loop** — one command that already goes red on *this* bug — then fixes with a regression test. Its post-mortem hands off to **`/improve-codebase-architecture`** when the real finding is that there's no good seam to lock the bug down.
+
+- **A huge, foggy effort — a greenfield project or a huge feature build, too big for one session** → **`/wayfinder`**, the most cognitively demanding flow here. When the way from here to the destination isn't visible yet, it charts a **shared map** of **decision tickets** on the issue tracker and resolves them one at a time — producing **decisions, not deliverables** — until the fog is pushed back and the way is clear. Where **`/grill-with-docs`** sharpens an idea you can hold in one session, wayfinder is for the idea you can't — and it's slower and denser, so save it for exactly that, never a well-scoped feature.
+
+  When the map clears, **it hands off, it doesn't build**: merge onto the main flow at **`/to-spec`**, which collapses the map's linked decisions into a buildable plan, then `/to-tickets` and `/implement` as usual. Looping the map straight into `/implement` skips that collapse and throws the linked detail away — go straight to `/implement` only when the effort turned out genuinely small.
+
+## Codebase health
+
+Not feature work — upkeep.
+
+- **`/improve-codebase-architecture`** — run whenever you have a spare moment to keep the codebase good for agents to operate in. It surfaces **deepening opportunities**; picking one _generates an idea_ you can take into the main flow at `/grill-with-docs`. It's the survey that finds the candidates; **`/codebase-design`** (below) is the bench you design the chosen one on.
+
+## Vocabulary underneath
+
+Two model-invoked references that run *beneath* the other skills — each the single source of truth for its vocabulary. Reach for them directly when the **words**, not the process, are the problem; or let the skills above pull them in.
+
+- **`/domain-modeling`** — sharpen the project's *domain* language: challenge a fuzzy term, resolve an overloaded word ("account" doing three jobs), record a hard-to-reverse decision as an ADR. It's the active discipline `/grill-with-docs` drives to keep `CONTEXT.md` a clean glossary.
+- **`/codebase-design`** — the deep-module vocabulary (module, interface, depth, seam, adapter, leverage, locality) for designing a module's *shape*: a lot of behaviour behind a small interface at a clean seam. `/tdd` and `/improve-codebase-architecture` both speak it.
+
+## Crossing sessions
+
+- **`/handoff`** — when a thread is full or you need to branch off (e.g. into a `/prototype` session), this compacts the conversation into a markdown file. You don't continue in place — you **open a new session and reference that file** to carry the context across. It's the bridge between context windows, in either direction. Use it when you want a **fresh session** but need the **current conversation preserved**.
+- **`/compact`** (built-in) — stay in the **same conversation**, letting the earlier turns be summarized. Use it at **intentional breaks between phases**, when you don't mind losing the verbatim history. Don't compact mid-phase — the agent can lose its way. `/handoff` forks; `/compact` continues.
+
+## Standalone
+
+Off the main flow entirely.
+
+- **`/grill-me`** — the same relentless interview as `/grill-with-docs`, but for when you have **no codebase**. Stateless: it saves nothing locally, builds no `CONTEXT.md`. Reach for it to sharpen any plan or design that doesn't live in a repo.
+- **`/prototype`** — a small, throwaway program that answers one design question: does this state model feel right, or what should this UI look like. Throwaway from day one — keep the answer, delete the code. It's the detour in step 2 of the main flow, but reach for it any time a design question is hard to settle on paper.
+- **`/research`** — delegate reading legwork to a **background agent**: it investigates a question against **primary sources**, then leaves a cited Markdown file in the repo. Keep working while it reads. The file it produces is something to take *into* the main flow at `/grill-with-docs` — research feeds the thinking, it doesn't replace it.
+- **`/teach`** — learn a concept over multiple sessions, using the current directory as a stateful workspace.
+- **`/writing-great-skills`** — reference for writing and editing skills well.
+
+## Precondition
+
+**`/setup-matt-pocock-skills`** — run before your first engineering flow to configure the issue tracker, triage labels, and doc layout the other skills assume. Custom issue trackers also work.
@@ -0,0 +1,5 @@
+interface:
+  display_name: "Ask Matt"
+  short_description: "Find the right skill or workflow"
+policy:
+  allow_implicit_invocation: false
@@ -0,0 +1,89 @@
+---
+name: code-review
+description: Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
+---
+
+Two-axis review of the diff between `HEAD` and a fixed point the user supplies:
+
+- **Standards** — does the code conform to this repo's documented coding standards?
+- **Spec** — does the code faithfully implement the originating issue / PRD / spec?
+
+Both axes run as **parallel sub-agents** so they don't pollute each other's context, then this skill aggregates their findings.
+
+The issue tracker should have been provided to you — run `/setup-matt-pocock-skills` if `docs/agents/issue-tracker.md` is missing.
+
+## Process
+
+### 1. Pin the fixed point
+
+Whatever the user said is the fixed point — a commit SHA, branch name, tag, `main`, `HEAD~5`, etc. If they didn't specify one, ask for it.
+
+Capture the diff command once: `git diff <fixed-point>...HEAD` (three-dot, so the comparison is against the merge-base). Also note the list of commits via `git log <fixed-point>..HEAD --oneline`.
+
+Before going further, confirm the fixed point resolves (`git rev-parse <fixed-point>`) and the diff is non-empty. A bad ref or empty diff should fail here — not inside two parallel sub-agents.
+
+### 2. Identify the spec source
+
+Look for the originating spec, in this order:
+
+1. Issue references in the commit messages (`#123`, `Closes #45`, GitLab `!67`, etc.) — fetch via the workflow in `docs/agents/issue-tracker.md`.
+2. A path the user passed as an argument.
+3. A PRD/spec file under `docs/`, `specs/`, or `.scratch/` matching the branch name or feature.
+4. If nothing is found, ask the user where the spec is. If they say there isn't one, the **Spec** sub-agent will skip and report "no spec available".
+
+### 3. Identify the standards sources
+
+Anything in the repo that documents how code should be written, such as `CODING_STANDARDS.md` or `CONTRIBUTING.md`.
+
+On top of whatever the repo documents, the Standards axis always carries the **smell baseline** below — a fixed set of Fowler code smells (_Refactoring_, ch.3) that applies even when a repo documents nothing. Two rules bind it:
+
+- **The repo overrides.** A documented repo standard always wins; where it endorses something the baseline would flag, suppress the smell.
+- **Always a judgement call.** Each smell is a labelled heuristic ("possible Feature Envy"), never a hard violation — and, like any standard here, skip anything tooling already enforces.
+
+Each smell reads *what it is* → *how to fix*; match it against the diff:
+
+- **Mysterious Name** — a function, variable, or type whose name doesn't reveal what it does or holds. → rename it; if no honest name comes, the design's murky.
+- **Duplicated Code** — the same logic shape appears in more than one hunk or file in the change. → extract the shared shape, call it from both.
+- **Feature Envy** — a method that reaches into another object's data more than its own. → move the method onto the data it envies.
+- **Data Clumps** — the same few fields or params keep travelling together (a type wanting to be born). → bundle them into one type, pass that.
+- **Primitive Obsession** — a primitive or string standing in for a domain concept that deserves its own type. → give the concept its own small type.
+- **Repeated Switches** — the same `switch`/`if`-cascade on the same type recurs across the change. → replace with polymorphism, or one map both sites share.
+- **Shotgun Surgery** — one logical change forces scattered edits across many files in the diff. → gather what changes together into one module.
+- **Divergent Change** — one file or module is edited for several unrelated reasons. → split so each module changes for one reason.
+- **Speculative Generality** — abstraction, parameters, or hooks added for needs the spec doesn't have. → delete it; inline back until a real need shows.
+- **Message Chains** — long `a.b().c().d()` navigation the caller shouldn't depend on. → hide the walk behind one method on the first object.
+- **Middle Man** — a class or function that mostly just delegates onward. → cut it, call the real target direct.
+- **Refused Bequest** — a subclass or implementer that ignores or overrides most of what it inherits. → drop the inheritance, use composition.
+
+### 4. Spawn both sub-agents in parallel
+
+Send a single message with two `Agent` tool calls. Use the `general-purpose` subagent for both.
+
+**Standards sub-agent prompt** — include:
+
+- The full diff command and commit list.
+- The list of standards-source files you found in step 3, **plus the smell baseline from step 3** pasted in full — the sub-agent has no other access to it.
+- The brief: "Report — per file/hunk where relevant — (a) every place the diff violates a documented standard: cite the standard (file + the rule); and (b) any baseline smell you spot: name it and quote the hunk. Distinguish hard violations from judgement calls — documented-standard breaches can be hard, but baseline smells are always judgement calls, and a documented repo standard overrides the baseline. Skip anything tooling enforces. Under 400 words."
+
+**Spec sub-agent prompt** — include:
+
+- The diff command and commit list.
+- The path or fetched contents of the spec.
+- The brief: "Report: (a) requirements the spec asked for that are missing or partial; (b) behaviour in the diff that wasn't asked for (scope creep); (c) requirements that look implemented but where the implementation looks wrong. Quote the spec line for each finding. Under 400 words."
+
+If the spec is missing, skip the Spec sub-agent and note this in the final report.
+
+### 5. Aggregate
+
+Present the two reports under `## Standards` and `## Spec` headings, verbatim or lightly cleaned. Do **not** merge or rerank findings — the two axes are deliberately separate (see _Why two axes_).
+
+End with a one-line summary: total findings per axis, and the worst issue _within each axis_ (if any). Don't pick a single winner across axes — that's the reranking the separation exists to prevent.
+
+## Why two axes
+
+A change can pass one axis and fail the other:
+
+- Code that follows every standard but implements the wrong thing → **Standards pass, Spec fail.**
+- Code that does exactly what the issue asked but breaks the project's conventions → **Spec pass, Standards fail.**
+
+Reporting them separately stops one axis from masking the other.
@@ -0,0 +1,3 @@
+interface:
+  display_name: "Code Review"
+  short_description: "Review a diff on standards and spec"
@@ -1,6 +1,6 @@
 # Deepening

-How to deepen a cluster of shallow modules safely, given its dependencies. Assumes the vocabulary in [LANGUAGE.md](LANGUAGE.md) — **module**, **interface**, **seam**, **adapter**.
+How to deepen a cluster of shallow modules safely, given its dependencies. Assumes the vocabulary in [SKILL.md](SKILL.md) — **module**, **interface**, **seam**, **adapter**.

 ## Dependency categories

@@ -1,8 +1,8 @@
-# Interface Design
+# Design It Twice

 When the user wants to explore alternative interfaces for a chosen deepening candidate, use this parallel sub-agent pattern. Based on "Design It Twice" (Ousterhout) — your first idea is unlikely to be the best.

-Uses the vocabulary in [LANGUAGE.md](LANGUAGE.md) — **module**, **interface**, **seam**, **adapter**, **leverage**.
+Uses the vocabulary in [SKILL.md](SKILL.md) — **module**, **interface**, **seam**, **adapter**, **leverage**.

 ## Process

@@ -27,7 +27,7 @@ Prompt each sub-agent with a separate technical brief (file paths, coupling deta
 - Agent 3: "Optimise for the most common caller — make the default case trivial."
 - Agent 4 (if applicable): "Design around ports & adapters for cross-seam dependencies."

-Include both [LANGUAGE.md](LANGUAGE.md) vocabulary and CONTEXT.md vocabulary in the brief so each sub-agent names things consistently with the architecture language and the project's domain language.
+Include both [SKILL.md](SKILL.md) vocabulary and CONTEXT.md vocabulary in the brief so each sub-agent names things consistently with the architecture language and the project's domain language.

 Each sub-agent outputs:

@@ -0,0 +1,114 @@
+---
+name: codebase-design
+description: Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
+---
+
+# Codebase Design
+
+Design **deep modules**: a lot of behaviour behind a small interface, placed at a clean seam, testable through that interface. Use this language and these principles wherever code is being designed or restructured. The aim is leverage for callers, locality for maintainers, and testability for everyone.
+
+## Glossary
+
+Use these terms exactly — don't substitute "component," "service," "API," or "boundary." Consistent language is the whole point.
+
+**Module** — anything with an interface and an implementation. Deliberately scale-agnostic: a function, class, package, or tier-spanning slice. _Avoid_: unit, component, service.
+
+**Interface** — everything a caller must know to use the module correctly: the type signature, but also invariants, ordering constraints, error modes, required configuration, and performance characteristics. _Avoid_: API, signature (too narrow — they refer only to the type-level surface).
+
+**Implementation** — what's inside a module, its body of code. Distinct from **Adapter**: a thing can be a small adapter with a large implementation (a Postgres repo) or a large adapter with a small implementation (an in-memory fake). Reach for "adapter" when the seam is the topic; "implementation" otherwise.
+
+**Depth** — leverage at the interface: the amount of behaviour a caller (or test) can exercise per unit of interface they have to learn. A module is **deep** when a large amount of behaviour sits behind a small interface, **shallow** when the interface is nearly as complex as the implementation.
+
+**Seam** _(Michael Feathers)_ — a place where you can alter behaviour without editing in that place; the *location* at which a module's interface lives. Where to put the seam is its own design decision, distinct from what goes behind it. _Avoid_: boundary (overloaded with DDD's bounded context).
+
+**Adapter** — a concrete thing that satisfies an interface at a seam. Describes *role* (what slot it fills), not substance (what's inside).
+
+**Leverage** — what callers get from depth: more capability per unit of interface they learn. One implementation pays back across N call sites and M tests.
+
+**Locality** — what maintainers get from depth: change, bugs, knowledge, and verification concentrate in one place rather than spreading across callers. Fix once, fixed everywhere.
+
+## Deep vs shallow
+
+**Deep module** = small interface + lots of implementation:
+
+```
+┌─────────────────────┐
+│   Small Interface   │  ← Few methods, simple params
+├─────────────────────┤
+│                     │
+│  Deep Implementation│  ← Complex logic hidden
+│                     │
+└─────────────────────┘
+```
+
+**Shallow module** = large interface + little implementation (avoid):
+
+```
+┌─────────────────────────────────┐
+│       Large Interface           │  ← Many methods, complex params
+├─────────────────────────────────┤
+│  Thin Implementation            │  ← Just passes through
+└─────────────────────────────────┘
+```
+
+When designing an interface, ask:
+
+- Can I reduce the number of methods?
+- Can I simplify the parameters?
+- Can I hide more complexity inside?
+
+## Principles
+
+- **Depth is a property of the interface, not the implementation.** A deep module can be internally composed of small, mockable, swappable parts — they just aren't part of the interface. A module can have **internal seams** (private to its implementation, used by its own tests) as well as the **external seam** at its interface.
+- **The deletion test.** Imagine deleting the module. If complexity vanishes, it was a pass-through. If complexity reappears across N callers, it was earning its keep.
+- **The interface is the test surface.** Callers and tests cross the same seam. If you want to test *past* the interface, the module is probably the wrong shape.
+- **One adapter means a hypothetical seam. Two adapters means a real one.** Don't introduce a seam unless something actually varies across it.
+
+## Designing for testability
+
+Good interfaces make testing natural:
+
+1. **Accept dependencies, don't create them.**
+
+   ```typescript
+   // Testable
+   function processOrder(order, paymentGateway) {}
+
+   // Hard to test
+   function processOrder(order) {
+     const gateway = new StripeGateway();
+   }
+   ```
+
+2. **Return results, don't produce side effects.**
+
+   ```typescript
+   // Testable
+   function calculateDiscount(cart): Discount {}
+
+   // Hard to test
+   function applyDiscount(cart): void {
+     cart.total -= discount;
+   }
+   ```
+
+3. **Small surface area.** Fewer methods = fewer tests needed. Fewer params = simpler test setup.
+
+## Relationships
+
+- A **Module** has exactly one **Interface** (the surface it presents to callers and tests).
+- **Depth** is a property of a **Module**, measured against its **Interface**.
+- A **Seam** is where a **Module**'s **Interface** lives.
+- An **Adapter** sits at a **Seam** and satisfies the **Interface**.
+- **Depth** produces **Leverage** for callers and **Locality** for maintainers.
+
+## Rejected framings
+
+- **Depth as ratio of implementation-lines to interface-lines** (Ousterhout): rewards padding the implementation. We use depth-as-leverage instead.
+- **"Interface" as the TypeScript `interface` keyword or a class's public methods**: too narrow — interface here includes every fact a caller must know.
+- **"Boundary"**: overloaded with DDD's bounded context. Say **seam** or **interface**.
+
+## Going deeper
+
+- **Deepening a cluster given its dependencies** — see [DEEPENING.md](DEEPENING.md): dependency categories, seam discipline, and replace-don't-layer testing.
+- **Exploring alternative interfaces** — see [DESIGN-IT-TWICE.md](DESIGN-IT-TWICE.md): spin up parallel sub-agents to design the interface several radically different ways, then compare on depth, locality, and seam placement.
@@ -0,0 +1,3 @@
+interface:
+  display_name: "Codebase Design"
+  short_description: "Vocabulary for deep-module design"
@@ -0,0 +1,134 @@
+---
+name: diagnosing-bugs
+description: Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
+---
+
+# Diagnosing Bugs
+
+A discipline for hard bugs. Skip phases only when explicitly justified.
+
+When exploring the codebase, read `CONTEXT.md` (if it exists) to get a clear mental model of the relevant modules, and check ADRs in the area you're touching.
+
+## Phase 1 — Build a feedback loop
+
+**This is the skill.** Everything else is mechanical. If you have a **tight** pass/fail signal for the bug — one that goes red on _this_ bug — you will find the cause; bisection, hypothesis-testing, and instrumentation all just consume it. If you don't have one, no amount of staring at code will save you.
+
+Spend disproportionate effort here. **Be aggressive. Be creative. Refuse to give up.**
+
+### Ways to construct one — try them in roughly this order
+
+1. **Failing test** at whatever seam reaches the bug — unit, integration, e2e.
+2. **Curl / HTTP script** against a running dev server.
+3. **CLI invocation** with a fixture input, diffing stdout against a known-good snapshot.
+4. **Headless browser script** (Playwright / Puppeteer) — drives the UI, asserts on DOM/console/network.
+5. **Replay a captured trace.** Save a real network request / payload / event log to disk; replay it through the code path in isolation.
+6. **Throwaway harness.** Spin up a minimal subset of the system (one service, mocked deps) that exercises the bug code path with a single function call.
+7. **Property / fuzz loop.** If the bug is "sometimes wrong output", run 1000 random inputs and look for the failure mode.
+8. **Bisection harness.** If the bug appeared between two known states (commit, dataset, version), automate "boot at state X, check, repeat" so you can `git bisect run` it.
+9. **Differential loop.** Run the same input through old-version vs new-version (or two configs) and diff outputs.
+10. **HITL bash script.** Last resort. If a human must click, drive _them_ with `scripts/hitl-loop.template.sh` so the loop is still structured. Captured output feeds back to you.
+
+Build the right feedback loop, and the bug is 90% fixed.
+
+### Tighten the loop
+
+Treat the loop as a product. Once you have _a_ loop, **tighten** it:
+
+- Can I make it faster? (Cache setup, skip unrelated init, narrow the test scope.)
+- Can I make the signal sharper? (Assert on the specific symptom, not "didn't crash".)
+- Can I make it more deterministic? (Pin time, seed RNG, isolate filesystem, freeze network.)
+
+A 30-second flaky loop is barely better than no loop; a 2-second deterministic one is tight — a debugging superpower.
+
+### Non-deterministic bugs
+
+The goal is not a clean repro but a **higher reproduction rate**. Loop the trigger 100×, parallelise, add stress, narrow timing windows, inject sleeps. A 50%-flake bug is debuggable; 1% is not — keep raising the rate until it's debuggable.
+
+### When you genuinely cannot build a loop
+
+Stop and say so explicitly. List what you tried. Ask the user for: (a) access to whatever environment reproduces it, (b) a captured artifact (HAR file, log dump, core dump, screen recording with timestamps), or (c) permission to add temporary production instrumentation. Do **not** proceed to hypothesise without a loop.
+
+### Completion criterion — a tight loop that goes red
+
+Phase 1 is done when the loop is **tight** and **red-capable**: you can name **one command** — a script path, a test invocation, a curl — that you have **already run at least once** (paste the invocation and its output), and that is:
+
+- [ ] **Red-capable** — it drives the actual bug code path and asserts the **user's exact symptom**, so it can go red on this bug and green once fixed. Not "runs without erroring" — it must be able to _catch this specific bug_.
+- [ ] **Deterministic** — same verdict every run (flaky bugs: a pinned, high reproduction rate, per above).
+- [ ] **Fast** — seconds, not minutes.
+- [ ] **Agent-runnable** — you can run it unattended; a human in the loop only via `scripts/hitl-loop.template.sh`.
+
+If you catch yourself reading code to build a theory before this command exists, **stop — jumping straight to a hypothesis is the exact failure this skill prevents.** No red-capable command, no Phase 2.
+
+## Phase 2 — Reproduce + minimise
+
+Run the loop. Watch it go red — the bug appears.
+
+Confirm:
+
+- [ ] The loop produces the failure mode the **user** described — not a different failure that happens to be nearby. Wrong bug = wrong fix.
+- [ ] The failure is reproducible across multiple runs (or, for non-deterministic bugs, reproducible at a high enough rate to debug against).
+- [ ] You have captured the exact symptom (error message, wrong output, slow timing) so later phases can verify the fix actually addresses it.
+
+### Minimise
+
+Once it's red, shrink the repro to the **smallest scenario that still goes red**. Cut inputs, callers, config, data, and steps **one at a time**, re-running the loop after each cut — keep only what's load-bearing for the failure.
+
+Why bother: a minimal repro shrinks the hypothesis space in Phase 3 (fewer moving parts left to suspect) and becomes the clean regression test in Phase 5.
+
+Done when **every remaining element is load-bearing** — removing any one of them makes the loop go green.
+
+Do not proceed until you have reproduced **and** minimised.
+
+## Phase 3 — Hypothesise
+
+Generate **3–5 ranked hypotheses** before testing any of them. Single-hypothesis generation anchors on the first plausible idea.
+
+Each hypothesis must be **falsifiable**: state the prediction it makes.
+
+> Format: "If <X> is the cause, then <changing Y> will make the bug disappear / <changing Z> will make it worse."
+
+If you cannot state the prediction, the hypothesis is a vibe — discard or sharpen it.
+
+**Show the ranked list to the user before testing.** They often have domain knowledge that re-ranks instantly ("we just deployed a change to #3"), or know hypotheses they've already ruled out. Cheap checkpoint, big time saver. Don't block on it — proceed with your ranking if the user is AFK.
+
+## Phase 4 — Instrument
+
+Each probe must map to a specific prediction from Phase 3. **Change one variable at a time.**
+
+Tool preference:
+
+1. **Debugger / REPL inspection** if the env supports it. One breakpoint beats ten logs.
+2. **Targeted logs** at the boundaries that distinguish hypotheses.
+3. Never "log everything and grep".
+
+**Tag every debug log** with a unique prefix, e.g. `[DEBUG-a4f2]`. Cleanup at the end becomes a single grep. Untagged logs survive; tagged logs die.
+
+**Perf branch.** For performance regressions, logs are usually wrong. Instead: establish a baseline measurement (timing harness, `performance.now()`, profiler, query plan), then bisect. Measure first, fix second.
+
+## Phase 5 — Fix + regression test
+
+Write the regression test **before the fix** — but only if there is a **correct seam** for it.
+
+A correct seam is one where the test exercises the **real bug pattern** as it occurs at the call site. If the only available seam is too shallow (single-caller test when the bug needs multiple callers, unit test that can't replicate the chain that triggered the bug), a regression test there gives false confidence.
+
+**If no correct seam exists, that itself is the finding.** Note it. The codebase architecture is preventing the bug from being locked down. Flag this for the next phase.
+
+If a correct seam exists:
+
+1. Turn the minimised repro into a failing test at that seam.
+2. Watch it fail.
+3. Apply the fix.
+4. Watch it pass.
+5. Re-run the Phase 1 feedback loop against the original (un-minimised) scenario.
+
+## Phase 6 — Cleanup + post-mortem
+
+Required before declaring done:
+
+- [ ] Original repro no longer reproduces (re-run the Phase 1 loop)
+- [ ] Regression test passes (or absence of seam is documented)
+- [ ] All `[DEBUG-...]` instrumentation removed (`grep` the prefix)
+- [ ] Throwaway prototypes deleted (or moved to a clearly-marked debug location)
+- [ ] The hypothesis that turned out correct is stated in the commit / PR message — so the next debugger learns
+
+**Then ask: what would have prevented this bug?** If the answer involves architectural change (no good test seam, tangled callers, hidden coupling) hand off to the `/improve-codebase-architecture` skill with the specifics. Make the recommendation **after** the fix is in, not before — you have more information now than when you started.
@@ -0,0 +1,3 @@
+interface:
+  display_name: "Diagnosing Bugs"
+  short_description: "Diagnose hard bugs and regressions"
@@ -0,0 +1,41 @@
+#!/usr/bin/env bash
+# Human-in-the-loop reproduction loop.
+# Copy this file, edit the steps below, and run it.
+# The agent runs the script; the user follows prompts in their terminal.
+#
+# Usage:
+#   bash hitl-loop.template.sh
+#
+# Two helpers:
+#   step "<instruction>"          → show instruction, wait for Enter
+#   capture VAR "<question>"      → show question, read response into VAR
+#
+# At the end, captured values are printed as KEY=VALUE for the agent to parse.
+
+set -euo pipefail
+
+step() {
+  printf '\n>>> %s\n' "$1"
+  read -r -p "    [Enter when done] " _
+}
+
+capture() {
+  local var="$1" question="$2" answer
+  printf '\n>>> %s\n' "$question"
+  read -r -p "    > " answer
+  printf -v "$var" '%s' "$answer"
+}
+
+# --- edit below ---------------------------------------------------------
+
+step "Open the app at http://localhost:3000 and sign in."
+
+capture ERRORED "Click the 'Export' button. Did it throw an error? (y/n)"
+
+capture ERROR_MSG "Paste the error message (or 'none'):"
+
+# --- edit above ---------------------------------------------------------
+
+printf '\n--- Captured ---\n'
+printf 'ERRORED=%s\n' "$ERRORED"
+printf 'ERROR_MSG=%s\n' "$ERROR_MSG"
@@ -10,7 +10,7 @@
 ## Language

 **Order**:
-{A concise description of the term}
+{A one or two sentence description of the term}
 _Avoid_: Purchase, transaction

 **Invoice**:
@@ -20,31 +20,14 @@ _Avoid_: Bill, payment request
 **Customer**:
 A person or organization that places orders.
 _Avoid_: Client, buyer, account
-
-## Relationships
-
- An **Order** produces one or more **Invoices**
- An **Invoice** belongs to exactly one **Customer**
-
-## Example dialogue
-
-> **Dev:** "When a **Customer** places an **Order**, do we create the **Invoice** immediately?"
-> **Domain expert:** "No — an **Invoice** is only generated once a **Fulfillment** is confirmed."
-
-## Flagged ambiguities
-
- "account" was used to mean both **Customer** and **User** — resolved: these are distinct concepts.
 ```

 ## Rules

- **Be opinionated.** When multiple words exist for the same concept, pick the best one and list the others as aliases to avoid.
- **Flag conflicts explicitly.** If a term is used ambiguously, call it out in "Flagged ambiguities" with a clear resolution.
- **Keep definitions tight.** One sentence max. Define what it IS, not what it does.
- **Show relationships.** Use bold term names and express cardinality where obvious.
+- **Be opinionated.** When multiple words exist for the same concept, pick the best one and list the others under `_Avoid_`.
+- **Keep definitions tight.** One or two sentences max. Define what it IS, not what it does.
 - **Only include terms specific to this project's context.** General programming concepts (timeouts, error types, utility patterns) don't belong even if the project uses them extensively. Before adding a term, ask: is this a concept unique to this context, or a general programming concept? Only the former belongs.
 - **Group terms under subheadings** when natural clusters emerge. If all terms belong to a single cohesive area, a flat list is fine.
- **Write an example dialogue.** A conversation between a dev and a domain expert that demonstrates how the terms interact naturally and clarifies boundaries between related concepts.

 ## Single vs multi-context repos

@@ -1,20 +1,13 @@
 ---
-name: domain-model
-description: Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
-disable-model-invocation: true
+name: domain-modeling
+description: Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.
 ---

-Interview me relentlessly about every aspect of this plan until we reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one. For each question, provide your recommended answer.
+# Domain Modeling

-Ask the questions one at a time, waiting for feedback on each question before continuing.
+Actively build and sharpen the project's domain model as you design. This is the *active* discipline — challenging terms, inventing edge-case scenarios, and writing the glossary and decisions down the moment they crystallise. (Merely *reading* `CONTEXT.md` for vocabulary is not this skill — that's a one-line habit any skill can do. This skill is for when you're changing the model, not just consuming it.)

-If a question can be answered by exploring the codebase, explore the codebase instead.
-
-## Domain awareness
-
-During codebase exploration, also look for existing documentation:
-
-### File structure
+## File structure

 Most repos have a single context:

@@ -68,7 +61,7 @@ When the user states how something works, check whether the code agrees. If you

 When a term is resolved, update `CONTEXT.md` right there. Don't batch these up — capture them as they happen. Use the format in [CONTEXT-FORMAT.md](./CONTEXT-FORMAT.md).

-Don't couple `CONTEXT.md` to implementation details. Only include terms that are meaningful to domain experts.
+`CONTEXT.md` should be totally devoid of implementation details. Do not treat `CONTEXT.md` as a spec, a scratch pad, or a repository for implementation decisions. It is a glossary and nothing else.

 ### Offer ADRs sparingly

@@ -0,0 +1,3 @@
+interface:
+  display_name: "Domain Modeling"
+  short_description: "Build and sharpen a domain model"
@@ -0,0 +1,7 @@
+---
+name: grill-with-docs
+description: A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
+disable-model-invocation: true
+---
+
+Run a `/grilling` session, using the `/domain-modeling` skill.
@@ -0,0 +1,5 @@
+interface:
+  display_name: "Grill with Docs"
+  short_description: "Grill a design and write its docs"
+policy:
+  allow_implicit_invocation: false
@@ -0,0 +1,15 @@
+---
+name: implement
+description: "Implement a piece of work based on a spec or set of tickets."
+disable-model-invocation: true
+---
+
+Implement the work described by the user in the spec or tickets.
+
+Use /tdd where possible, at pre-agreed seams.
+
+Run typechecking regularly, single test files regularly, and the full test suite once at the end.
+
+Once done, use /code-review to review the work.
+
+Commit your work to the current branch.
@@ -0,0 +1,5 @@
+interface:
+  display_name: "Implement"
+  short_description: "Build work from a spec or tickets"
+policy:
+  allow_implicit_invocation: false
@@ -0,0 +1,123 @@
+# HTML Report Format
+
+The architectural review is rendered as a single self-contained HTML file in the OS temp directory. Tailwind and Mermaid both come from CDNs. Mermaid handles graph-shaped diagrams reliably; hand-built divs and inline SVG handle the more editorial visuals (mass diagrams, cross-sections). Mix the two — don't lean on Mermaid for everything, it'll start to look generic.
+
+## Scaffold
+
+```html
+<!doctype html>
+<html lang="en">
+  <head>
+    <meta charset="utf-8" />
+    <title>Architecture review — {{repo name}}</title>
+    <script src="https://cdn.tailwindcss.com"></script>
+    <script type="module">
+      import mermaid from "https://cdn.jsdelivr.net/npm/mermaid@11/dist/mermaid.esm.min.mjs";
+      mermaid.initialize({ startOnLoad: true, theme: "neutral", securityLevel: "loose" });
+    </script>
+    <style>
+      /* small custom layer for things Tailwind doesn't cover cleanly:
+         dashed seam lines, hand-drawn-feeling arrow heads, etc. */
+      .seam { stroke-dasharray: 4 4; }
+      .leak { stroke: #dc2626; }
+      .deep { background: linear-gradient(135deg, #0f172a, #1e293b); }
+    </style>
+  </head>
+  <body class="bg-stone-50 text-slate-900 font-sans">
+    <main class="max-w-5xl mx-auto px-6 py-12 space-y-12">
+      <header>...</header>
+      <section id="candidates" class="space-y-10">...</section>
+      <section id="top-recommendation">...</section>
+    </main>
+  </body>
+</html>
+```
+
+## Header
+
+Repo name, date, and a compact legend: solid box = module, dashed line = seam, red arrow = leakage, thick dark box = deep module. No introduction paragraph — straight into the candidates.
+
+## Candidate card
+
+The diagrams carry the weight. Prose is sparse, plain, and uses the glossary terms (from the `/codebase-design` skill) without ceremony.
+
+Each candidate is one `<article>`:
+
+- **Title** — short, names the deepening (e.g. "Collapse the Order intake pipeline").
+- **Badge row** — recommendation strength (`Strong` = emerald, `Worth exploring` = amber, `Speculative` = slate), plus a tag for the dependency category (`in-process`, `local-substitutable`, `ports & adapters`, `mock`).
+- **Files** — monospaced list, `font-mono text-sm`.
+- **Before / After diagram** — the centrepiece. Two columns, side by side. See patterns below.
+- **Problem** — one sentence. What hurts.
+- **Solution** — one sentence. What changes.
+- **Wins** — bullets, ≤6 words each. e.g. "Tests hit one interface", "Pricing logic stops leaking", "Delete 4 shallow wrappers".
+- **ADR callout** (if applicable) — one line in an amber-tinted box.
+
+No paragraphs of explanation. If the diagram needs a paragraph to be understood, redraw the diagram.
+
+## Diagram patterns
+
+Pick the pattern that fits the candidate. Mix them. Don't make every diagram look the same — variety is part of the point.
+
+### Mermaid graph (the workhorse for dependencies / call flow)
+
+Use a Mermaid `flowchart` or `graph` when the point is "X calls Y calls Z, and look at the mess." Wrap it in a Tailwind-styled card so it doesn't feel parachuted in. Style with classDef to colour leakage edges red and the deep module dark. Sequence diagrams work well for "before: 6 round-trips; after: 1."
+
+```html
+<div class="rounded-lg border border-slate-200 bg-white p-4">
+  <pre class="mermaid">
+    flowchart LR
+      A[OrderHandler] --> B[OrderValidator]
+      B --> C[OrderRepo]
+      C -.leak.-> D[PricingClient]
+      classDef leak stroke:#dc2626,stroke-width:2px;
+      class C,D leak
+  </pre>
+</div>
+```
+
+### Hand-built boxes-and-arrows (when Mermaid's layout fights you)
+
+Modules as `<div>`s with borders and labels. Arrows as inline SVG `<line>` or `<path>` elements positioned absolutely over a relative container. Reach for this when you want the "after" diagram to feel like one thick-bordered deep module with greyed-out internals — Mermaid won't render that with the right weight.
+
+### Cross-section (good for layered shallowness)
+
+Stack horizontal bands (`h-12 border-l-4`) to show layers a call passes through. Before: 6 thin layers each doing nothing. After: 1 thick band labelled with the consolidated responsibility.
+
+### Mass diagram (good for "interface as wide as implementation")
+
+Two rectangles per module — one for interface surface area, one for implementation. Before: interface rectangle is nearly as tall as the implementation rectangle (shallow). After: interface rectangle is short, implementation rectangle is tall (deep).
+
+### Call-graph collapse
+
+Before: a tree of function calls rendered as nested boxes. After: the same tree collapsed into one box, with the now-internal calls shown faded inside it.
+
+## Style guidance
+
+- Lean editorial, not corporate-dashboard. Generous whitespace. Serif optional for headings (`font-serif` works well with stone/slate).
+- Colour sparingly: one accent (emerald or indigo) plus red for leakage and amber for warnings.
+- Keep diagrams ~320px tall so before/after sits comfortably side by side without scrolling.
+- Use `text-xs uppercase tracking-wider` for module labels inside diagrams — they should read as schematic, not as UI.
+- The only scripts are the Tailwind CDN and the Mermaid ESM import. The report is otherwise static — no app code, no interactivity beyond Mermaid's own rendering.
+
+## Top recommendation section
+
+One larger card. Candidate name, one sentence on why, anchor link to its card. That's it.
+
+## Tone
+
+Plain English, concise — but the architectural nouns and verbs come straight from the `/codebase-design` skill. Concision is not an excuse to drift.
+
+**Use exactly:** module, interface, implementation, depth, deep, shallow, seam, adapter, leverage, locality.
+
+**Never substitute:** component, service, unit (for module) · API, signature (for interface) · boundary (for seam) · layer, wrapper (for module, when you mean module).
+
+**Phrasings that fit the style:**
+
+- "Order intake module is shallow — interface nearly matches the implementation."
+- "Pricing leaks across the seam."
+- "Deepen: one interface, one place to test."
+- "Two adapters justify the seam: HTTP in prod, in-memory in tests."
+
+**Wins bullets** name the gain in glossary terms: *"locality: bugs concentrate in one module"*, *"leverage: one interface, N call sites"*, *"interface shrinks; implementation absorbs the wrappers"*. Don't write *"easier to maintain"* or *"cleaner code"* — those terms aren't in the glossary and don't earn their place.
+
+No hedging, no throat-clearing, no "it's worth noting that…". If a sentence could be a bullet, make it a bullet. If a bullet could be cut, cut it. If a term isn't in the `/codebase-design` glossary, reach for one that is before inventing a new one.
@@ -0,0 +1,71 @@
+---
+name: improve-codebase-architecture
+description: Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
+disable-model-invocation: true
+---
+
+# Improve Codebase Architecture
+
+Surface architectural friction and propose **deepening opportunities** — refactors that turn shallow modules into deep ones. The aim is testability and AI-navigability.
+
+This command is _informed_ by the project's domain model and built on a shared design vocabulary:
+
+- Run the `/codebase-design` skill for the architecture vocabulary (**module**, **interface**, **depth**, **seam**, **adapter**, **leverage**, **locality**) and its principles (the deletion test, "the interface is the test surface", "one adapter = hypothetical seam, two = real"). Use these terms exactly in every suggestion — don't drift into "component," "service," "API," or "boundary."
+- The domain language in `CONTEXT.md` gives names to good seams; ADRs in `docs/adr/` record decisions this command should not re-litigate.
+
+## Process
+
+### 1. Explore
+
+**Scope before you scan — YAGNI.** Deepening a module pays off by making future changes to it easier, so put extra weight on the parts of the codebase that have recently changed. Decide *where* to look before you look:
+
+- If the user named a direction — a module, a subsystem, a pain point — take it, and skip the inference below.
+- Otherwise, walk back a good stretch of the commit history (`git log --oneline`) to find the codebase's hot spots — the files and areas that keep coming up — and let those paths pull your attention first. If the changes are scattered with no clear hot spot, widen the net.
+
+Read the project's domain glossary (`CONTEXT.md`) and any ADRs in the area you're touching first.
+
+Then use the Agent tool with `subagent_type=Explore` to walk the codebase. Don't follow rigid heuristics — explore organically and note where you experience friction:
+
+- Where does understanding one concept require bouncing between many small modules?
+- Where are modules **shallow** — interface nearly as complex as the implementation?
+- Where have pure functions been extracted just for testability, but the real bugs hide in how they're called (no **locality**)?
+- Where do tightly-coupled modules leak across their seams?
+- Which parts of the codebase are untested, or hard to test through their current interface?
+
+Apply the **deletion test** to anything you suspect is shallow: would deleting it concentrate complexity, or just move it? A "yes, concentrates" is the signal you want.
+
+### 2. Present candidates as an HTML report
+
+Write a self-contained HTML file to the OS temp directory so nothing lands in the repo. Resolve the temp dir from `$TMPDIR`, falling back to `/tmp` (or `%TEMP%` on Windows), and write to `<tmpdir>/architecture-review-<timestamp>.html` so each run gets a fresh file. Open it for the user — `xdg-open <path>` on Linux, `open <path>` on macOS, `start <path>` on Windows — and tell them the absolute path.
+
+The report uses **Tailwind via CDN** for layout and styling, and **Mermaid via CDN** for diagrams where a graph/flow/sequence reliably communicates the structure. Mix Mermaid with hand-crafted CSS/SVG visuals — use Mermaid when relationships are graph-shaped (call graphs, dependencies, sequences), and hand-built divs/SVG when you want something more editorial (mass diagrams, cross-sections, collapse animations). Each candidate gets a **before/after visualisation**. Be visual.
+
+For each candidate, render a card with:
+
+- **Files** — which files/modules are involved
+- **Problem** — why the current architecture is causing friction
+- **Solution** — plain English description of what would change
+- **Benefits** — explained in terms of locality and leverage, and how tests would improve
+- **Before / After diagram** — side-by-side, custom-drawn, illustrating the shallowness and the deepening
+- **Recommendation strength** — one of `Strong`, `Worth exploring`, `Speculative`, rendered as a badge
+
+End the report with a **Top recommendation** section: which candidate you'd tackle first and why.
+
+**Use CONTEXT.md vocabulary for the domain, and the `/codebase-design` vocabulary for the architecture.** If `CONTEXT.md` defines "Order," talk about "the Order intake module" — not "the FooBarHandler," and not "the Order service."
+
+**ADR conflicts**: if a candidate contradicts an existing ADR, only surface it when the friction is real enough to warrant revisiting the ADR. Mark it clearly in the card (e.g. a warning callout: _"contradicts ADR-0007 — but worth reopening because…"_). Don't list every theoretical refactor an ADR forbids.
+
+See [HTML-REPORT.md](HTML-REPORT.md) for the full HTML scaffold, diagram patterns, and styling guidance.
+
+Do NOT propose interfaces yet. After the file is written, ask the user: "Which of these would you like to explore?"
+
+### 3. Grilling loop
+
+Once the user picks a candidate, run the `/grilling` skill to walk the decision tree with them — constraints, dependencies, the shape of the deepened module, what sits behind the seam, what tests survive.
+
+Side effects happen inline as decisions crystallize — run the `/domain-modeling` skill to keep the domain model current as you go:
+
+- **Naming a deepened module after a concept not in `CONTEXT.md`?** Add the term to `CONTEXT.md`. Create the file lazily if it doesn't exist.
+- **Sharpening a fuzzy term during the conversation?** Update `CONTEXT.md` right there.
+- **User rejects the candidate with a load-bearing reason?** Offer an ADR, framed as: _"Want me to record this as an ADR so future architecture reviews don't re-suggest it?"_ Only offer when the reason would actually be needed by a future explorer to avoid re-suggesting the same thing — skip ephemeral reasons ("not worth it right now") and self-evident ones.
+- **Want to explore alternative interfaces for the deepened module?** Run the `/codebase-design` skill and use its design-it-twice parallel sub-agent pattern.
@@ -0,0 +1,5 @@
+interface:
+  display_name: "Improve Codebase Architecture"
+  short_description: "Find and grill architecture improvements"
+policy:
+  allow_implicit_invocation: false
@@ -0,0 +1,79 @@
+# Logic Prototype
+
+A tiny interactive terminal app that lets the user drive a state model by hand. Use this when the question is about **business logic, state transitions, or data shape** — the kind of thing that looks reasonable on paper but only feels wrong once you push it through real cases.
+
+## When this is the right shape
+
+- "I'm not sure if this state machine handles the edge case where X then Y."
+- "Does this data model actually let me represent the case where..."
+- "I want to feel out what the API should look like before writing it."
+- Anything where the user wants to **press buttons and watch state change**.
+
+If the question is "what should this look like" — wrong branch. Use [UI.md](UI.md).
+
+## Process
+
+### 1. State the question
+
+Before writing code, write down what state model and what question you're prototyping. One paragraph, in the prototype's README or a comment at the top of the file. A logic prototype that answers the wrong question is pure waste — make the question explicit so it can be checked later, whether the user is watching now or returning to it AFK.
+
+### 2. Pick the language
+
+Use whatever the host project uses. If the project has no obvious runtime (e.g. a docs repo), ask.
+
+Match the project's existing conventions for tooling — don't add a new package manager or runtime just for the prototype.
+
+### 3. Isolate the logic in a portable module
+
+Put the actual logic — the bit that's answering the question — behind a small, pure interface that could be lifted out and dropped into the real codebase later. The TUI around it is throwaway; the logic module shouldn't be.
+
+The right shape depends on the question:
+
+- **A pure reducer** — `(state, action) => state`. Good when actions are discrete events and state is a single value.
+- **A state machine** — explicit states and transitions. Good when "which actions are even legal right now" is part of the question.
+- **A small set of pure functions** over a plain data type. Good when there's no implicit current state — just transformations.
+- **A class or module with a clear method surface** when the logic genuinely owns ongoing internal state.
+
+Pick whichever shape best fits the question being asked, *not* whichever is easiest to wire to a TUI. Keep it pure: no I/O, no terminal code, no `console.log` for control flow. The TUI imports it and calls into it; nothing flows the other direction.
+
+This is what makes the prototype useful past its own lifetime: when the question's been answered, the validated reducer / machine / function set can be lifted into the real module on its own.
+
+### 4. Build the smallest TUI that exposes the state
+
+Build it as a **lightweight TUI** — on every tick, clear the screen (`console.clear()` / `print("\033[2J\033[H")` / equivalent) and re-render the whole frame. The user should always see one stable view, not an ever-growing scrollback.
+
+Each frame has two parts, in this order:
+
+1. **Current state**, pretty-printed and diff-friendly (one field per line, or formatted JSON). Use **bold** for field names or section headers and **dim** for less important context (timestamps, IDs, derived values). Native ANSI escape codes are fine — `\x1b[1m` bold, `\x1b[2m` dim, `\x1b[0m` reset. No need to pull in a styling library unless one is already in the project.
+2. **Keyboard shortcuts**, listed at the bottom: `[a] add user  [d] delete user  [t] tick clock  [q] quit`. Bold the key, dim the description, or vice-versa — whatever reads cleanly.
+
+Behaviour:
+
+1. **Initialise state** — a single in-memory object/struct. Render the first frame on start.
+2. **Read one keystroke (or one line)** at a time, dispatch to a handler that mutates state.
+3. **Re-render** the full frame after every action — don't append, replace.
+4. **Loop until quit.**
+
+The whole frame should fit on one screen.
+
+### 5. Make it runnable in one command
+
+Add a script to the project's existing task runner (`package.json` scripts, `Makefile`, `justfile`, `pyproject.toml`). The user should run `pnpm run <prototype-name>` or equivalent — never need to remember a path.
+
+If the host project has no task runner, just put the command at the top of the prototype's README.
+
+### 6. Hand it over
+
+Give the user the run command. They'll drive it themselves; the interesting moments are when they say "wait, that shouldn't be possible" or "huh, I assumed X would be different" — those are the bugs in the _idea_, which is the whole point. If they want new actions added, add them. Prototypes evolve.
+
+### 7. Capture the answer and the prototype
+
+Once the prototype has answered its question, capture the answer, then capture the prototype the way the [SKILL](SKILL.md) describes. The logic-specific mapping: the validated reducer / machine / function set lifts into the real module (the decision, absorbed); the TUI shell rides along to the throwaway branch that keeps the prototype as a primary source.
+
+## Anti-patterns
+
+- **Don't add tests.** A prototype that needs tests is no longer a prototype.
+- **Don't wire it to the real database.** Use an in-memory store unless the question is specifically about persistence.
+- **Don't generalise.** No "what if we wanted to support X later." The prototype answers one question.
+- **Don't blur the logic and the TUI together.** If the reducer / state machine references `console.log`, prompts, or terminal escape codes, it's no longer portable. Keep the TUI as a thin shell over a pure module.
+- **Don't ship the TUI shell into production.** The shell is optimised for being driven by hand from a terminal. The logic module behind it is the bit worth keeping.
@@ -0,0 +1,26 @@
+---
+name: prototype
+description: Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
+---
+
+# Prototype
+
+A prototype is **throwaway code that answers a question**. The question decides the shape.
+
+## Pick a branch
+
+Identify which question is being answered — from the user's prompt, the surrounding code, or by asking if the user is around:
+
+- **"Does this logic / state model feel right?"** → [LOGIC.md](LOGIC.md). Build a tiny interactive terminal app that pushes the state machine through cases that are hard to reason about on paper.
+- **"What should this look like?"** → [UI.md](UI.md). Generate several radically different UI variations on a single route, switchable via a URL search param and a floating bottom bar.
+
+The two branches produce very different artifacts — getting this wrong wastes the whole prototype. If the question is genuinely ambiguous and the user isn't reachable, default to whichever branch better matches the surrounding code (a backend module → logic; a page or component → UI) and state the assumption at the top of the prototype.
+
+## Rules that apply to both
+
+1. **Throwaway from day one, and clearly marked as such.** Locate the prototype code close to where it will actually be used (next to the module or page it's prototyping for) so context is obvious — but name it so a casual reader can see it's a prototype, not production. For throwaway UI routes, obey whatever routing convention the project already uses; don't invent a new top-level structure.
+2. **One command to run.** Whatever the project's existing task runner supports — `pnpm <name>`, `python <path>`, `bun <path>`, etc. The user must be able to start it without thinking.
+3. **No persistence by default.** State lives in memory. Persistence is the thing the prototype is _checking_, not something it should depend on. If the question explicitly involves a database, hit a scratch DB or a local file with a clear "PROTOTYPE — wipe me" name.
+4. **Skip the polish.** No tests, no error handling beyond what makes the prototype _runnable_, no abstractions. The point is to learn something fast.
+5. **Surface the state.** After every action (logic) or on every variant switch (UI), print or render the full relevant state so the user can see what changed.
+6. **Capture it when done.** Fold any validated decision into the real code, then capture the prototype itself as a **primary source**: commit it to a throwaway branch, out of main, and leave a context pointer to that branch on the implementation issue. Capture the answer too — the verdict and the question it settled — in the issue or a commit. The main branch keeps only the validated decision.
@@ -0,0 +1,112 @@
+# UI Prototype
+
+Generate **several radically different UI variations** on a single route, switchable from a floating bottom bar. The user flips between variants in the browser, picks one (or steals bits from each), then throws the rest away.
+
+If the question is about logic/state rather than what something looks like — wrong branch. Use [LOGIC.md](LOGIC.md).
+
+## When this is the right shape
+
+- "What should this page look like?"
+- "I want to see a few options for this dashboard before committing."
+- "Try a different layout for the settings screen."
+- Any time the user would otherwise spend a day picking between three vague mockups in their head.
+
+## Two sub-shapes — strongly prefer sub-shape A
+
+A UI prototype is much easier to judge when it's **butting up against the rest of the app** — real header, real sidebar, real data, real density. A throwaway route on its own is a vacuum: every variant looks fine in isolation. Default to sub-shape A whenever there's a plausible existing page to host the variants. Only reach for sub-shape B if the prototype genuinely has no nearby home.
+
+### Sub-shape A — adjustment to an existing page (preferred)
+
+The route already exists. Variants are rendered **on the same route**, gated by a `?variant=` URL search param. The existing data fetching, params, and auth all stay — only the rendering swaps. This is the default; pick it unless there's a specific reason not to.
+
+If the prototype is for something that doesn't yet have a page but *would naturally live inside one* (a new section of the dashboard, a new card on the settings screen, a new step in an existing flow) — that's still sub-shape A. Mount the variants inside the host page.
+
+### Sub-shape B — a new page (last resort)
+
+Only use this when the thing being prototyped genuinely has no existing page to live inside — e.g. an entirely new top-level surface, or a flow that can't be embedded anywhere sensible.
+
+Create a **throwaway route** following whatever routing convention the project already uses — don't invent a new top-level structure. Name it so it's obviously a prototype (e.g. include the word `prototype` in the path or filename). Same `?variant=` pattern.
+
+Before committing to sub-shape B, sanity-check: is there really no existing page this could be embedded in? An empty route hides design problems that a populated one would expose.
+
+In both sub-shapes the floating bottom bar is identical.
+
+## Process
+
+### 1. State the question and pick N
+
+Default to **3 variants**. More than 5 stops being radically different and starts being noise — cap there.
+
+Write down the plan in one line, in the prototype's location or a top-of-file comment:
+
+> "Three variants of the settings page, switchable via `?variant=`, on the existing `/settings` route."
+
+This works whether the user is here to push back or not.
+
+### 2. Generate radically different variants
+
+Draft each variant. Hold each one to:
+
+- The page's purpose and the data it has access to.
+- The project's component library / styling system (TailwindCSS, shadcn, MUI, plain CSS, whatever).
+- A clear exported component name, e.g. `VariantA`, `VariantB`, `VariantC`.
+
+Variants must be **structurally different** — different layout, different information hierarchy, different primary affordance, not just different colours. Three slightly-tweaked card grids isn't a UI prototype, it's wallpaper. If two drafts come out too similar, redo one with explicit "do not use a card grid" guidance.
+
+### 3. Wire them together
+
+Create a single switcher component on the route:
+
+```tsx
+// pseudo-code — adapt to the project's framework
+const variant = searchParams.get('variant') ?? 'A';
+return (
+  <>
+    {variant === 'A' && <VariantA {...data} />}
+    {variant === 'B' && <VariantB {...data} />}
+    {variant === 'C' && <VariantC {...data} />}
+    <PrototypeSwitcher variants={['A','B','C']} current={variant} />
+  </>
+);
+```
+
+For sub-shape A (existing page): keep all the existing data fetching above the switcher; only the rendered subtree changes per variant.
+
+For sub-shape B (new page): the throwaway route under `/prototype/<name>` mounts the same switcher.
+
+### 4. Build the floating switcher
+
+A small fixed-position bar at the bottom-centre of the screen with three pieces:
+
+- **Left arrow** — cycles to the previous variant (wraps around).
+- **Variant label** — shows the current variant key and, if the variant exports a name, that name too. e.g. `B — Sidebar layout`.
+- **Right arrow** — cycles forward (wraps around).
+
+Behaviour:
+
+- Clicking an arrow updates the URL search param (use the framework's router — `router.replace` on Next, `navigate` on React Router, etc) so the variant is shareable and reload-stable.
+- Keyboard: `←` and `→` arrow keys also cycle. Don't intercept arrow keys when an `<input>`, `<textarea>`, or `[contenteditable]` is focused.
+- Visually distinct from the page (e.g. high-contrast pill, subtle shadow) so it's obviously not part of the design being evaluated.
+- Hidden in production builds — gate on `process.env.NODE_ENV !== 'production'` or an equivalent check, so a stray prototype merge can't ship the bar to users.
+
+Put the switcher in a single shared component so both sub-shapes can reuse it. Locate it wherever shared UI lives in the project.
+
+### 5. Hand it over
+
+Surface the URL (and the `?variant=` keys). The user will flip through whenever they get to it. The interesting feedback is usually **"I want the header from B with the sidebar from C"** — that's the actual design they want.
+
+### 6. Capture the answer and clean up
+
+Once a variant has won, capture the answer — which variant and why — then capture the prototype the way the [SKILL](SKILL.md) describes. Fold the winner into the real code and move the rest onto the throwaway branch, not into main:
+
+- **Sub-shape A** — fold the winner into the existing page; drop the losing variants and the switcher from main.
+- **Sub-shape B** — promote the winning variant to a real route; drop the throwaway route and the switcher from main.
+
+The full set of variants is the primary source, so it lands on the throwaway branch, not the bin — variant components and the switcher left in the main branch rot fast and confuse the next reader.
+
+## Anti-patterns
+
+- **Variants that differ only in colour or copy.** That's a tweak, not a prototype. Real variants disagree about structure.
+- **Sharing too much code between variants.** A shared `<Header>` is fine; a shared `<Layout>` defeats the point. Each variant should be free to throw out the layout.
+- **Wiring variants to real mutations.** Read-only prototypes are fine. If a variant needs to mutate, point it at a stub — the question is "what should this look like", not "does the backend work".
+- **Promoting the prototype directly to production.** The variant code was written under prototype constraints (no tests, minimal error handling). Rewrite it properly when you fold it in.
@@ -0,0 +1,3 @@
+interface:
+  display_name: "Prototype"
+  short_description: "Prototype to answer a design question"
@@ -0,0 +1,12 @@
+---
+name: research
+description: Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.
+---
+
+Spin up a **background agent** to do the research, so you keep working while it reads.
+
+Its job:
+
+1. Investigate the question against **primary sources** — official docs, source code, specs, first-party APIs — not a secondary write-up of them. Follow every claim back to the source that owns it.
+2. Write the findings to a single Markdown file, citing each claim's source.
+3. Save it where the repo already keeps such notes; match the existing convention, and if there is none, put it somewhere sensible and say where.
@@ -0,0 +1,3 @@
+interface:
+  display_name: "Research"
+  short_description: "Research from high-trust sources"
@@ -0,0 +1,14 @@
+---
+name: resolving-merge-conflicts
+description: "Use when you need to resolve an in-progress git merge/rebase conflict."
+---
+
+1. **See the current state** of the merge/rebase. Check git history, and the conflicting files.
+
+2. **Find the primary sources** for each conflict. Understand deeply why each change was made, and what the original intent was. Read the commit messages, check the PRs, check original issues/tickets.
+
+3. **Resolve each hunk.** Preserve both intents where possible. Where incompatible, pick the one matching the merge's stated goal and note the trade-off. Do **not** invent new behaviour. Always resolve; never `--abort`.
+
+4. Discover the project's **automated checks** and run them — typically typecheck, then tests, then format. Fix anything the merge broke.
+
+5. **Finish the merge/rebase.** Stage everything and commit. If rebasing, continue the rebase process until all commits are rebased.
@@ -0,0 +1,3 @@
+interface:
+  display_name: "Resolving Merge Conflicts"
+  short_description: "Resolve merge and rebase conflicts"
@@ -0,0 +1,116 @@
+---
+name: setup-matt-pocock-skills
+description: Configure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
+disable-model-invocation: true
+---
+
+# Setup Matt Pocock's Skills
+
+Scaffold the per-repo configuration that the engineering skills assume:
+
+- **Issue tracker** — where issues live (GitHub by default; local markdown is also supported out of the box)
+- **Triage labels** — the strings used for the five canonical triage roles
+- **Domain docs** — where `CONTEXT.md` and ADRs live, and the consumer rules for reading them
+
+This is a prompt-driven skill, not a deterministic script. Explore, present what you found, confirm with the user, then write.
+
+## Process
+
+### 1. Explore
+
+Look at the current repo to understand its starting state. Read whatever exists; don't assume:
+
+- `git remote -v` and `.git/config` — is this a GitHub repo? Which one?
+- `AGENTS.md` and `CLAUDE.md` at the repo root — does either exist? Is there already an `## Agent skills` section in either?
+- `CONTEXT.md` and `CONTEXT-MAP.md` at the repo root
+- `docs/adr/` and any `src/*/docs/adr/` directories
+- `docs/agents/` — does this skill's prior output already exist?
+- `.scratch/` — sign that a local-markdown issue tracker convention is already in use
+- Is the `triage` skill installed? (a `triage` skill folder alongside this one, or `triage` in your available skills.) This decides whether Section B runs at all.
+- Monorepo signals — a `pnpm-workspace.yaml`, a `workspaces` field in `package.json`, or a populated `packages/*` with its own `src/`. Present only in a genuinely large multi-package repo; their absence means single-context, which is almost every repo.
+
+### 2. Present findings and ask
+
+Summarise what's present and what's missing. Then take the sections in order — one section, one answer, then the next.
+
+Lead each section with the recommended answer so the user can accept it in a word. Give a one-line explainer only when the choice genuinely branches; skip the section entirely when exploration already settled it (Section B when `triage` isn't installed, Section C when there's no monorepo).
+
+**Section A — Issue tracker.**
+
+> Explainer: The "issue tracker" is where issues live for this repo. Skills like `to-tickets`, `triage`, `to-spec`, and `qa` read from and write to it — they need to know whether to call `gh issue create`, write a markdown file under `.scratch/`, or follow some other workflow you describe. Pick the place you actually track work for this repo.
+
+Default posture: these skills were designed for GitHub. If a `git remote` points at GitHub, propose that. If a `git remote` points at GitLab (`gitlab.com` or a self-hosted host), propose GitLab. Otherwise (or if the user prefers), offer:
+
+- **GitHub** — issues live in the repo's GitHub Issues (uses the `gh` CLI)
+- **GitLab** — issues live in the repo's GitLab Issues (uses the [`glab`](https://gitlab.com/gitlab-org/cli) CLI)
+- **Local markdown** — issues live as files under `.scratch/<feature>/` in this repo (good for solo projects or repos without a remote)
+- **Other** (Jira, Linear, etc.) — ask the user to describe the workflow in one paragraph; the skill will record it as freeform prose
+
+Record the choice in `docs/agents/issue-tracker.md`. The GitHub and GitLab templates carry a "PRs as a request surface" flag, defaulted **off** — leave it off and don't raise it; a user who wants external PRs in the triage queue can flip the flag in the file later.
+
+**Section B — Triage label vocabulary.** Skip this section entirely if the `triage` skill isn't installed (exploration told you) — an uninstalled skill needs no labels.
+
+If it is installed, ask exactly one question:
+
+> Do you want to keep the default triage labels? (recommended: **yes**)
+
+The defaults are the five canonical roles, each label string equal to its name: `needs-triage`, `needs-info`, `ready-for-agent`, `ready-for-human`, `wontfix`. On **yes**, write them as-is. Only if the user says no — usually because their tracker already uses other names (e.g. `bug:triage` for `needs-triage`) — collect the overrides so `triage` applies existing labels instead of creating duplicates.
+
+**Section C — Domain docs.** Default to **single-context** — one `CONTEXT.md` + `docs/adr/` at the repo root. This fits almost every repo; write it without asking.
+
+Offer **multi-context** — a root `CONTEXT-MAP.md` pointing to per-context `CONTEXT.md` files — only when exploration found monorepo signals. Then confirm which layout they want.
+
+### 3. Confirm and edit
+
+Show the user a draft of:
+
+- The `## Agent skills` block to add to whichever of `CLAUDE.md` / `AGENTS.md` is being edited (see step 4 for selection rules)
+- The contents of `docs/agents/issue-tracker.md`, `docs/agents/domain.md`, and `docs/agents/triage-labels.md` (the last only when `triage` is installed)
+
+Let them edit before writing.
+
+### 4. Write
+
+**Pick the file to edit:**
+
+- If `CLAUDE.md` exists, edit it.
+- Else if `AGENTS.md` exists, edit it.
+- If neither exists, ask the user which one to create — don't pick for them.
+
+Never create `AGENTS.md` when `CLAUDE.md` already exists (or vice versa) — always edit the one that's already there.
+
+If an `## Agent skills` block already exists in the chosen file, update its contents in-place rather than appending a duplicate. Don't overwrite user edits to the surrounding sections.
+
+The block:
+
+```markdown
+## Agent skills
+
+### Issue tracker
+
+[one-line summary of where issues are tracked]. See `docs/agents/issue-tracker.md`.
+
+### Triage labels
+
+[one-line summary of the label vocabulary]. See `docs/agents/triage-labels.md`.
+
+### Domain docs
+
+[one-line summary of layout — "single-context" or "multi-context"]. See `docs/agents/domain.md`.
+```
+
+Include the `### Triage labels` sub-block, and write `docs/agents/triage-labels.md`, only when `triage` is installed and Section B ran. When it isn't, both are omitted.
+
+Then write the docs files using the seed templates in this skill folder as a starting point:
+
+- [issue-tracker-github.md](./issue-tracker-github.md) — GitHub issue tracker
+- [issue-tracker-gitlab.md](./issue-tracker-gitlab.md) — GitLab issue tracker
+- [issue-tracker-local.md](./issue-tracker-local.md) — local-markdown issue tracker
+- [triage-labels.md](./triage-labels.md) — label mapping (only if `triage` is installed)
+- [domain.md](./domain.md) — domain doc consumer rules + layout
+
+For "other" issue trackers, write `docs/agents/issue-tracker.md` from scratch using the user's description.
+
+### 5. Done
+
+Tell the user the setup is complete and which engineering skills will now read from these files. Mention they can edit `docs/agents/*.md` directly later — re-running this skill is only necessary if they want to switch issue trackers or restart from scratch.
@@ -0,0 +1,5 @@
+interface:
+  display_name: "Setup Matt Pocock Skills"
+  short_description: "Configure a repo for the skills"
+policy:
+  allow_implicit_invocation: false
--- a/Show More
+++ b/Show More