refactor(plugin): self-maintaining directory form for plugin skills

Replace the hand-listed 22 skill directories in
.claude-plugin/plugin.json with the two promoted buckets
(./skills/engineering, ./skills/productivity). Claude Code
discovers skills one level down, so newly promoted skills are
picked up automatically and the manifest can't drift out of sync
with the tree. Resolves the same enumeration gap that once left
resolving-merge-conflicts off the list.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

.changeset/ask-matt-wayfinder-guidance.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.

.changeset/codex-skill-metadata.md

@@ -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.

.changeset/friendlier-setup-and-local-tickets.md

@@ -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.

.changeset/grilling-general-use.md

@@ -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.

.changeset/plugin-skills-directory-form.md

@@ -0,0 +1,5 @@
+---
+"mattpocock-skills": patch
+---
+
+Switch the plugin manifest's `skills` field to self-maintaining directory form. Instead of hand-listing all 22 skill directories, `.claude-plugin/plugin.json` now points at the two promoted buckets (`./skills/engineering`, `./skills/productivity`) and lets Claude Code discover the skills one level down. New promoted skills are picked up automatically, and the manifest can no longer drift out of sync with the tree.

.changeset/prototype-primary-source.md

@@ -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.

.changeset/ship-as-claude-plugin.md

@@ -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.

.changeset/wayfinder-decision-tickets.md

@@ -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.

.changeset/wayfinder-research-subagents.md

@@ -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*.

.changeset/yagni-scope-improve-architecture.md

@@ -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.

.claude-plugin/plugin.json

@@ -19,27 +19,7 @@
     "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"
+    "./skills/engineering",
+    "./skills/productivity"
   ]
 }

CHANGELOG.md

@@ -1,57 +1,5 @@
 # mattpocock-skills
 
-## 1.2.0
-
-### Minor Changes
-
-- [#551](https://github.com/mattpocock/skills/pull/551) [`697d4ce`](https://github.com/mattpocock/skills/commit/697d4ce9742da558fd1ba6697c8e9775e2e302dd) Thanks [@mattpocock](https://github.com/mattpocock)! - 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.
-
-- [#488](https://github.com/mattpocock/skills/pull/488) [`cdec9f6`](https://github.com/mattpocock/skills/commit/cdec9f6eb24dbfe606e3ad9b3eb457ba09210b85) Thanks [@mattpocock](https://github.com/mattpocock)! - 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.
-
-- [#536](https://github.com/mattpocock/skills/pull/536) [`42a5b70`](https://github.com/mattpocock/skills/commit/42a5b70fcacc7baff1977b13f3919fb2f63af14e) Thanks [@mattpocock](https://github.com/mattpocock)! - 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.
-
-- [#538](https://github.com/mattpocock/skills/pull/538) [`2602257`](https://github.com/mattpocock/skills/commit/260225724133c4a204489599f04642aa089259a0) Thanks [@mattpocock](https://github.com/mattpocock)! - 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_.
-
-- [#533](https://github.com/mattpocock/skills/pull/533) [`45afd80`](https://github.com/mattpocock/skills/commit/45afd8074a8b7de5fe073845d080fa9dd6c429fa) Thanks [@mattpocock](https://github.com/mattpocock)! - 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.
-
-### Patch Changes
-
-- [#535](https://github.com/mattpocock/skills/pull/535) [`e74fee8`](https://github.com/mattpocock/skills/commit/e74fee89feb6025a6a74f6282feb7d33b1b6e578) Thanks [@mattpocock](https://github.com/mattpocock)! - 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.
-
-- [#502](https://github.com/mattpocock/skills/pull/502) [`44eed54`](https://github.com/mattpocock/skills/commit/44eed545186ffd0263e8004867750b80cfddd215) Thanks [@mattpocock](https://github.com/mattpocock)! - 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.
-
-- [#532](https://github.com/mattpocock/skills/pull/532) [`170ad48`](https://github.com/mattpocock/skills/commit/170ad48655825783d0193e850e31a9aac957bb95) Thanks [@mattpocock](https://github.com/mattpocock)! - 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.
-
-- [#534](https://github.com/mattpocock/skills/pull/534) [`7d694b7`](https://github.com/mattpocock/skills/commit/7d694b7ae981ca221a8f759b15273fe7b5dc393e) Thanks [@mattpocock](https://github.com/mattpocock)! - 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.
-
 ## 1.1.0
 
 ### Minor Changes

package.json

@@ -1,6 +1,6 @@
 {
   "name": "mattpocock-skills",
-  "version": "1.2.0",
+  "version": "1.1.0",
   "private": true,
   "description": "Matt Pocock's agent skills for real engineering",
   "repository": {

skills/in-progress/README.md

@@ -9,5 +9,3 @@ Skills that are still being developed. They're not ready to ship — expect roug
 - **[writing-shape](./writing-shape/SKILL.md)** — Take a markdown file of raw material and shape it into an article paragraph by paragraph, arguing format choices at each step.
 - **[claude-handoff](./claude-handoff/SKILL.md)** — Hand the current conversation off to a fresh background agent that picks up the work immediately, seeded with a handoff summary via `claude --bg`. User-invoked.
 - **[setup-ts-deep-modules](./setup-ts-deep-modules/SKILL.md)** — Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files, tests exercising it through those. User-invoked.
-- **[to-questionnaire](./to-questionnaire/SKILL.md)** — Turn a decision you can't fully answer into a Markdown questionnaire for someone else to fill in async, or over a meeting. It grills you about the send (who it's for, what you need back), not the subject. User-invoked.
-- **[batch-grill-me](./batch-grill-me/SKILL.md)** — Relentless interview that walks the design tree in rounds instead of one question at a time — each round asks the whole frontier of decisions whose prerequisites are already settled, then recomputes from your answers. User-invoked.

skills/in-progress/batch-grill-me/SKILL.md

@@ -1,15 +0,0 @@
----
-name: batch-grill-me
-description: A relentless interview that asks every frontier question at once, round by round.
-disable-model-invocation: true
----
-
-Interview the user relentlessly until you reach a shared understanding. Map this as a **design tree**: every decision branches into the decisions that hang off it.
-
-Work the tree in **rounds**. The **frontier** is every decision whose prerequisites are already settled — the questions you can ask *now* without guessing at answers you haven't heard yet. Ask the whole frontier in one round: number each question and give your recommended answer. Then wait for the user's answers before the next round.
-
-Each round the user answers reshapes the tree — settled decisions push the frontier outward and unblock questions that depended on them. Recompute the frontier and ask the next round. A question whose answer depends on another question still open in this round belongs to a *later* round, not this one.
-
-Finding *facts* is your job, never the user's. When a frontier question needs a fact from the environment (filesystem, tools, etc.), dispatch a sub-agent to find it — don't ask the user for anything you could look up yourself. Don't block on it: a running exploration is an unsettled prerequisite, so only the questions downstream of it wait for the sub-agent to report — ask the rest of the frontier now. The *decisions* are the user's — put each to them and wait.
-
-The session is done when the frontier is empty: every branch of the design tree visited, nothing left silently assumed. Do not act on it until the user confirms you have reached a shared understanding.

skills/in-progress/batch-grill-me/agents/openai.yaml

@@ -1,5 +0,0 @@
-interface:
-  display_name: "Batch Grill Me"
-  short_description: "Sharpen a plan a round of questions at a time"
-policy:
-  allow_implicit_invocation: false

skills/in-progress/to-questionnaire/SKILL.md

@@ -1,53 +0,0 @@
----
-name: to-questionnaire
-description: Turn a decision you can't fully answer into a questionnaire for someone else to fill in.
-disable-model-invocation: true
----
-
-Turn something the user can't answer alone into a **questionnaire** — a Markdown document they hand to one person to fill in async, or fill out together over a meeting. The recipient holds knowledge the user lacks; the questionnaire pulls it out of them.
-
-**Grill the send, not the subject.** Interview the user only about the _send_, which they can always answer: who it goes to, and what they need back. The questions in the document then target the **gap** between what the recipient knows and what the user needs.
-
-1. **Who is it going to?** Ask, in one exchange, the recipient's role, expertise, and relationship to the user. This fixes the questionnaire's tone and how much context it must carry. Done when you know who the recipient is and what they know that the user doesn't.
-
-2. **What do you need back?** Ask, in one exchange, the specific decisions or facts the user can't resolve alone and needs from this person. Done when you have a concrete list of what the user must walk away able to do or decide.
-
-3. **Write the questionnaire.** Draft questions aimed at the gap from steps 1–2, following the Document structure below. Write it to `to-questionnaire-<slug>.md` in the current directory (slug from the topic) and report the path. Done when the file exists and every item the user named in step 2 is covered by a question.
-
-## Document structure
-
-Frame the document as a **discovery questionnaire**: the user lacks context, the recipient holds it. Order questions most-important-first — async means you may only get one pass — and group them under `##` headings by theme once there are more than a handful. Write it using the template below.
-
-<questionnaire-template>
-
-# <Questionnaire title>
-
-**Purpose:** why this questionnaire exists and the decision riding on it.
-
-**From:** <the user> — **To:** <the recipient> — **How your answers will be used:** <where they go>
-
-## Context
-
-One paragraph orienting a recipient who wasn't in the user's head. Enough to answer well, not a page.
-
-## How to answer
-
-Deadline and rough effort. Partial answers and "I don't know" are useful — flag anything you're unsure of rather than skipping it.
-
-## <Theme heading>
-
-One `##` section per theme. Under each, its questions, most-important-first. Every question is one idea — never compound — with an answer stub directly beneath, and a one-line _why this matters_ only where the question could be misread or invite a throwaway answer.
-
-<question-example>
-### What load is the system expected to handle at launch?
-
-_Why this matters: it decides whether we provision for burst traffic now or defer it._
-
->
-</question-example>
-
-## Anything else?
-
-A closing catch-all: anything we didn't ask that we should know?
-
-</questionnaire-template>

skills/in-progress/to-questionnaire/agents/openai.yaml

@@ -1,5 +0,0 @@
-interface:
-  display_name: "To Questionnaire"
-  short_description: "Front-load questions into a doc for someone to answer"
-policy:
-  allow_implicit_invocation: false