The reference now covers any document an agent consumes — skills,
AGENTS.md/CLAUDE.md, docs reached by a pointer. GLOSSARY.md merged into
SKILL.md as a dedup (Avoid-lists and the standalone Predictability
definition pruned); skill-only mechanics disclosed to SKILL-MECHANICS.md;
the skill is now model-invoked. Clean rename, no alias.
Spec: mattpocock/personal-wiki#187 · ships via mattpocock/personal-wiki#193
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Reshape the logic branch from a terminal app into a single
self-contained HTML file a non-developer can drive: a labelled
state panel, free-play buttons, and tabbed guided walkthroughs
(scenarios) with the ordered buttons to press underneath each.
The portable pure-logic module still lifts into the real code;
the HTML shell is the throwaway primary source.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Rework grilling from one-question-at-a-time to asking the whole
frontier each round, with background sub-agents for fact-finding so
research never blocks the round. Fold the batch-grill-me experiment
into grilling and delete it. Re-sync the docs page, including how to
opt back into one-at-a-time via global CLAUDE.md.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Adds an `agents/openai.yaml` beside each `SKILL.md` so the skills work in
Codex as well as Claude Code, without generated copies:
- `interface.display_name` + `interface.short_description` for the Codex
skill picker, hand-written for all 39 skills.
- `policy.allow_implicit_invocation: false` on the 22 user-invoked skills —
the Codex analog of `disable-model-invocation: true`, so Codex excludes
them from implicit invocation while explicit `$skill` 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
instructions; note Codex as a `link-skills.sh` install target.
Slimmed-down rework of the approach prototyped in #522: keeps the essential
cross-harness metadata, drops the Ruby validator, the runtime-detector test,
per-skill `default_prompt`s, and the unrelated promotion changes.
Co-authored-by: gabimoncha <gabimoncha@users.noreply.github.com>
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Drop the software-plan scoping from grilling's description and body so the
interview reads as a stress-test of any plan, decision, or idea:
"this plan" → "this", "enact the plan" → "act on it", "codebase" →
"environment". The technique is unchanged, and grill-me is left as-is.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Research stays a real ticket type — it's a shared blocker downstream
decisions hang on, which the frontier's blocking edges exist to render.
What changes is resolution: because research is AFK, charting doesn't
stop and read. After creating the tickets, the charting session fires a
/research subagent for each research ticket to burn it down in parallel,
capturing findings on a throwaway research/<name> branch with a context
pointer.
Charting's "fire the research subagents" step owns how research is
handled; the Ticket Types bullet just names the resolver, and the
one-ticket-per-session rule carries the research exception.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Before scanning, decide where to look. If the user named a direction, take
it; otherwise read 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 — leverage only pays off where you keep editing.
Syncs the docs page and adds a changeset.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
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.
Introduce "decision ticket" as a light leading word: the skill
description and its opening line name it (and say what makes it one),
and the ask-matt / engineering README blurbs and the docs page match,
while "ticket" stays the everyday word once the term is established.
Record "Decision ticket" in CONTEXT.md so the "avoid: ticket" domain
rule no longer contradicts wayfinder's deliberate use of the word.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Wayfinder is the heaviest, most cognitively demanding flow, and the
wiki shows people misusing it two ways: over-reaching for it on
well-scoped work (it's slower and denser than a single grill), and
losing the way at the handoff after the map (looping straight into
/implement and skipping /to-spec). Sharpen the router's wayfinder
on-ramp to steer both.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add a Claude Code plugin marketplace so the promoted skills can be
installed as a managed, read-only bundle (subscribe rather than fork),
alongside the existing skills.sh installer.
- Enrich .claude-plugin/plugin.json with marketplace metadata (version,
description, author, license, keywords); keep the curated promoted-only
skills array.
- Add .claude-plugin/marketplace.json making the repo its own
single-plugin marketplace (mattpocock-skills@mattpocock).
- README: document /plugin install alongside skills.sh, and the
subscribe-vs-fork tradeoff.
- CLAUDE.md: extend the promoted-set invariant to cover marketplace.json
and plugin.json/package.json version sync.
- ADR 0002: record why Claude ships now and a native Codex plugin is
deferred (Codex skills field is single-path + drops symlinks, which
can't express a curated subset of a bucketed repo without a restructure).
Verified: 'claude plugin validate . --strict' passes, and marketplace
add -> install resolves all 21 promoted skills at v1.2.0.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Reframe the artifact handling as capturing the prototype somewhere out
of main — a throwaway branch — with a context pointer to it left on the
implementation issue, instead of "disposing" of it. The main branch
still keeps only the validated decision.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Rework /setup-matt-pocock-skills to ask fewer, friendlier questions and
align the local-markdown issue tracker with the current spec.
- Triage labels: asked 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: no longer a setup question. The
GitHub/GitLab templates still carry the flag, defaulted off; 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: one file per ticket under
.scratch/<feature>/issues/<NN>-<slug>.md, never a single combined
tickets.md. /to-tickets, ask-matt, and the local template now agree, and
the spec file is spec.md (not PRD.md) to match /to-spec.
- Re-sync docs pages for setup-matt-pocock-skills and to-tickets; changeset.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Drop the secondary-source label — the actionable distinction is just
that the prototype is a primary source to retain on a throwaway branch.
Collapse the re-descriptions in LOGIC/UI so they point to SKILL for the
disposal concept and add only branch-specific nuance.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Retain the prototype as a primary source on a throwaway branch linked
from the relevant issue, rather than deleting it, while the distilled
answer remains the secondary source. Keeps prototype scaffolding out of
the main branch without destroying the runnable evidence.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The grill-led idea→ship chain stays the documented front door; wayfinder
is a situational on-ramp (greenfield / huge feature build), reserving
"new default spine" for a potential v2.
- ask-matt router: name wayfinder's concrete triggers
- grill-me / grill-with-docs: signpost up to wayfinder as the
too-big-for-one-session on-ramp
Resolves the main-flow decision on the Skills v1.1 wayfinder map (#120).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Graduate `wayfinder` out of in-progress into the engineering bucket
(plugin.json, top-level + Engineering READMEs under User-invoked, docs
page, ask-matt on-ramp, disable-model-invocation).
Consolidate the 22 pending changesets into 10 coherent v1.1 entries:
one `wayfinder` (rename from decision-mapping + full reframe +
graduation), one `grilling`, one `code-review`, one `tdd`; fold the
superseded to-issues changeset into unify-to-tickets and drop its stray
`</content>` tag. Highest bump is minor → 1.0.1 becomes 1.1.0.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Executes the `unify-to-tickets` decision (personal-wiki #23), reworking
this PR from "add /to-plan" into the full planning-skills unification.
- Rename /to-prd → /to-spec. "spec" is now the single through-line term
(the skill still opens with "you may know this document as a PRD" for
discoverability).
- Merge /to-plan + /to-issues into one /to-tickets skill; delete
/to-issues. /to-tickets emits a set of tickets, each declaring its
blocking edges — one medium-agnostic artifact that reads as a
sequential plan (local `tickets.md`, edges as text) or a parallelizable
DAG (real tracker, native blocking links). The edges live in the ticket
either way; the medium only decides whether anything acts on them in
parallel.
- ask-matt now routes idea → /to-spec → /to-tickets → /implement.
- Sweep every cross-reference (docs pages, chain diagrams, CONTEXT.md,
ADRs, .agents, setup templates) to the new names and vocabulary.
- Rewrite the changeset to describe the unification.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add a user-invoked `to-plan` skill — the sequential, HITL sibling of
`to-issues`. Both slice work into tracer-bullet vertical slices, but
`to-plan` produces one ordered sequence you drive by hand, one phase per
fresh context, rather than parallel independently-grabbable issues.
It publishes to the tracker `/setup-matt-pocock-skills` configured, shaped
to it: a single sequential `plan.md` for a local tracker, or a parent
issue with ordered sub-issues (native sub-issues where supported) for a
real one.
Registers the skill everywhere CLAUDE.md requires (plugin.json, top-level
and bucket READMEs, docs page), updates the `ask-matt` router's main-flow
fork to offer both to-issues and to-plan, and adds a changeset.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Wayfinder pinned the literal docs/agents/issue-tracker.md, breaking the
indirection to-issues/to-prd/triage rely on: they resolve the tracker
through the ### Issue tracker block setup writes into CLAUDE.md / AGENTS.md.
In repos that keep agent docs elsewhere, wayfinder silently fell back to
local-markdown. It now follows the same pointer and reads the doc's
"Wayfinding operations" section by name.
Closes#471
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Revert the description change and keep the wide-refactor material in
one place. Reshape the skill into a lean Process (steps) and a
Reference section holding the vertical-slice rules, the wide-refactor
expand–contract rules, and the issue body template as co-located
blocks the steps point to.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add a wide-refactor exception to the tracer-bullet rule: a single
mechanical change whose blast radius fans across the codebase can't
land as one green vertical slice. Seed "wide refactor" / "blast radius"
across the description, the explore step (detection), and the drafting
step (strategy), and give the expand–contract sequence in prose.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Negative Space read as clever but not actionable — "notice your
silences" is fuzzy legwork the agent can't reliably act on. Negation
stays: a checkable authoring failure with a positive-instruction cure.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Not "implement directly" — the point is the journey fits one session and
doesn't justify a map. Stop and ask the user how to proceed.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Bring back the "skip the map when there's no fog" branch that was
collateral-deleted with the Handoff section. Co-located in Chart the
map step 2, where the fog/no-fog outcome is determined: if breadth-first
grilling surfaces no fog, offer to skip the map and implement directly.
The offer (ask, don't auto-skip) is preserved from the original.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Two minimal edits to the to-issues skill:
- The "What to build" template now points explicitly at the `/prototype`
skill's code as the source of an inlined decision snippet, rather than
gesturing at "a prototype".
- Publishing now prefers the tracker's native sub-issues (parent → slice)
and native blocking edges (Blocked by) where supported — mechanics
already documented in the issue-tracker doc — keeping the `## Parent`
and `## Blocked by` body sections as the fallback.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
QA follow-up: the Fog of war section was teaching both concepts, which
muddies the leading word — fog should point only *toward* the
destination. Now Fog of war teaches only the not-yet-specified bucket
(with the two-way fog-or-ticket sharpness test restored), and a new
Out of scope section owns the scope axis: beyond the destination,
closed not graduating, kept out of Decisions so far.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Following review: the map-body headings a cold reader sees should be
self-evident without having read the skill, so drop the metaphor from
the headings — `## Not yet specified` (in-scope, unripe) and
`## Out of scope` (beyond the destination). Keep **fog of war** as the
leading word: it still titles the explanatory section and drives the
"clears the fog" / "graduate the fog" behavior in the prose.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Fog is the undiscovered frontier *toward* the destination — in scope,
just not yet sharp — so it graduates into tickets as the frontier
advances. Work ruled out of *this* effort's scope was being parked in
Fog too, where it read as takeable frontier (an unblocked, unclaimed
ticket is indistinguishable from a live one).
Add a dedicated `## Deferred` section for beyond-the-destination work:
it never graduates (the frontier stops at the destination) and returns
only as a fresh effort if the destination is redrawn. The "Fog or
ticket?" test becomes "Fog, ticket, or deferred?", gated on scope as
well as sharpness, and both charting and working-the-map now defer a
mis-scoped ticket (close it, one line in Deferred) rather than leaving
it on the frontier or logging it in Decisions so far.
Builds on #455 (destination as the leading word / destination fixes
scope).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Wayfinding finds the way to a destination rather than building it. The
destination varies per effort and is named first, since it shapes every
ticket. Adds a Destination map-body field, makes it triage step 1, and
unifies the stray "goal" mentions onto "destination".
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
A session now claims a ticket by assigning it to the dev driving the
map, rather than setting a `wayfinder:claimed` label. The assignee is
the claim; an open, unassigned ticket is unclaimed. Reads more naturally
in the tracker's own UI and frees the label vocabulary to
`wayfinder:<type>` alone.
Updates the GitHub and GitLab tracker-operations docs to the assignee
mechanism (`--add-assignee @me` / `--assignee @me`). The local-markdown
tracker keeps its `Status: claimed` line — a file store has no assignee.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Concision pass on the blocking rule (fold the "wherever the tracker has
one" clause into the fallback sentence; drop restatements). Bring the
GitHub and GitLab issue-tracker templates up to the same standard: the
GitHub template now carries the native issue-dependencies recipe and
frontier query; the GitLab template names the native /blocked_by link
(Premium/Ultimate) with the body-convention fallback.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The blocking rule now leads with the tracker's native dependency
relationship and encodes the rationale: native rendering makes the
frontier visible in the tracker's own UI, so the human sees what's
takeable without opening the map. Notes the body-convention fallback
for trackers that lack native blocking (GitHub has it; GitLab only on
paid tiers).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The description does the skill's invocation work, so lead with the trigger
that actually reaches for Wayfinder — a huge chunk of work, more than one
agent session can hold — instead of the softer "chart a route through a
foggy problem". Skill body and fog-of-war mechanic unchanged.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
State the no-duplication contract up front with a leading word: the map
indexes decisions and points at the tickets that hold them; a decision
lives in exactly one place — its ticket — so the map only gists and links.
Also close a fog-vs-ticket duplication: graduating fog into a ticket now
clears the graduated patch from the Fog.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Move the map off a local Markdown file and onto the repo's configured
issue tracker. The map is a single wayfinder:map issue whose tickets are
its child issues — one shared URL the team can watch and comment on.
Blocking, claiming (wayfinder:claimed), and the frontier query use native
tracker semantics; a session loads the map at low resolution (Notes +
per-closed-ticket context pointers + Fog prose) and zooms into tickets on
demand. Per-tracker mechanics live behind the docs/agents/issue-tracker.md
pointer, so setup-matt-pocock-skills seeds a "Wayfinding operations"
section for GitHub, GitLab, and local-markdown; absent that doc, Wayfinder
defaults to local-markdown.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Remove the "You are the Wayfinder" second-person persona from the intro,
description, and README so the agent doesn't adopt a persona. Keep the
leading-word frame (chart / fog / frontier / map); wayfinder stays only as
the skill/invocation name.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
