Skip to content

v1.1: planning-skills unification (breaking) + wayfinder graduation#464

Merged
mattpocock merged 8 commits into
mainfrom
release/v1.1
Jul 8, 2026
Merged

v1.1: planning-skills unification (breaking) + wayfinder graduation#464
mattpocock merged 8 commits into
mainfrom
release/v1.1

Conversation

@mattpocock

Copy link
Copy Markdown
Owner

This is the v1.1 release branch — a breaking change (the planning-skills rename/merge), bundled with the skill work accumulated since 1.0.1 and the graduation of wayfinder. Highest changeset bump is minor, so 1.0.1 → 1.1.0.

Not a release commit: no changeset version, no package.json bump, no CHANGELOG, no tag. The changesets are left pending; the version is cut separately at release time.

Headline: planning-skills unification (breaking)

  • /to-prd/to-spec. Renamed dir, docs page, plugin.json, both READMEs, and body. "spec" is now the single through-line term; the skill still opens with "you may know this document as a PRD" for discoverability.
  • /to-plan + /to-issues/to-tickets; /to-issues deleted. /to-tickets emits a set of tickets, each declaring its blocking edges — one medium-agnostic artifact that reads two ways: a local file (tickets.md, edges as text, worked top-to-bottom) or a real tracker (edges as native blocking links, so any unblocked ticket is on the frontier and several agents can run at once). Publishing prefers native sub-issues / blocking edges where the tracker supports them.
  • ask-matt now routes idea → /to-spec → /to-tickets → /implement.
  • Full cross-reference sweep to the new names + vocabulary; no stale to-prd/to-plan/to-issues slugs remain.

Graduate wayfinder → engineering

wayfinder (the "plan a huge chunk of work, more than one session can hold" skill) moves out of in-progress/ into engineering/:

  • Added to plugin.json, top-level + Engineering READMEs (User-invoked), and a docs page at docs/engineering/wayfinder.md; removed from the in-progress README; disable-model-invocation: true added.
  • Routed in ask-matt as a big-idea on-ramp that merges onto the main flow at /to-spec.

Changeset unification

Consolidated the 22 pending changesets into 10 coherent v1.1 entries — one each for the wayfinder story (decision-mapping → wayfinder rename + full reframe + graduation), grilling, code-review, and tdd — folded the superseded to-issues changeset into unify-to-tickets, and dropped a stray </content> tag.

Also included (accumulated since 1.0.1)

ask-matt full skill map · code-review promotion + Fowler smell baseline · grilling confirmation gate + facts/decisions split · prototype made model-invoked · new research skill · tdd reference-only reshape + tautological-test anti-pattern · triage external-PR support · writing-great-skills negation / negative-space failure modes.


Supersedes #410, which GitHub auto-closed when its head branch to-plan-skill was renamed to release/v1.1. Same work and history — the branch just carries a new name for the v1.1 release.

@changeset-bot

changeset-bot Bot commented Jul 6, 2026

Copy link
Copy Markdown

🦋 Changeset detected

Latest commit: d6e21b6

The changes in this PR will be included in the next version bump.

This PR includes changesets to release 1 package
Name Type
mattpocock-skills Minor

Not sure what this means? Click here to learn what changesets are.

Click here if you're a maintainer who wants to add another changeset to this PR

@mattpocock

Copy link
Copy Markdown
Owner Author

Landed the main-flow decision for the AI Hero docs (personal-wiki wayfinder map, ticket #120): the grill-led idea→ship chain stays the front door; wayfinder is a situational on-ramp (greenfield / huge feature build), not the new default spine — that's a v2-sized move.

Changes in 06c7546:

  • ask-matt router: name wayfinder's concrete triggers.
  • grill-me / grill-with-docs reader posts: signpost up to wayfinder.
  • README + main-flow diagram: intentionally left as-is (grill stays the spine).

mattpocock and others added 8 commits July 8, 2026 14:11
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>
Fold the redundant 'thin vertical slice cuts through all layers, NOT
horizontal' intro sentence into vertical-slice-rules bullet 1 (it was
duplicating the bullet), and cut to-plan's 'no parallelism / top-to-bottom'
restatement — 'sequential' is already anchored as the leading word. Keeps
the shared core identical across the two sibling skills.

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>
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
It documented what the skill does rather than steering the agent — the
publish mechanics it described are already Step 5's instructions, and the
conceptual framing already lives in ask-matt and the docs page.

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>
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>
implement is the central Main Flow step but was missing from the
public Reference list. Add it after to-tickets.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@mattpocock mattpocock merged commit cc1e248 into main Jul 8, 2026
vdsmon added a commit to vdsmon/skills that referenced this pull request Jul 9, 2026
#15)

Close the gaps between our steals and upstream v1.1.0:

- grilling: split facts from decisions (facts get looked up in the codebase, decisions go to the human and wait for an answer), add the do-not-enact-until-confirmed stop-gate, and recruit the 'grill' leading word in the description. Upstream PR mattpocock/skills#464.
- skill-smith: add the Negation failure mode (steering by prohibition drags the forbidden behaviour into context; prompt the positive instead) to the design glossary and the principles failure-mode list. Upstream PR mattpocock/skills#463. Upstream also drafted a 'Negative Space' twin entry but cut it before tagging v1.1.0 as not actionable; we skip it for the same reason.

Descriptions updated in plugin.json + marketplace.json; versions bumped (grilling 0.2.0, skill-smith 0.3.3); Codex artifacts regenerated via sync-codex.sh.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant