feat(plugins): sync mattpocock/skills v1.2 learnings across five lanes - #2082
Merged
Conversation
Lane 1 of the pocock-skills-v12-sync effort (Brief in docs/topics/pocock-skills-v12-sync/PLAN.md): - Add docs/upstream/mattpocock-skills.md — the single source of truth for all material derived from mattpocock/skills: per-skill attribution table (including the previously unrecorded work-items triage/decompose phrasing influence), an observable recheck trigger, the last-audited upstream ref (v1.2.3 @ 84fdeff), and harness findings (upstream #693, the Codex sidecar hidden-skill gotcha). - Promote the verified 35-skill upstream<->ours map and the v1.2 research summary into docs/topics/pocock-skills-v12-sync/. - Strip upstream-provenance bookkeeping from planning questionnaire and wayfind SKILL.md bodies (agent-facing noise; the questionnaire line had also gone stale — upstream to-questionnaire graduated in v1.2.0). The SSOT and plugin CHANGELOG carry credit now. Planning plugin 0.28.2. - Annotate the ai-adoption-ladder sandcastle research doc with a v1.2 staleness note (writing-great-skills -> writing-for-agents rename, six skill removals, current star count). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Close Lane 2 of the pocock-skills-v12-sync plan: each of M6 M7 M8 M9 M11 M12 adopted, rejected, or tracked, driven by six fresh-context vetting agents per the lane interview's mandate. Outcomes recorded in docs/upstream/mattpocock-skills.md; per-plugin CHANGELOGs carry detail. - planning 0.29.0: interview gains opt-in emoji anchors (use_emoji_question_markers userConfig, default off; fresh-docs verified against the current plugins-reference userConfig schema); wayfind gains the parallel research burn-down exception and the no-fog chart bail-out. Rejected: one-question-at-a-time opt-out (consumer CLAUDE.md is the native seam), "decision ticket" term (parity as "decision item"), research/<name> branch (two-lane branch-naming prohibition). - architecture 0.4.3: improve's deepening Phase 1 opens with the YAGNI scoping filter (named direction, else commit-history hot spots); precomputed recent commits widened 10 -> 20. - debugging 0.5.0: debug gains a standing secret-redaction guard; the no-loop escape hatch asks for a redacted artifact. - testing 0.4.0: diagnose gains a Redact section, tagged debug logs ([DEBUG-a4f2]) in investigation, and a remove-tagged-logs step at the loop's green gate. - session-flow 0.18.1: the continuation router's continue question gains the zone-gated primary-source criterion; the rest of upstream's phase-boundaries tree audited at parity or rejected (~150k smart-zone figure is folklore; context-guard bands unchanged). - M6 questionnaire re-audit closed with no delta (upstream graduation was a 100%-similarity rename; ours is a superset). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
…ne 3) Lane 3 of the pocock-skills-v12-sync plan: Q9 resolved by the lane interview (rounds 4-6) with agent-gathered evidence and a naming tournament; the user locked PORT. - New skill `discipline:wait-what` — one-shot, user-invoked-only communication repair (disable-model-invocation: true is load-bearing: only the human can detect that a message did not land). Body stays deliberately small: re-pitch with the missing context, ASD-STE100 Simplified Technical English (inline five-word gloss), and the project's ubiquitous language read from the nearest glossary per the consumer's own convention, degrading silently when none exists. - Declared as a non-corrector species beside sweep-all; no discipline-batch tier, so sweeps never fire it. discipline 0.10.1 -> 0.11.0 + CHANGELOG; README species table + skill section. - Name kept upstream: sixth entry on the PLUGIN-PHILOSOPHY naming exception list (utterance-is-mechanism + upstream muscle-memory parity; tournament record in PLAN.md Lane 3). - SSOT row in docs/upstream/mattpocock-skills.md carries provenance and the X-thread evidence that the same instruction failed as passive CLAUDE.md and as an output style (on-demand is the working shape); map row 24 updated with the corrected adjacency (explain/clarify third cell). - Fresh docs fetched for the skills frontmatter surface; skill-quality gate PASS; markdownlint 0 issues; portability check clean. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
…ne 4)
Lane 4 of the pocock-skills-v12-sync plan: Q10 resolved by the lane
interview; the user locked PORT, hardened, as a new single-capability
plugin.
- New plugin `wizard` 0.1.0, one skill `generate` (/wizard:generate,
leaf named via naming tournament; grammar-clean, no naming-exception
entry). Model-invoked with upstream's non-trigger fence kept ("Don't
invoke this for steps the agent can perform itself").
- Hardened template.sh (the gating outcome of a completed security
review, all conditions shipped): mandatory human read-and-approve of
the full STAGES block before chmod +x; https-only open_url with the
URL printed before dispatch (closes a Windows UNC/NTLM leak via
explorer.exe); /dev/tty fail-closed prompts retiring a verified
multi-line-paste confirm bypass and pause's EOF fail-open; quoted
0600 .env writes + gitignore pre-flight assert + trap-cleaned atomic
temp; repo-resolved/confirmed --repo-explicit gh writes with stderr
surfaced into SKIPPED and empty values refused; key-name validation
in every helper; readline on non-secret asks (upstream #741 fixed
where safe); set_var via --body-file - (stdin, never argv).
- Scoping honesty fix: step 1 reads .env.example/README/workflows fully
but takes key NAMES only from a live .env, never values; the skill
states the secrets-and-context property honestly.
- Fresh-context static trace delegated in the skill's verify step per
the fresh-eyes rules; bash -n/shellcheck stay deterministic gates.
- Records: SSOT attribution row + open-evaluations update, map row 18,
PLAN.md Q10/lane-4 closure, MIGRATION-PLAYBOOK ACCEPT record for the
model-generated-executable surface (deliberately breaks the
statusline-shim no-templating precedent, mitigations recorded).
- Marketplace entry + regenerated CATALOG and skill cheat sheet.
- Gates: bash -n + shellcheck clean; skill-quality check PASS (0 warn);
portability gate clean (gh sites declared portability-ok); typos and
markdownlint clean; claude plugin validate + --strict catalog pass;
functional smoke of the library helpers; fresh-context verifier
subagent returned 25/25 PASS (its two non-blocking findings fixed:
explorer.exe spurious warning, gitignore check now pre-flight).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
…ts (lane 5) M10 SPLIT: adopt the shareable-HTML logic shell into prototype:pressure-test as an audience-routed substrate (TUI default; self-contained HTML demo for non-developer drivers or no-terminal handoffs, under explore-directions' CSP/ephemeral-temp/ synthetic-data/discard-after-capture constraint set); reject the throwaway-branch "primary source" capture half (two-lane violation; contradicts delete-when-done). prototype 0.4.0; provenance: mattpocock/skills v1.2.3 @ 84fdeff LOGIC.md. M13: reject writing-for-agents/SKILL-MECHANICS bulk at parity or stronger; track two strands on event triggers (leading-words+negation, cross-linked to the interview-batch-rounds deferral; invocation-reach invariant). M14: reject version-sync script (changesets/npm pipeline tool; check-changelog-parity.sh stronger; marketplace.json carries no version keys). M15: reject .out-of-scope/ KB as already-adopted (work-items 0.6.0 ledger is a superset) and correct the SSOT triage row to Derived (structured port); no work-items behavior change. M16: reject "It's working if" sections (docs-site decoration); reopen condition recorded in the rejection, not a TRACK row. Close the SSOT open-evaluations sentence; resolve Q11 and record the Lane 5 closure in the topic plan; regenerate the skill cheat-sheet for the pressure-test summary change. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
Bugbot is not enabled for your account, so this pull request was not reviewed. Enable Bugbot in the Cursor dashboard to get automatic reviews on future PRs. |
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: f727d19c4c
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
…2-sync # Conflicts: # plugins/architecture/CHANGELOG.md # plugins/discipline/.claude-plugin/plugin.json # plugins/discipline/CHANGELOG.md # plugins/planning/.claude-plugin/plugin.json # plugins/planning/CHANGELOG.md # plugins/prototype/CHANGELOG.md # plugins/session-flow/.claude-plugin/plugin.json # plugins/session-flow/CHANGELOG.md # plugins/testing/.claude-plugin/plugin.json # plugins/testing/CHANGELOG.md
Contributor
|
Claude encountered an error after 0s —— View job I'll analyze this and get back to you. |
|
Warning Automated review did not complete — this is an infrastructure failure, not a review verdict. Treat any Claude comment on this PR (including a placeholder like "I'll analyze this and get back to you") as incomplete, not "no findings."
Re-run the job to retry the review. A new push does not re-trigger this lane. |
Contributor
|
Claude encountered an error after 0s —— View job I'll analyze this and get back to you. |
…er the generate leaf - Graduate the durable audit record: docs/topics/pocock-skills-v12-sync/his-ours-map.md moves to docs/upstream/mattpocock-skills-v12-map.md (the SSOT already links it); delete PLAN.md and RESEARCH.md from the slice — decisions live in the SSOT, PLUGIN-PHILOSOPHY, and MIGRATION-PLAYBOOK records, and the slice history stays in git (contract-slice prune gate). - Register the generate leaf collision (ai-briefing,wizard) with grounds (skill-leaf-name gate). - Track template.sh executable (shebang exec-bit gate). - Add the missing blank lines at the discipline CHANGELOG merge seam (markdownlint). security-review failed on a transient API 429; this push retries it. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Contributor
|
Claude encountered an error after 0s —— View job I'll analyze this and get back to you. |
Contributor
|
Claude encountered an error after 0s —— View job I'll analyze this and get back to you. |
Two Codex review findings on template.sh, both verified locally: - set_var used `gh variable set --body-file -`, a flag that does not exist — every authenticated variable write would have failed before reaching the API. gh reads the value from standard input when --body is omitted (verified against gh 2.96.0 --help), so pipe the value with no body flag. - /dev/tty prompts did not drain buffered paste: `value\ny\n` pasted into an ask prompt left `y` in the tty buffer, silently answering the next confirm gate. New _drain_tty discards pending lines at the top of pause and confirm, so a gate only consumes a line typed at it. bash -n + shellcheck clean; drain semantics reproduced in a scripted check. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Contributor
|
Claude encountered an error after 0s —— View job I'll analyze this and get back to you. |
Contributor
|
Claude encountered an error after 1s —— View job I'll analyze this and get back to you. |
|
Warning Automated security review did not complete — this is an infrastructure failure, not a review verdict. Treat any Claude comment on this PR (including a placeholder like "I'll analyze this and get back to you") as incomplete, not "no findings."
The check is red on purpose. It certifies that a security pass ran, and this one did not complete, so it cannot report success. Where this check is required, merging is blocked until a review actually finishes. Re-running the job, or pushing a new commit, will retry the review. An automatic retry may already have run — it is skipped when a partial review could duplicate comments, or when the failure class needs an operator. Re-running does NOT help for every class:
|
kyle-sexton
pushed a commit
that referenced
this pull request
Aug 21, 2026
An independent audit re-checked every claim in the two upstream SSOT documents against the actual repo state, with three fresh-context verifiers re-testing each discrepancy and one candidate finding refuted and dropped. Nine survived. aihero-shipping-course.md: - Lane Y said the marketplace-wide glossary was deferred. docs/GLOSSARY.md landed 2026-08-20 (#3062) and already defines `phase boundary`. Corrected to record the promotion, with `item` and `checkpoint` staying reference-local. - Lane D said the container close-out review "is structurally larger than a mode addition". #3027 is closed: it landed as exactly that — a tenth quality-gate lens — with all four broken mechanisms resolved in-file. - Lane D C12 claimed the branch-scoped spec lens filled the dangling consumer in decompose and ship. It did not: that consumer was container-scoped, work-items' own changelog says so, and #3027's close-out mode filled it. The quoted phrase is also gone from both skills, surviving only in changelog history. - C23 cited `.agents/` trigger text. Verified against mattpocock/skills@068b6e0: `.agents/` holds five files and none carries a domain-modeling trigger. The real source is domain-modeling/SKILL.md:3, from PR #848 — so the Lane X row, which scoped all of C21-C23 to #878/#880, is corrected too. mattpocock-skills.md: - `to-tickets` was recorded as "Influence (vocabulary)", which understated it AND disagreed with the v12 map's own PARTIAL grade. Four of Lane B's five adopted candidates are mechanics, not phrasing; only "work the frontier" is vocabulary. mattpocock-skills-v12-map.md — four rows contradicted by landed work: - row 2 called the two-axis parallel-subagent structure "Omitted"; self.md:17 IS that structure, differing only in calling it a lens rather than an axis. - row 13 called the tdd seam discipline "Not ported"; it landed at plan/SKILL.md:96 with two deliberate divergences. - row 14 called to-spec "Not ported"; C3 and C4 both landed in decompose. - the invocation-reach rule was recorded as having "no such stated invariant in our repo"; it is a named section in the invocation-mode convention doc, and the sibling SSOT already recorded it CONFIRMED — the two docs contradicted. - drift findings 1 and 2 cite questionnaire/SKILL.md:48-50. That file is 45 lines and greps clean; the text was removed in #2082 BEFORE the map was written. Both marked discharged rather than left reading present-tense. Also fixes a divergence the audit surfaced as a side effect: `phase boundary` had TWO definitions — docs/GLOSSARY.md's and execution-shape.md's — one of them in a file claiming repo-wide authority. execution-shape.md now cedes the definition and keeps only the seam-specific relation to `checkpoint`. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01CnzwTKoTa6xNY7iyEzMYpm
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No linked issue
Summary
Syncs the learnings from mattpocock/skills v1.2 (HEAD v1.2.3 @
84fdeff) into this marketplace across five lanes on one branch: provenance SSOT + verified 35-skill map, owned-skill behavior deltas, two new-skill ports (discipline:wait-what,wizard:generate), and the infra-subset verdicts.Fix
docs/upstream/mattpocock-skills.md(single provenance SSOT, in-skill provenance stripped) plus the verified upstream↔ours map underdocs/topics/pocock-skills-v12-sync/.wait-whatas a declared non-corrector species indiscipline(0.11.0), with a documented naming-exception entry indocs/PLUGIN-PHILOSOPHY.md.wizardas a NEW single-capability plugin (wizard0.1.0,/wizard:generate, name locked via a 5-generator/3-judge blind naming tournament). The shippedtemplate.shis a hardened variant: human read/approval of authored stages beforechmod +x, https-onlyopen_urlwith pre-dispatch URL print,/dev/ttyfail-closed prompts,chmod 600+ gitignore assertion + temp-file trap on.envwrites, explicit--repoand empty-value refusal onghwrites, key-name validation, quoted/escaped env values, and an honest secrets-and-model-context statement (scoping reads key names only from a live.env). Adocs/MIGRATION-PLAYBOOK.mdacceptance record documents the deliberate break of the statusline-shim no-templating precedent with its load-bearing conditions.prototype:pressure-test(0.4.0); rejected the branch-capture half, version-sync script, and docs-site "It's working if" sections; recorded two event-triggered TRACK strands; corrected the SSOT triage row to a Derived structured port.Verification
check-skill.sh(wait-what, generate, pressure-test),check-skill-portability.sh, markdownlint-cli2 (repo config),check-changelog-parity.sh(--check,--check-bump,--check-order), typos,claude plugin validate --strict ., catalog/cheat-sheet drift checks,bash -n+ shellcheck (0 findings) + a functional smoke suite onwizard'stemplate.sh.docs/topics/pocock-skills-v12-sync/PLAN.md.Related
docs/topics/pocock-skills-v12-sync/PLAN.md— the five-lane Brief, per-lane closure records, and resolved decision log (Q1–Q27).docs/upstream/mattpocock-skills.md— provenance SSOT with attribution rows, rejections, and event-triggered TRACK records.84fdeff.