[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75K6XYRVCS69Z79MF4N71GV":3,"skill-same:01M75K6XYRVCS69Z79MF4N71GV":49},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M75K6XYRVCS69Z79MF4N71GV","self-review",null,"Gate-wired review pass of the current feature branch: Discovery Rigor fan-out, multi-pass validation, and act-then-review dispositions per the finding categorization. Standalone runs push and open or update a draft PR; pass --nested to stay local and return the audit record to the invoking skill.","inkatze\u002Fplanwright","inkatze","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F2029270?v=4","01M75K412KAPRFBSFXA7ZF2ZVY","Diego Romero","01M75K41364G95D0ZS5MWK7PZ3",4,"MIT","https:\u002F\u002Fgithub.com\u002Finkatze\u002Fplanwright\u002Fblob\u002Fmain\u002Fskills\u002Fself-review\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: self-review\ndescription: >\n  Gate-wired review pass of the current feature branch: Discovery Rigor\n  fan-out, multi-pass validation, and act-then-review dispositions per the\n  finding categorization. Standalone runs push and open or update a draft PR;\n  pass --nested to stay local and return the audit record to the invoking\n  skill.\nargument-hint: \"[--nested]\"\n---\n\n# \u002Fself-review\n\nOne complete review pass of the feature branch against its base, wired into\nplanwright's act-then-review autonomy gate (REQ-E2.1, D-12). `\u002Fpolish`\niterates it to convergence; this skill is the single pass.\n\n## Doctrine\n\nThis skill is procedure, not doctrine. Resolve the rule docs in the manifest\nbelow via the rule-doc resolution convention\n(`scripts\u002Fresolve-rule-doc.sh \u003Cdoc-name>` under the resolved planwright root,\nor the documented `PLANWRIGHT_ROOT`\u002F`CLAUDE_PLUGIN_ROOT` chain); their\ndefinitions govern wherever this skill names a concept. Issue one plain command\nper Bash call, test and lint runs through `compute-route.sh`\n(`doctrine\u002Fplugin-script-invocation.md`).\n\nIf a rule doc does not resolve, halt with a clear message naming the missing\ndoc and the resolution chain consulted.\n\nDoctrine manifest (per `doctrine\u002Finstruction-hygiene.md`; `run-start` docs\nload before work begins, `point-of-use` at the named step):\n\nDoctrine: point-of-use discovery-rigor (the Discovery step)\nDoctrine: point-of-use validation-rigor (Validation and fix validation)\nDoctrine: run-start finding-categorization\nDoctrine: run-start gate-wiring\nDoctrine: point-of-use research-rigor (the Validation step, where research triggers fire)\nDoctrine: point-of-use refactor-instinct (review mode, at the Discovery refactor filter)\nDoctrine: run-start security-posture (artifact data-hygiene)\nDoctrine: point-of-use proportionality (Discovery's fan-out and Validation's scoping)\n\n## Invocation modes\n\nRead the literal flag `--nested` from `$ARGUMENTS` at the start of the run:\n\n- **Standalone** (no flag): the pass ends by pushing the branch and creating\n  or updating a draft PR carrying the audit record (see \"Publishing the audit\n  record\").\n- **Nested** (`--nested`): another planwright skill (typically `\u002Fpolish`)\n  invoked this pass and owns everything after it. Skip push and PR handling;\n  hand the audit record back to the invoking skill. It may pass its loop\n  ledger of already-dispositioned findings: a re-discovered finding that\n  already carries a disposition is reported in the audit record but never\n  re-routed, re-applied, or re-paused. One exception: surface a\n  re-discovered finding whose ledger disposition is any on-branch\n  application (applied, resolved, or applied pending sign-off) prominently\n  in the handed-back record; it signals the fix did not hold and feeds the\n  invoking skill's loop detection.\n\nNested invocation is in-session skill composition (REQ-E2.2, D-13): the pass\nruns in the invoking skill's session and context, and hooks fire once per\nactual tool call, not once per skill layer. Record the resolved mode in the\npass summary.\n\n## Pre-flight\n\n1. **Resolve the doctrine docs** (above). Halt with a clear message on a\n   resolution failure.\n2. **Identify the base and capture the diff.** Fetch first, then diff against\n   the remote-tracking base: `git fetch origin` and\n   `git diff origin\u002Fmain...HEAD` (substitute the repository's actual default\n   branch). Fall back to the local base only when no remote is configured\n   (REQ-K1.7), since a stale local base inflates the diff with already-merged\n   commits. In nested mode, skip the fetch and reuse the base the invoking\n   skill recorded at its own pre-flight; the parent owns remote interaction.\n   Not a git repository, or no commits to diff: surface a clear message and\n   stop; there is nothing to review.\n3. **Require a clean working tree.** The gate's commit discipline needs\n   unambiguous boundaries. If `git status --porcelain` is non-empty, surface\n   the dirty state and ask before proceeding (dispatched or unattended: record the\n   unit to `tasks.md` Awaiting input and end the step, the pause protocol's\n   dispatched arm); never stash or discard.\n4. **Run the project's tooling once.** Whatever the project ships: linters,\n   formatters, type-checkers, static analyzers, security scanners. Discover\n   them via the project's task runner and config files, CI workflow\n   definitions, and the tool-discovery summary when a SessionStart hook has\n   injected one. Capture the output; it is shared input for every lens. A\n   tool whose runner itself errors out (as opposed to reporting rule\n   violations) is surfaced in the pass summary as degraded grounding for the\n   lenses that rely on it; never treat a crashed tool as a clean pass.\n5. **Detect the active kickoff brief.** Walk in order, stopping at the first\n   unambiguous match: the branch convention `planwright\u002F\u003Cspec>\u002Ftask-\u003Cids>`\n   names the spec, so the brief is `specs\u002F\u003Cspec>\u002Fkickoff-brief.md` (validate\n   the parsed `\u003Cspec>` segment against the spec-identifier discipline,\n   `^[a-z0-9][a-z0-9-]*$` and at most 64 characters per REQ-A1.8, before\n   forming the path; a failing segment is treated as no match, never\n   interpolated); a branch-named spec whose own `kickoff-brief.md` is absent\n   means the brief is absent for this pass, never a fall-through to another\n   spec's brief, and so does a flight branch `planwright\u002Fflight\u002F\u003Cid>`, which\n   names no spec. Otherwise resolve through the status render\n   (`scripts\u002Fspec-status.sh` \u002F `mise run status`; invariant-tasks D-6),\n   accepting a `specs\u002F*\u002F` bundle whose derived status is Ready or Active — so\n   a format-version-2 bundle with work in flight (stored Ready, derived\n   Active) resolves, not only a stored-`Active` v1 spec. When exactly one such\n   candidate exists, take its sibling `kickoff-brief.md`. A render error, zero\n   candidates, or multiple Ready-or-Active candidates are not an unambiguous\n   match: degrade to the existing arm — ask when attended, proceed brief-less\n   when unattended or dispatched (D-2). With\n   no active brief, the Agent-resolvable bucket is unavailable for this pass\n   (its predicate requires brief alignment); record that and proceed with\n   the remaining buckets.\n\n## Discovery\n\nApply the `discovery-rigor` doc against the diff:\n\n- **Fan out by default.** Spawn one read-only sub-agent per canonical lens\n  for any non-trivial diff, each with the diff slice, the shared tooling\n  output, and a single-lens brief that forbids severity pruning. Walk the\n  lenses inline only when the diff is small and narrow (a few files, mostly\n  prose or config, a few hundred changed lines at most); inline walking\n  waives no other invariant. Declare which path was taken.\n- **Merge and dedupe.** A finding hitting two lenses gets one row with both\n  labels.\n- **Filter refactor flags in review mode** per `refactor-instinct`: anchored\n  in tool output or made worse by this branch, otherwise dropped. This bullet\n  is the doc's only read site, which is what its `point-of-use` classification\n  rests on; a second, earlier read site needs the manifest revisited.\n- **Hold the Documentation lens to `discovery-rigor`'s four defect classes**:\n  prose the diff falsifies, documentation missing for behaviour the diff\n  introduces, a documentation guard's violation, and an interpretation fork.\n  Merely improvable prose is not a finding, and a `none` row that says so is\n  coverage rather than a gap.\n- **Emit the canonical lens-coverage table** before any per-finding output:\n  one row per lens, empty lenses as `none` or `n\u002Fa` with a one-line reason.\n- **Run the mandatory self-critique pass**: assume the list is incomplete,\n  re-scan for what is under-represented, add what surfaces.\n\n## Validation\n\nApply the `validation-rigor` doc to every candidate finding. Declared scoping\n(per `proportionality`): the full three passes are mandatory for any finding\nthat could be **applied on the branch** in this pass, which under\nact-then-review means Auto-applicable, Agent-resolvable, and Needs-sign-off\ncandidates alike. A soft-floor spot-check (drop clear false positives) is\nsufficient for findings that will only be declined or queued as judgment\nforks, since the human finishes validation when deciding those. Findings\nwhose passes do not converge are never applied; they are dropped, declined\nwith the divergence recorded, or routed to Needs human judgment per the\ncategorization.\n\nWhen a finding turns on an external fact (an API contract, spec compliance, a\ndeprecated pattern or security claim, library behavior), the outside-in pass\nreads `research-rigor` point-of-use here — source hierarchy, recency\ndiscipline, antipattern check.\n\n## Routing and dispositions\n\nRoute every validated finding through the `gate-wiring` doc's routing order:\nzone screen first, then bucket assignment per the `finding-categorization`\npredicates, then disposition by bucket. The wiring doc governs the mechanics\nthis skill executes. Every artifact the pass emits passes `security-posture`'s\nartifact data-hygiene first: commit bodies, audit rows, the PR body,\nobservation fragments, and the lens-coverage table Discovery has already\nproduced, whose Notes cells quote tooling output.\n\n- A finding whose fix edits **only prose** is classed on\n  `finding-categorization`'s *Prose findings* axis before it is routed:\n  expression-only when no normative statement changes meaning, meaning-class\n  otherwise.\n- Auto-applicable and Agent-resolvable items are applied or resolved with\n  their audit and evidence rows, and committed per the wiring doc's commit\n  discipline; their fixes get solution validation per `validation-rigor`.\n- Attended or unattended, a Needs-sign-off fix is committed on the branch,\n  never asked about first, per that same discipline (its\n  `Planwright-Sign-Off` trailer via\n  `scripts\u002Fplanwright-commit-trailers.sh --base \u003Cbase> --sign-off`), and entered in the\n  checklist.\n- Needs-human-judgment candidates climb the resolution ladder; every\n  consulted rung is recorded. Only irreducible forks queue, with bespoke\n  options.\n- Declined-with-rationale is available at any step after validation;\n  rationale rows are mandatory.\n- A hard-disqualifier zone or a blocking irreducible fork triggers the pause\n  protocol; nothing else interrupts the pass.\n\n**Findings whose fix edits a signed bundle** carry the three obligations the\nmeta-spec's writer prose states (`doctrine\u002Fspec-format.md`, *Sign-off records\nand content anchors*), which governs here. Before the first edit to each Ready or\nActive bundle's anchored content, run the **stale-anchor pre-flight**: recompute with\nthe brief's most recent recorded command; a mismatch, an absent or unparseable\nentry, and a failed recompute each block that edit and surface instead of\nediting on top of it (findings elsewhere in the diff keep routing normally).\nA blocked finding is never left undispositioned: it queues as an irreducible\nfork whose route is the anchor repair. An **expression-only** fix then lands\nthe edit, its dated Changelog entry, and the marked\n`Class: expression-only` self-re-anchor entry citing it in **one\ncommit**. A **meaning-class** fix is never applied: leave the bundle untouched\nand queue it as an irreducible fork naming a `\u002Fspec-kickoff` delta\nre-walkthrough as the route.\n\nIf any applied fix breaks the wider project suite and the breakage cannot be\nresolved within the finding's own scope, revert that finding's change (new\ncommit, never history rewrite) and surface the failure in the pass summary.\nThe reverted finding's terminal disposition is declined-with-rationale\n(\"fix attempted, broke the wider suite, reverted\"), recorded in the\ndeclined log, where it stays visible and re-raisable without re-entering the\nrouting order.\n\n## The audit record\n\nThe pass produces, **artifact-side**, in this order (the wiring doc's loop-end\nhandoff, extended with the lens-coverage table at the front and the pass\nsummary at the end):\n\n1. The lens-coverage table.\n2. In the wiring doc's formats: the four bucket tables, the declined log, and\n   the pending-sign-off checklist regenerated from sign-off trailers ahead of\n   the base.\n3. Queued irreducible forks with their bespoke options.\n4. The pass summary: resolved mode, base used, tooling and wider-suite\n   results, and any reverts or surfaced failures.\n\nThe **turn** gets the wiring's projection: counts, each pending sign-off and\neach fork; standalone, only forks are questions. Print each trailered\ncommit's SHA and the command `git log --format='%h\n%(trailers:key=Planwright-Sign-Off,key=Planwright-Sign-Off-Rejected,separator=%x20)\n%s' \u003Cbase>..HEAD`.\nThe approval act, never the ready flip, signs off\npending-sign-off items; reject one before it by its printed recipe.\n\n## Publishing the audit record (standalone only)\n\nPublishing is the pass's final action: the Observations and Maintenance\nsteps below run first, so their chore commits land before the push.\n\n1. **Push:** `git push origin \u003Cbranch>` (with `-u` on first push). Pushed\n   history stays append-only. On push or authentication failure, degrade gracefully\n   (REQ-K1.6, REQ-K1.7): the local work is committed; surface what failed\n   and stop.\n2. **Draft PR:** if a PR already exists for the branch, update its body;\n   otherwise `gh pr create --draft` with an explicit `--title` and `--body`\n   (headless `gh` prompts or fails without them). Assemble the body per the\n   **PR-body assembly** section of the `gate-wiring` doctrine, the single\n   normative home for the layout (D-2); the collapsed audit record is this\n   pass's own (the sequence in **The audit record** above). The PR is always a\n   draft: a standalone review run never flips or merges\n   (`doctrine\u002Fhuman-gates.md`).\n\n## Observations\n\nIn a repository with a spec bundle under `specs\u002F`, record anything noticed\noutside the branch's scope (complexity growth, outdated patterns, tooling or\ndoctrine gaps) as one fragment per observation through\n`scripts\u002Fobs-record.sh --slug \u003Ctopic> --scope \u003Crepo> --text '\u003Cobservation>'`\n(resolved under the planwright root). Before committing fragments, review\nthem with the spec lens set plus a duplication check against the store, each\nquoted message, named test, figure and attribution read against its source;\nrecord every disposition, and a refused record's recurrence or withdrawal, in\nthe audit record, correcting or withdrawing a falsified fragment. Commit them\nwithin the pass (the action commit, or a chore commit); never leave the tree\ndirty at a pass boundary, and surface a non-zero helper exit. Do not act on\nobservations during the pass; they seed `\u002Fspec-draft` (REQ-E2.1, REQ-H1.6).\n\n## Maintenance\n\nAfter the pass completes (or halts), compare these instructions against the\nresolved doctrine docs listed above (REQ-B3.2, D-42). If a concept this skill\nnames has changed meaning, gained or lost a step, or moved between docs,\nrecord a drift observation (`scripts\u002Fobs-record.sh --slug skill-drift\n--scope \u003Crepo> --text 'skill-drift(self-review): \u003Cwhat>'`, the text keeping\nthat prefix; without `specs\u002F`, surface the drift to the user instead),\nreview the fragment as the Observations step does, commit it as its own chore\ncommit, tell the user what drifted, and surface a non-zero helper exit.\nDo not edit this skill or the doctrine docs to resolve the drift; `\u002Fspec-draft`\nowns folding drift into spec amendments.\n","# \u002Fself-review\n\nOne complete review pass of the feature branch against its base, wired into\nplanwright's act-then-review autonomy gate (REQ-E2.1, D-12). `\u002Fpolish`\niterates it to convergence; this skill is the single pass.\n\n## Doctrine\n\nThis skill is procedure, not doctrine. Resolve the rule docs in the manifest\nbelow via the rule-doc resolution convention\n(`scripts\u002Fresolve-rule-doc.sh \u003Cdoc-name>` under the resolved planwright root,\nor the documented `PLANWRIGHT_ROOT`\u002F`CLAUDE_PLUGIN_ROOT` chain); their\ndefinitions govern wherever this skill names a concept. Issue one plain command\nper Bash call, test and lint runs through `compute-route.sh`\n(`doctrine\u002Fplugin-script-invocation.md`).\n\nIf a rule doc does not resolve, halt with a clear message naming the missing\ndoc and the resolution chain consulted.\n\nDoctrine manifest (per `doctrine\u002Finstruction-hygiene.md`; `run-start` docs\nload before work begins, `point-of-use` at the named step):\n\nDoctrine: point-of-use discovery-rigor (the Discovery step)\nDoctrine: point-of-use validation-rigor (Validation and fix validation)\nDoctrine: run-start finding-categorization\nDoctrine: run-start gate-wiring\nDoctrine: point-of-use research-rigor (the Validation step, where research triggers fire)\nDoctrine: point-of-use refactor-instinct (review mode, at the Discovery refactor filter)\nDoctrine: run-start security-posture (artifact data-hygiene)\nDoctrine: point-of-use proportionality (Discovery's fan-out and Validation's scoping)\n\n## Invocation modes\n\nRead the literal flag `--nested` from `$ARGUMENTS` at the start of the run:\n\n- **Standalone** (no flag): the pass ends by pushing the branch and creating\n  or updating a draft PR carrying the audit record (see \"Publishing the audit\n  record\").\n- **Nested** (`--nested`): another planwright skill (typically `\u002Fpolish`)\n  invoked this pass and owns everything after it. Skip push and PR handling;\n  hand the audit record back to the invoking skill. It may pass its loop\n  ledger of already-dispositioned findings: a re-discovered finding that\n  already carries a disposition is reported in the audit record but never\n  re-routed, re-applied, or re-paused. One exception: surface a\n  re-discovered finding whose ledger disposition is any on-branch\n  application (applied, resolved, or applied pending sign-off) prominently\n  in the handed-back record; it signals the fix did not hold and feeds the\n  invoking skill's loop detection.\n\nNested invocation is in-session skill composition (REQ-E2.2, D-13): the pass\nruns in the invoking skill's session and context, and hooks fire once per\nactual tool call, not once per skill layer. Record the resolved mode in the\npass summary.\n\n## Pre-flight\n\n1. **Resolve the doctrine docs** (above). Halt with a clear message on a\n   resolution failure.\n2. **Identify the base and capture the diff.** Fetch first, then diff against\n   the remote-tracking base: `git fetch origin` and\n   `git diff origin\u002Fmain...HEAD` (substitute the repository's actual default\n   branch). Fall back to the local base only when no remote is configured\n   (REQ-K1.7), since a stale local base inflates the diff with already-merged\n   commits. In nested mode, skip the fetch and reuse the base the invoking\n   skill recorded at its own pre-flight; the parent owns remote interaction.\n   Not a git repository, or no commits to diff: surface a clear message and\n   stop; there is nothing to review.\n3. **Require a clean working tree.** The gate's commit discipline needs\n   unambiguous boundaries. If `git status --porcelain` is non-empty, surface\n   the dirty state and ask before proceeding (dispatched or unattended: record the\n   unit to `tasks.md` Awaiting input and end the step, the pause protocol's\n   dispatched arm); never stash or discard.\n4. **Run the project's tooling once.** Whatever the project ships: linters,\n   formatters, type-checkers, static analyzers, security scanners. Discover\n   them via the project's task runner and config files, CI workflow\n   definitions, and the tool-discovery summary when a SessionStart hook has\n   injected one. Capture the output; it is shared input for every lens. A\n   tool whose runner itself errors out (as opposed to reporting rule\n   violations) is surfaced in the pass summary as degraded grounding for the\n   lenses that rely on it; never treat a crashed tool as a clean pass.\n5. **Detect the active kickoff brief.** Walk in order, stopping at the first\n   unambiguous match: the branch convention `planwright\u002F\u003Cspec>\u002Ftask-\u003Cids>`\n   names the spec, so the brief is `specs\u002F\u003Cspec>\u002Fkickoff-brief.md` (validate\n   the parsed `\u003Cspec>` segment against the spec-identifier discipline,\n   `^[a-z0-9][a-z0-9-]*$` and at most 64 characters per REQ-A1.8, before\n   forming the path; a failing segment is treated as no match, never\n   interpolated); a branch-named spec whose own `kickoff-brief.md` is absent\n   means the brief is absent for this pass, never a fall-through to another\n   spec's brief, and so does a flight branch `planwright\u002Fflight\u002F\u003Cid>`, which\n   names no spec. Otherwise resolve through the status render\n   (`scripts\u002Fspec-status.sh` \u002F `mise run status`; invariant-tasks D-6),\n   accepting a `specs\u002F*\u002F` bundle whose derived status is Ready or Active — so\n   a format-version-2 bundle with work in flight (stored Ready, derived\n   Active) resolves, not only a stored-`Active` v1 spec. When exactly one such\n   candidate exists, take its sibling `kickoff-brief.md`. A render error, zero\n   candidates, or multiple Ready-or-Active candidates are not an unambiguous\n   match: degrade to the existing arm — ask when attended, proceed brief-less\n   when unattended or dispatched (D-2). With\n   no active brief, the Agent-resolvable bucket is unavailable for this pass\n   (its predicate requires brief alignment); record that and proceed with\n   the remaining buckets.\n\n## Discovery\n\nApply the `discovery-rigor` doc against the diff:\n\n- **Fan out by default.** Spawn one read-only sub-agent per canonical lens\n  for any non-trivial diff, each with the diff slice, the shared tooling\n  output, and a single-lens brief that forbids severity pruning. Walk the\n  lenses inline only when the diff is small and narrow (a few files, mostly\n  prose or config, a few hundred changed lines at most); inline walking\n  waives no other invariant. Declare which path was taken.\n- **Merge and dedupe.** A finding hitting two lenses gets one row with both\n  labels.\n- **Filter refactor flags in review mode** per `refactor-instinct`: anchored\n  in tool output or made worse by this branch, otherwise dropped. This bullet\n  is the doc's only read site, which is what its `point-of-use` classification\n  rests on; a second, earlier read site needs the manifest revisited.\n- **Hold the Documentation lens to `discovery-rigor`'s four defect classes**:\n  prose the diff falsifies, documentation missing for behaviour the diff\n  introduces, a documentation guard's violation, and an interpretation fork.\n  Merely improvable prose is not a finding, and a `none` row that says so is\n  coverage rather than a gap.\n- **Emit the canonical lens-coverage table** before any per-finding output:\n  one row per lens, empty lenses as `none` or `n\u002Fa` with a one-line reason.\n- **Run the mandatory self-critique pass**: assume the list is incomplete,\n  re-scan for what is under-represented, add what surfaces.\n\n## Validation\n\nApply the `validation-rigor` doc to every candidate finding. Declared scoping\n(per `proportionality`): the full three passes are mandatory for any finding\nthat could be **applied on the branch** in this pass, which under\nact-then-review means Auto-applicable, Agent-resolvable, and Needs-sign-off\ncandidates alike. A soft-floor spot-check (drop clear false positives) is\nsufficient for findings that will only be declined or queued as judgment\nforks, since the human finishes validation when deciding those. Findings\nwhose passes do not converge are never applied; they are dropped, declined\nwith the divergence recorded, or routed to Needs human judgment per the\ncategorization.\n\nWhen a finding turns on an external fact (an API contract, spec compliance, a\ndeprecated pattern or security claim, library behavior), the outside-in pass\nreads `research-rigor` point-of-use here — source hierarchy, recency\ndiscipline, antipattern check.\n\n## Routing and dispositions\n\nRoute every validated finding through the `gate-wiring` doc's routing order:\nzone screen first, then bucket assignment per the `finding-categorization`\npredicates, then disposition by bucket. The wiring doc governs the mechanics\nthis skill executes. Every artifact the pass emits passes `security-posture`'s\nartifact data-hygiene first: commit bodies, audit rows, the PR body,\nobservation fragments, and the lens-coverage table Discovery has already\nproduced, whose Notes cells quote tooling output.\n\n- A finding whose fix edits **only prose** is classed on\n  `finding-categorization`'s *Prose findings* axis before it is routed:\n  expression-only when no normative statement changes meaning, meaning-class\n  otherwise.\n- Auto-applicable and Agent-resolvable items are applied or resolved with\n  their audit and evidence rows, and committed per the wiring doc's commit\n  discipline; their fixes get solution validation per `validation-rigor`.\n- Attended or unattended, a Needs-sign-off fix is committed on the branch,\n  never asked about first, per that same discipline (its\n  `Planwright-Sign-Off` trailer via\n  `scripts\u002Fplanwright-commit-trailers.sh --base \u003Cbase> --sign-off`), and entered in the\n  checklist.\n- Needs-human-judgment candidates climb the resolution ladder; every\n  consulted rung is recorded. Only irreducible forks queue, with bespoke\n  options.\n- Declined-with-rationale is available at any step after validation;\n  rationale rows are mandatory.\n- A hard-disqualifier zone or a blocking irreducible fork triggers the pause\n  protocol; nothing else interrupts the pass.\n\n**Findings whose fix edits a signed bundle** carry the three obligations the\nmeta-spec's writer prose states (`doctrine\u002Fspec-format.md`, *Sign-off records\nand content anchors*), which governs here. Before the first edit to each Ready or\nActive bundle's anchored content, run the **stale-anchor pre-flight**: recompute with\nthe brief's most recent recorded command; a mismatch, an absent or unparseable\nentry, and a failed recompute each block that edit and surface instead of\nediting on top of it (findings elsewhere in the diff keep routing normally).\nA blocked finding is never left undispositioned: it queues as an irreducible\nfork whose route is the anchor repair. An **expression-only** fix then lands\nthe edit, its dated Changelog entry, and the marked\n`Class: expression-only` self-re-anchor entry citing it in **one\ncommit**. A **meaning-class** fix is never applied: leave the bundle untouched\nand queue it as an irreducible fork naming a `\u002Fspec-kickoff` delta\nre-walkthrough as the route.\n\nIf any applied fix breaks the wider project suite and the breakage cannot be\nresolved within the finding's own scope, revert that finding's change (new\ncommit, never history rewrite) and surface the failure in the pass summary.\nThe reverted finding's terminal disposition is declined-with-rationale\n(\"fix attempted, broke the wider suite, reverted\"), recorded in the\ndeclined log, where it stays visible and re-raisable without re-entering the\nrouting order.\n\n## The audit record\n\nThe pass produces, **artifact-side**, in this order (the wiring doc's loop-end\nhandoff, extended with the lens-coverage table at the front and the pass\nsummary at the end):\n\n1. The lens-coverage table.\n2. In the wiring doc's formats: the four bucket tables, the declined log, and\n   the pending-sign-off checklist regenerated from sign-off trailers ahead of\n   the base.\n3. Queued irreducible forks with their bespoke options.\n4. The pass summary: resolved mode, base used, tooling and wider-suite\n   results, and any reverts or surfaced failures.\n\nThe **turn** gets the wiring's projection: counts, each pending sign-off and\neach fork; standalone, only forks are questions. Print each trailered\ncommit's SHA and the command `git log --format='%h\n%(trailers:key=Planwright-Sign-Off,key=Planwright-Sign-Off-Rejected,separator=%x20)\n%s' \u003Cbase>..HEAD`.\nThe approval act, never the ready flip, signs off\npending-sign-off items; reject one before it by its printed recipe.\n\n## Publishing the audit record (standalone only)\n\nPublishing is the pass's final action: the Observations and Maintenance\nsteps below run first, so their chore commits land before the push.\n\n1. **Push:** `git push origin \u003Cbranch>` (with `-u` on first push). Pushed\n   history stays append-only. On push or authentication failure, degrade gracefully\n   (REQ-K1.6, REQ-K1.7): the local work is committed; surface what failed\n   and stop.\n2. **Draft PR:** if a PR already exists for the branch, update its body;\n   otherwise `gh pr create --draft` with an explicit `--title` and `--body`\n   (headless `gh` prompts or fails without them). Assemble the body per the\n   **PR-body assembly** section of the `gate-wiring` doctrine, the single\n   normative home for the layout (D-2); the collapsed audit record is this\n   pass's own (the sequence in **The audit record** above). The PR is always a\n   draft: a standalone review run never flips or merges\n   (`doctrine\u002Fhuman-gates.md`).\n\n## Observations\n\nIn a repository with a spec bundle under `specs\u002F`, record anything noticed\noutside the branch's scope (complexity growth, outdated patterns, tooling or\ndoctrine gaps) as one fragment per observation through\n`scripts\u002Fobs-record.sh --slug \u003Ctopic> --scope \u003Crepo> --text '\u003Cobservation>'`\n(resolved under the planwright root). Before committing fragments, review\nthem with the spec lens set plus a duplication check against the store, each\nquoted message, named test, figure and attribution read against its source;\nrecord every disposition, and a refused record's recurrence or withdrawal, in\nthe audit record, correcting or withdrawing a falsified fragment. Commit them\nwithin the pass (the action commit, or a chore commit); never leave the tree\ndirty at a pass boundary, and surface a non-zero helper exit. Do not act on\nobservations during the pass; they seed `\u002Fspec-draft` (REQ-E2.1, REQ-H1.6).\n\n## Maintenance\n\nAfter the pass completes (or halts), compare these instructions against the\nresolved doctrine docs listed above (REQ-B3.2, D-42). If a concept this skill\nnames has changed meaning, gained or lost a step, or moved between docs,\nrecord a drift observation (`scripts\u002Fobs-record.sh --slug skill-drift\n--scope \u003Crepo> --text 'skill-drift(self-review): \u003Cwhat>'`, the text keeping\nthat prefix; without `specs\u002F`, surface the drift to the user instead),\nreview the fragment as the Observations step does, commit it as its own chore\ncommit, tell the user what drifted, and surface a non-zero helper exit.\nDo not edit this skill or the doctrine docs to resolve the drift; `\u002Fspec-draft`\nowns folding drift into spec amendments.\n",{"name":5,"description":24,"argument-hint":25},"Gate-wired review pass of the current feature branch: Discovery Rigor fan-out, multi-pass validation, and act-then-review dispositions per the finding categorization. Standalone runs push and open or update a draft PR; pass --nested to stay local and return the audit record to the invoking skill.\n","[--nested]","main","f7b4996cafaef47ab9dfe92b4b47f4d2de424b5a","skills\u002Fself-review",0,"https:\u002F\u002Fgithub.com\u002Finkatze\u002Fplanwright","https:\u002F\u002Fgithub.com\u002Finkatze","https:\u002F\u002Fwww.inkatze.com","Software Engineer | Open Source n00b","2026-11-15 05:06:45",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add inkatze\u002Fplanwright --skill self-review",{"tool":41,"command":42},"bunx","bunx skills add inkatze\u002Fplanwright --skill self-review",{"tool":44,"command":45},"pnpm","pnpm dlx skills add inkatze\u002Fplanwright --skill self-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Finkatze\u002Fplanwright\u002Fblob\u002Fmain\u002Fskills\u002Fself-review\u002FSKILL.md",true,[],[50,56,62,67,74,81],{"skillNo":51,"name":52,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M75K7QKF8AFQ3JAJ1T67HT3F","demo","https:\u002F\u002Fgithub.com\u002Finkatze\u002Fplanwright\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fscript-invocation\u002Fsh-runs-bash\u002Fskills\u002Fdemo\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M75K7NKAW0V15FAVSWPVV4NZ","usage","https:\u002F\u002Fgithub.com\u002Finkatze\u002Fplanwright\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fscript-invocation\u002Fclean\u002Fskills\u002Fusage\u002FSKILL.md",[],[],{"skillNo":63,"name":52,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M75K7MD8DA50HDQ1NSTZCVXM","https:\u002F\u002Fgithub.com\u002Finkatze\u002Fplanwright\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fscript-invocation\u002Fclean\u002Fskills\u002Fdemo\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M75K7GFAKYN7X3QZ385P3V7H","tower","The front door: a standing conversational session that takes any ask about the repository in plain language, answers questions, and routes work that changes the repository per request onto visual flight (an isolated worker that lands a draft PR) or instrument flight (the spec pipeline), stating its grounds, with status on demand. Use it to start work without writing a spec first. It never edits the repository itself, never merges, never marks a PR ready, and never starts a kickoff.","https:\u002F\u002Fgithub.com\u002Finkatze\u002Fplanwright\u002Fblob\u002Fmain\u002Fskills\u002Ftower\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M75K7AVKFPCAKKX8BBK2HWWN","spec-walkthrough","Render a spec bundle (or a chosen slice) into a plain-language, didactic comprehension artifact a human reads and judges for themselves: an unaided cold read before kickoff, re-orientation mid-execution, or onboarding to a finished or abandoned spec. Standalone and strictly read-only: it renders any status, never edits, signs off, mutates the pipeline, or delivers a verdict of its own. The independent complement to \u002Fspec-kickoff's guided dialogue.","https:\u002F\u002Fgithub.com\u002Finkatze\u002Fplanwright\u002Fblob\u002Fmain\u002Fskills\u002Fspec-walkthrough\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M75K72A3397KH8GXFDJ0FCJM","spec-draft","Interactively elicit a four-file spec bundle (requirements.md, design.md, tasks.md, test-spec.md) at Status Draft on the spec's own branch, mining seed sources (pending notes, the observations log, transcripts) and citing them. Runs fold-detection against existing specs on every invocation and surfaces an extend recommendation instead of spinning a duplicate bundle. Commits the completed bundle (commit_on_draft opt-out); never pushes, never flips a spec to Ready.","https:\u002F\u002Fgithub.com\u002Finkatze\u002Fplanwright\u002Fblob\u002Fmain\u002Fskills\u002Fspec-draft\u002FSKILL.md",[],[]]