[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78C072V7Q2ZRSPJSDJFS83C":3,"skill-same:01M78C072V7Q2ZRSPJSDJFS83C":60},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M78C072V7Q2ZRSPJSDJFS83C","audit-task-status",null,"Reconciles Forge Flow task and epic files with the task registry (docs\u002Ftasks\u002Fregistry.json, the single source of truth): fixes status drift in task-file frontmatter and epic files, and surfaces registry tasks with no body file on disk. Use when task or epic statuses look out of sync with the registry (\"the epic file is stale\", \"are the statuses in sync\"), after a batch of merges or completions, or as a pre-release consistency check.","rynhardt81\u002FforgeFlow","rynhardt81","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F52700299?v=4","01M78BZMY2RF5TVDY59XT67ZB6","RjvR","01M78BZMYQ2AJGBHKAT0M1Q2ZB",0,"MIT","https:\u002F\u002Fgithub.com\u002Frynhardt81\u002FforgeFlow\u002Fblob\u002Fmain\u002Fskills\u002Faudit-task-status\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: audit-task-status\ndescription: >\n  Reconciles Forge Flow task and epic files with the task registry\n  (docs\u002Ftasks\u002Fregistry.json, the single source of truth): fixes status drift in\n  task-file frontmatter and epic files, and surfaces registry tasks with no body\n  file on disk. Use when task or epic statuses look out of sync with the registry\n  (\"the epic file is stale\", \"are the statuses in sync\"), after a batch of\n  merges or completions, or as a pre-release consistency check.\n---\n\n# Audit & align task status\n\nMakes task-file frontmatter and epic files tell the same truth as `docs\u002Ftasks\u002Fregistry.json`, and reports registry-health gaps (tasks with no body file). The `forge` CLI is the only sanctioned writer of the registry; never hand-edit it.\n\n## Index\n\n| File or section | Read when… |\n|---|---|\n| `WHY.md` | Explaining to the user why epic files drifted, or deciding which of the three layers to trust |\n| The authority rule (below) | Before any edit — which layer wins |\n| Workflow (below) | Every invocation — steps 1–5 |\n| `scripts\u002Faudit_status.py` | **Run** it (step 2 and step 5) — read-only detector |\n| What \"aligned\" means (below) | Deciding you are done |\n\n## The authority rule\n\n**The registry is ground truth. Always reconcile the other layers TO it, never the\nreverse.** If a task file or epic file disagrees with the registry, the registry\nwins — fix the doc. The only exception is if the registry itself looks wrong (a\nstatus that contradicts a merged PR); in that case stop and surface it to the user,\nbecause changing the registry means a `forge task` state transition, not a doc edit.\n\n## Workflow\n\n### 1. Sync the machine layer (registry ↔ task-file frontmatter)\n\nRun the consistency hook with `--fix` — it auto-corrects trivial registry\u002Ftask-file\ndrift and reports anything it can't fix:\n\n```bash\npython3 .claude\u002Fhooks\u002Fforge\u002Fconsistency-banner.py --fix --json\n```\n\n`rc=0` with no findings means layers 1↔2 agree. If it reports blocking drift it\ncan't auto-fix, resolve that first (it usually means a task file was hand-edited to\na status the registry disagrees with — fix the file to match the registry).\n\n**Do not trust `rc=0` alone as proof of full alignment** — this hook only checks\nregistry↔task-file. It is blind to epic files. The next steps are where the value is.\n\n### 2. Independently verify task-file frontmatter (don't just trust the hook)\n\nThe hook is informational and has been wrong before. Confirm independently — for\nevery registry task, the body file's `status:` frontmatter must equal the registry\nstatus. Use the bundled script:\n\n```bash\npython3 .claude\u002Fskills\u002Faudit-task-status\u002Fscripts\u002Faudit_status.py\n```\n\nIt reads the registry, locates each task's body file, and reports three things:\n- **task-file status mismatches** (frontmatter `status:` ≠ registry status),\n- **epic-file drift** (see step 3),\n- **registry tasks with no body file on disk**.\n\nRead its output before editing anything — it tells you the exact scope.\n\n### 3. Reconcile epic files (the layer the framework forgets)\n\nFor each epic with open or recently-changed work, the epic file (`\u003Cepic>\u002F\u003Cepic>.md`)\nhas up to four things that drift — the bundled script reports the first three; you\nverify and fix:\n\n- **The progress counter** — a prose line like `**Tasks:** N total — M completed, …`.\n  Recompute from the registry and rewrite it. Refresh any \"as of \u003Cdate>\" stamp.\n- **The per-task status — in TWO idioms**, depending on the epic:\n  - *Pipe tables*: `| T### | … | \u003Cstatus> | … |`. Column position varies between\n    epics (some add columns before `Status`), so locate the `Status` header rather\n    than counting columns. Cells may carry annotations after the status\n    (`completed (PR #N)`, `closed — phantom`). Fix any cell whose leading status\n    token disagrees with the registry.\n  - *Checklists*: `- [x] T###: … ✅` \u002F `- [~] T###a: … superseded`. The\n    checkbox alone is ambiguous, so the script only flags a row when an explicit\n    status word in the line contradicts the registry. Verify these by hand — a\n    `[x]` next to a task the registry calls `superseded` is real drift; a `[x]`\n    that's merely annotated `(commit pending)` while the registry says `completed`\n    is cosmetic, not a status mismatch.\n- **The prose `**Status:**` header** (and the epic's `status:` frontmatter). An epic\n  whose every task is terminal (completed\u002Fsuperseded\u002Fclosed) but whose prose header\n  still says `in_progress`\u002F`pending` is contradicting itself — fix the header to\n  match the rollup. (This is distinct from the counter; an epic can have a right\n  counter and a stale header, or vice-versa.)\n\n**Watch for internal contradictions** — a counter saying \"1 ready\" while the table\nrow for the same task says `completed`, or a `**Status:** in_progress` header on an\nall-terminal epic. Make every layer (header, counter, rows) AND the registry agree.\n\n**Scope discipline — do NOT backfill missing table rows by default.** Epic files\nroutinely list only a subset of their tasks (the headline ones); the registry holds\nthe complete per-task detail. Many Forge epic files explicitly say \"registry is\nauthoritative — counts drift as tasks are added\". Adding a row for every\nregistry task is a large rewrite that fights the file's design. Fix the *counters*\nand the *statuses of rows that already exist*; only backfill individual rows if the\nuser explicitly asks. When you skip a backfill, say so plainly (e.g. \"counter now\nreflects all N tasks; 35 of them don't have individual table rows, by design\").\n\n### 4. Report the registry-health extras\n\nBeyond status, surface (don't fix unless asked):\n\n- **Tasks with no body file** — registry entries created with `--no-file`, or whose body was later deleted\u002Fmoved. The\n  script lists them. These aren't a *status* problem, but they break resume\u002Flock for\n  those tasks. Offer the fix rather than doing it silently:\n  `python3 .claude\u002Fscripts\u002Fforge\u002Fforge.py task reconcile-files` (dry-run) →\n  `--apply` to create stub bodies.\n\n### 5. Verify and commit\n\nRe-run the audit script — every layer should now report **0 mismatches**. Re-run\nthe consistency hook (`rc=0`) to confirm your epic-file edits didn't disturb the\nmachine layer (they shouldn't — you only touched epic prose). Then commit the epic\nfiles (and any task files the hook fixed) together:\n\n```\ndocs(epics): align \u003Cepics> statuses with registry\n```\n\nSpell out in the commit what drifted and what you deliberately left (e.g. \"fixed\ncounters + N stale rows + the T### contradiction; did NOT backfill the M missing\nrows — epic defers per-task detail to the registry\").\n\n## What \"aligned\" means (the done condition)\n\n- Registry ↔ task-file frontmatter: 0 status mismatches.\n- Every epic-file counter matches the registry's completed\u002Ftotal for that epic.\n- Every epic-file row that exists (table OR checklist) matches the registry status.\n- Every epic's prose `**Status:**` header agrees with its task rollup.\n- No internal contradictions within an epic file (header vs counter vs rows).\n- Registry-tasks-without-body-files reported (and fixed only if the user opted in).\n\n## Verify the script's findings — it is a first pass, not an oracle\n\nThe bundled `audit_status.py` is a fast detector, but it resolves body files by the\nregistry `file` field with a glob fallback, and parses heterogeneous human prose —\nso it can mis-report at the edges. Treat its output as candidates to confirm, not\ngospel. Two false-positive classes it has produced before (now guarded, but stay\nalert): a `T###-*.md` file outside a `\u002Ftasks\u002F`-or-`\u002Forphan\u002F` dir (e.g. a\n`docs\u002Fdebug\u002F` triage note) shadowing the real body file; and a cosmetic annotation\n(`[x] … (commit pending)`) read as a status. Before you edit anything, spot-check\neach flagged item against the registry and the actual file line — the same\nempirical-premise discipline any audit finding deserves.\n\n## Notes\n\n- This is a deterministic audit, not a judgment call — the registry decides every\n  status. The only place judgment enters is the scope of epic-file backfill (step 3)\n  and whether to create missing body files (step 4); both default to \"ask, don't\n  silently expand scope\".\n- The bundled `scripts\u002Faudit_status.py` does the read-only detection; the fixes are\n  small targeted edits you apply by hand (epic prose is human-authored — an\n  Edit-per-fix keeps the change reviewable). Don't try to regex-rewrite whole tables.\n\n---\n\n**Project-specific overrides:** if `SKILL.local.md` exists in this directory, read it — it is consumer-owned, survives framework refresh, and **wins on conflict**. A sidecar that relaxes a gate defined above must state how to prove the gate is wrong in that case. Doctrine: `rules\u002Fframework-vs-project-root.md`.\n","# Audit & align task status\n\nMakes task-file frontmatter and epic files tell the same truth as `docs\u002Ftasks\u002Fregistry.json`, and reports registry-health gaps (tasks with no body file). The `forge` CLI is the only sanctioned writer of the registry; never hand-edit it.\n\n## Index\n\n| File or section | Read when… |\n|---|---|\n| `WHY.md` | Explaining to the user why epic files drifted, or deciding which of the three layers to trust |\n| The authority rule (below) | Before any edit — which layer wins |\n| Workflow (below) | Every invocation — steps 1–5 |\n| `scripts\u002Faudit_status.py` | **Run** it (step 2 and step 5) — read-only detector |\n| What \"aligned\" means (below) | Deciding you are done |\n\n## The authority rule\n\n**The registry is ground truth. Always reconcile the other layers TO it, never the\nreverse.** If a task file or epic file disagrees with the registry, the registry\nwins — fix the doc. The only exception is if the registry itself looks wrong (a\nstatus that contradicts a merged PR); in that case stop and surface it to the user,\nbecause changing the registry means a `forge task` state transition, not a doc edit.\n\n## Workflow\n\n### 1. Sync the machine layer (registry ↔ task-file frontmatter)\n\nRun the consistency hook with `--fix` — it auto-corrects trivial registry\u002Ftask-file\ndrift and reports anything it can't fix:\n\n```bash\npython3 .claude\u002Fhooks\u002Fforge\u002Fconsistency-banner.py --fix --json\n```\n\n`rc=0` with no findings means layers 1↔2 agree. If it reports blocking drift it\ncan't auto-fix, resolve that first (it usually means a task file was hand-edited to\na status the registry disagrees with — fix the file to match the registry).\n\n**Do not trust `rc=0` alone as proof of full alignment** — this hook only checks\nregistry↔task-file. It is blind to epic files. The next steps are where the value is.\n\n### 2. Independently verify task-file frontmatter (don't just trust the hook)\n\nThe hook is informational and has been wrong before. Confirm independently — for\nevery registry task, the body file's `status:` frontmatter must equal the registry\nstatus. Use the bundled script:\n\n```bash\npython3 .claude\u002Fskills\u002Faudit-task-status\u002Fscripts\u002Faudit_status.py\n```\n\nIt reads the registry, locates each task's body file, and reports three things:\n- **task-file status mismatches** (frontmatter `status:` ≠ registry status),\n- **epic-file drift** (see step 3),\n- **registry tasks with no body file on disk**.\n\nRead its output before editing anything — it tells you the exact scope.\n\n### 3. Reconcile epic files (the layer the framework forgets)\n\nFor each epic with open or recently-changed work, the epic file (`\u003Cepic>\u002F\u003Cepic>.md`)\nhas up to four things that drift — the bundled script reports the first three; you\nverify and fix:\n\n- **The progress counter** — a prose line like `**Tasks:** N total — M completed, …`.\n  Recompute from the registry and rewrite it. Refresh any \"as of \u003Cdate>\" stamp.\n- **The per-task status — in TWO idioms**, depending on the epic:\n  - *Pipe tables*: `| T### | … | \u003Cstatus> | … |`. Column position varies between\n    epics (some add columns before `Status`), so locate the `Status` header rather\n    than counting columns. Cells may carry annotations after the status\n    (`completed (PR #N)`, `closed — phantom`). Fix any cell whose leading status\n    token disagrees with the registry.\n  - *Checklists*: `- [x] T###: … ✅` \u002F `- [~] T###a: … superseded`. The\n    checkbox alone is ambiguous, so the script only flags a row when an explicit\n    status word in the line contradicts the registry. Verify these by hand — a\n    `[x]` next to a task the registry calls `superseded` is real drift; a `[x]`\n    that's merely annotated `(commit pending)` while the registry says `completed`\n    is cosmetic, not a status mismatch.\n- **The prose `**Status:**` header** (and the epic's `status:` frontmatter). An epic\n  whose every task is terminal (completed\u002Fsuperseded\u002Fclosed) but whose prose header\n  still says `in_progress`\u002F`pending` is contradicting itself — fix the header to\n  match the rollup. (This is distinct from the counter; an epic can have a right\n  counter and a stale header, or vice-versa.)\n\n**Watch for internal contradictions** — a counter saying \"1 ready\" while the table\nrow for the same task says `completed`, or a `**Status:** in_progress` header on an\nall-terminal epic. Make every layer (header, counter, rows) AND the registry agree.\n\n**Scope discipline — do NOT backfill missing table rows by default.** Epic files\nroutinely list only a subset of their tasks (the headline ones); the registry holds\nthe complete per-task detail. Many Forge epic files explicitly say \"registry is\nauthoritative — counts drift as tasks are added\". Adding a row for every\nregistry task is a large rewrite that fights the file's design. Fix the *counters*\nand the *statuses of rows that already exist*; only backfill individual rows if the\nuser explicitly asks. When you skip a backfill, say so plainly (e.g. \"counter now\nreflects all N tasks; 35 of them don't have individual table rows, by design\").\n\n### 4. Report the registry-health extras\n\nBeyond status, surface (don't fix unless asked):\n\n- **Tasks with no body file** — registry entries created with `--no-file`, or whose body was later deleted\u002Fmoved. The\n  script lists them. These aren't a *status* problem, but they break resume\u002Flock for\n  those tasks. Offer the fix rather than doing it silently:\n  `python3 .claude\u002Fscripts\u002Fforge\u002Fforge.py task reconcile-files` (dry-run) →\n  `--apply` to create stub bodies.\n\n### 5. Verify and commit\n\nRe-run the audit script — every layer should now report **0 mismatches**. Re-run\nthe consistency hook (`rc=0`) to confirm your epic-file edits didn't disturb the\nmachine layer (they shouldn't — you only touched epic prose). Then commit the epic\nfiles (and any task files the hook fixed) together:\n\n```\ndocs(epics): align \u003Cepics> statuses with registry\n```\n\nSpell out in the commit what drifted and what you deliberately left (e.g. \"fixed\ncounters + N stale rows + the T### contradiction; did NOT backfill the M missing\nrows — epic defers per-task detail to the registry\").\n\n## What \"aligned\" means (the done condition)\n\n- Registry ↔ task-file frontmatter: 0 status mismatches.\n- Every epic-file counter matches the registry's completed\u002Ftotal for that epic.\n- Every epic-file row that exists (table OR checklist) matches the registry status.\n- Every epic's prose `**Status:**` header agrees with its task rollup.\n- No internal contradictions within an epic file (header vs counter vs rows).\n- Registry-tasks-without-body-files reported (and fixed only if the user opted in).\n\n## Verify the script's findings — it is a first pass, not an oracle\n\nThe bundled `audit_status.py` is a fast detector, but it resolves body files by the\nregistry `file` field with a glob fallback, and parses heterogeneous human prose —\nso it can mis-report at the edges. Treat its output as candidates to confirm, not\ngospel. Two false-positive classes it has produced before (now guarded, but stay\nalert): a `T###-*.md` file outside a `\u002Ftasks\u002F`-or-`\u002Forphan\u002F` dir (e.g. a\n`docs\u002Fdebug\u002F` triage note) shadowing the real body file; and a cosmetic annotation\n(`[x] … (commit pending)`) read as a status. Before you edit anything, spot-check\neach flagged item against the registry and the actual file line — the same\nempirical-premise discipline any audit finding deserves.\n\n## Notes\n\n- This is a deterministic audit, not a judgment call — the registry decides every\n  status. The only place judgment enters is the scope of epic-file backfill (step 3)\n  and whether to create missing body files (step 4); both default to \"ask, don't\n  silently expand scope\".\n- The bundled `scripts\u002Faudit_status.py` does the read-only detection; the fixes are\n  small targeted edits you apply by hand (epic prose is human-authored — an\n  Edit-per-fix keeps the change reviewable). Don't try to regex-rewrite whole tables.\n\n---\n\n**Project-specific overrides:** if `SKILL.local.md` exists in this directory, read it — it is consumer-owned, survives framework refresh, and **wins on conflict**. A sidecar that relaxes a gate defined above must state how to prove the gate is wrong in that case. Doctrine: `rules\u002Fframework-vs-project-root.md`.\n",{"name":5,"description":7},"main","51a4b0dd2ff140f5a7ccf57daaa79defe2489745","skills\u002Faudit-task-status","https:\u002F\u002Fgithub.com\u002Frynhardt81\u002FforgeFlow","https:\u002F\u002Fgithub.com\u002Frynhardt81","2026-10-23 13:56:45",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add rynhardt81\u002FforgeFlow --skill audit-task-status",{"tool":36,"command":37},"bunx","bunx skills add rynhardt81\u002FforgeFlow --skill audit-task-status",{"tool":39,"command":40},"pnpm","pnpm dlx skills add rynhardt81\u002FforgeFlow --skill audit-task-status","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Frynhardt81\u002FforgeFlow\u002Fblob\u002Fmain\u002Fskills\u002Faudit-task-status\u002FSKILL.md",true,[44,50,56],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"evals\u002Fevals.json","REFERENCE","参考文档",1577,"https:\u002F\u002Fgithub.com\u002Frynhardt81\u002FforgeFlow\u002Fblob\u002Fmain\u002Fskills\u002Faudit-task-status\u002Fevals\u002Fevals.json",{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"scripts\u002Faudit_status.py","SCRIPT","脚本",25403,"https:\u002F\u002Fgithub.com\u002Frynhardt81\u002FforgeFlow\u002Fblob\u002Fmain\u002Fskills\u002Faudit-task-status\u002Fscripts\u002Faudit_status.py",{"path":57,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":58,"sourceHtmlUrl":59},"WHY.md",1124,"https:\u002F\u002Fgithub.com\u002Frynhardt81\u002FforgeFlow\u002Fblob\u002Fmain\u002Fskills\u002Faudit-task-status\u002FWHY.md",[61,68,75,82,89,96],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M78C3X48Y2TPS649BRYJZWT3","wizard","Generates an interactive bash wizard that walks a human through steps only they can perform — opens each URL, says what to click and copy, captures values (hidden entry for secrets), writes .env and GitHub secrets, confirms before irreversible actions. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.","https:\u002F\u002Fgithub.com\u002Frynhardt81\u002FforgeFlow\u002Fblob\u002Fmain\u002Fskills\u002Fwizard\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M78C3RJ1F82TBBK398FR824Q","vet-idea","Vets an idea, decision, or plan BEFORE it is built. Runs a single model through five fixed adversarial advisor roles, a peer-review pass, and a chairman synthesis that emits a halt-capable GO \u002F NO-GO \u002F RECONSIDER verdict. Advisory and non-mutating — outputs a report, never writes task state. Use when an idea, feature, or costly hard-to-reverse decision is of uncertain worth and the question is whether to build it at all. NOT FOR settled work (bug fixes, approved features) or for shaping how to build it (the ISA Interview workflow).","https:\u002F\u002Fgithub.com\u002Frynhardt81\u002FforgeFlow\u002Fblob\u002Fmain\u002Fskills\u002Fvet-idea\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M78C3JXH3ABXMDK2ZESXYM3R","triage-incident","Production incident triage — from \"something is broken for users\" to fixed, verified, and learned-from. Pulls the error signal (Sentry\u002Flogs\u002Fuser report), reproduces before touching code, routes the fix through \u002Ffix-bug's prod fast path, and closes with a postmortem entry. Use when something is broken for users in production — an outage, data corruption, a Sentry spike, or a crash-rate alert. NOT FOR bugs found in development (use \u002Ffix-bug directly) or CI failures (use \u002Fdiagnose-ci).","https:\u002F\u002Fgithub.com\u002Frynhardt81\u002FforgeFlow\u002Fblob\u002Fmain\u002Fskills\u002Ftriage-incident\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M78C3F8RA1PSYSV5KR6FYYDW","setup-review-bot","Configures a repo's AI code reviewers — the post-PR mention bot and the pre-push local reviewer — and writes the AGENTS.md the reviewers read. Interviews the user for what the reviewer should weight, then sets git config forge.reviewBot \u002F forge.localReview and populates AGENTS.md at the project root. Use when a repo has no reviewer configured, when review findings are consistently off-target, or when onboarding a new project.","https:\u002F\u002Fgithub.com\u002Frynhardt81\u002FforgeFlow\u002Fblob\u002Fmain\u002Fskills\u002Fsetup-review-bot\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M78C3AFB8Y33VNN47DAB0QKJ","security-review","Portable security review for a feature, endpoint, or change before it ships. Orchestrates the existing OWASP review (@security-boss) and secrets scan (security_secrets validator), then adds the pass they miss — an explicit business-logic-flaw walkthrough (IDOR, race\u002FTOCTOU, state-machine bypass, privilege escalation, price\u002Fquantity tampering). Advisory and non-mutating — produces a findings report; real findings are filed as tasks. Use when a change touching money, access control, or multi-step state is about to ship, or when the auth looks fine but the flow could be abused. NOT FOR SAST or dependency-CVE scanning (consumer CI owns those).","https:\u002F\u002Fgithub.com\u002Frynhardt81\u002FforgeFlow\u002Fblob\u002Fmain\u002Fskills\u002Fsecurity-review\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":19},"01M78C36APGXG6WFF3DFEPPQMZ","run-epic","Autonomously drains every open task in a single epic. Pulls ready tasks via the forge CLI, executes the work in-context using the matching discipline (fix-bug \u002F new-feature \u002F refactor), files newly-discovered work as follow-up tasks without stopping to ask, opens a PR per completed task via \u002Fcreate-pr, and repeats until the epic has zero ready\u002Fin-progress\u002Fpending tasks. Use when the user says `\u002Frun-epic E##`, \"run epic autonomously\", \"finish all remaining tasks for epic X\", or \"drive epic X to completion\".","https:\u002F\u002Fgithub.com\u002Frynhardt81\u002FforgeFlow\u002Fblob\u002Fmain\u002Fskills\u002Frun-epic\u002FSKILL.md",[],[]]