[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M757AFSATAAWHV6104K521EP":3,"skill-same:01M757AFSATAAWHV6104K521EP":58},{"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":35,"commitSha":36,"skillDirectory":37,"forksCount":38,"repositoryHtmlUrl":39,"repositoryHomepageUrl":6,"ownerHtmlUrl":40,"ownerBlogUrl":41,"ownerDescription":42,"updatedAt":43,"install":44,"resources":57},"01M757AFSATAAWHV6104K521EP","x-internal-summarize-epic",null,"Generates ai\u002Fmemory\u002Fepic-XXXX-summary.md from a completed epic's artifacts using structured header parsing","review-bench\u002Federcnj_ia-dev-environment","review-bench","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F286778065?v=4","01M7517F9NTEPDZDAXJBR30FWT","ReviewBench","01M7517FAC9F4P7TGWCNJ8VYVW",0,"MIT","https:\u002F\u002Fgithub.com\u002Freview-bench\u002Federcnj_ia-dev-environment\u002Fblob\u002Fmain\u002Fsrc\u002Ftest\u002Fresources\u002Fgolden\u002Fjava-spring\u002Fplatform-claude-code\u002F.claude\u002Fskills\u002Fx-internal-summarize-epic\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: x-internal-summarize-epic\ndescription: Generates ai\u002Fmemory\u002Fepic-XXXX-summary.md from a completed epic's artifacts using structured header parsing\nvisibility: internal\nuser-invocable: false\nmodel: haiku\nrequires-capabilities: [governance.ai-memory]\nallowed-tools: [Read, Write, Bash, Grep, Glob]\ncontext-budget: light\n---\n\n> 🔒 **INTERNAL SKILL** — Invoked only by other skills via the Skill tool. Not user-invocable.\n\n# x-internal-summarize-epic\n\nDeterministic memory summary generator for completed epics. Parses epic markdown with structured\nheader extraction (not free-form regex), composes `_TEMPLATE-EPIC-MEMORY-SUMMARY.md`, and writes\n`ai\u002Fmemory\u002Fepic-XXXX-summary.md` + updates `ai\u002Fmemory\u002F_index.yaml`.\n\n**Determinism contract:** Same inputs MUST produce bytewise-identical output across runs.\nUse explicit extraction rules; never introduce creative variance.\n\n## Triggers\n\nInvoked by `x-implement-epic` Phase 5 (Rule 33):\n\n    Skill(skill: \"x-internal-summarize-epic\", args: \"--epic-id EPIC-XXXX\")\n\n## Parameters\n\n| Flag | Type | Default | Description |\n| :--- | :--- | :--- | :--- |\n| `--epic-id` | `EPIC-\\d{4}` | required | Epic identifier |\n| `--out-dir` | path | `ai\u002Fmemory\u002F` | Output directory override (tests) |\n| `--dry-run` | bool | false | Print content without writing files or updating index |\n| `--allow-legacy-fallback` | bool | false | For retro-seed (story-0075-0006) only — generates placeholder when v2 Decision sections absent |\n\n## Exit Codes\n\n| Exit | Code | Condition |\n| :--- | :--- | :--- |\n| 0 | OK | Summary written and index updated |\n| 1 | EPIC_NOT_FOUND | `ai\u002Fepics\u002Fepic-XXXX-*\u002F` absent |\n| 2 | SCHEMA_VIOLATION | Generated frontmatter fails `frontmatter-3.0.json` |\n| 3 | MEMORY_SUMMARY_TOO_LONG | Body exceeds 200 lines after composition |\n| 4 | EXTRACTION_FAILED | Section 6 (Decision Rationale) absent on v2 epic and `--allow-legacy-fallback` not set |\n| 5 | INDEX_LOCK_TIMEOUT | Failed to acquire flock on `ai\u002Fmemory\u002F_index.yaml` within 5s |\n| 6 | TEMPLATE_VERSION_MISMATCH | `summary-version` in template changed; mass-regeneration required |\n| 7 | MANUAL_REFINEMENT_PRESENT | Summary file contains `\u003C!-- manually-refined: -->` marker; abort to preserve human override |\n\n## Execution Protocol\n\n### Step 1 — Locate epic\n\n```bash\nfind ai\u002Fepics -maxdepth 1 -type d -name \"epic-XXXX-*\" | head -1\n```\n\nExit 1 `EPIC_NOT_FOUND` when no directory matches.\n\n### Step 2 — Check for manual refinement\n\nRead `ai\u002Fmemory\u002Fepic-XXXX-summary.md` if it exists. If it contains `\u003C!-- manually-refined:`, exit 7\n`MANUAL_REFINEMENT_PRESENT`.\n\n### Step 3 — Extract sections (structured parser — deterministic)\n\nRead `ai\u002Fepics\u002Fepic-XXXX-*\u002Fepic-XXXX.md`. Apply extraction rules below in order:\n\n| Target section | Source | Extraction rule |\n| :--- | :--- | :--- |\n| `## Why this epic existed` | `## 1. Visão & Problema` (v2) or `## Contexto` (v1) | First paragraph only; trim to 5 lines max |\n| `## Hypothesis tested` | `## 3. Hipótese & OKRs` (v2) | Extract `If...then...because` line; append `outcome: pending` if no completion report |\n| `## Decisions taken (with why)` | `## 8. Decision Rationale` or `## 6.*` sub-sections | Lines starting with `**Decisão:**`, `**Motivo:**`, `**Consequência:**`; if absent and `--allow-legacy-fallback` → placeholder |\n| `## Alternatives rejected (with why)` | Same source | Lines starting with `**Alternativa descartada:**` |\n| `## Reusable patterns produced` | Same source + keyword scan | Lines matching `\u002Fpadrão|pattern|convenção\u002Fi`; dedup |\n| `## Anti-patterns observed` | Same source + keyword scan | Lines matching `\u002Fanti-padrão|rejeitado|evitar\u002Fi`; dedup |\n| `## Links` | Deterministic filesystem + ADR frontmatter | Epic path, `adrs-referenced`, story list, `reports\u002F` dir |\n\n### Step 4 — Assemble frontmatter\n\nExtract deterministically:\n- `tags`: normalize headers to taxonomy IDs from `tags-catalog.md`\n- `capabilities-affected`: grep `requires-capabilities:` in story files\n- `rules-affected`: grep `Rule \\d+` in epic markdown\n- `adrs-referenced`: grep `ADR-\\d{4}` in epic markdown\n- `patterns-introduced` \u002F `antipatterns-rejected`: mirror Step 3 extraction\n- `dependencies-of` \u002F `dependencies-for`: grep `Depende de:` \u002F `Blocks:`\n\n### Step 5 — Validate and write\n\n1. Count lines in composed summary. If > 200 → exit 3 `MEMORY_SUMMARY_TOO_LONG`.\n2. Validate frontmatter against schema. If fails → exit 2 `SCHEMA_VIOLATION`.\n3. If `--dry-run`: print to stdout, exit 0.\n4. Write `{out-dir}\u002Fepic-XXXX-summary.md`.\n5. Acquire flock on `{out-dir}\u002F_index.yaml` (5s timeout → exit 5). Update entry:\n   - If entry exists: preserve `indexable` and `archived` flags; update `last-updated`.\n   - If new entry: add with `indexable: true`, `archived: false`.\n6. Release flock. Exit 0.\n\n## Integration Notes\n\n- Invoked by `x-implement-epic` Phase 5 (Rule 33 — MANDATORY TOOL CALL).\n- `--allow-legacy-fallback` is for `x-internal-summarize-epic` called from retro-seed (story-0075-0006);\n  normal Phase 5 invocations MUST NOT pass this flag.\n- Idempotent: re-execution regenerates the summary completely (no append).\n- Uses `_TEMPLATE-EPIC-MEMORY-SUMMARY.md` from `.claude\u002Ftemplates\u002F` (present when `governance.ai-memory` active).\n","> 🔒 **INTERNAL SKILL** — Invoked only by other skills via the Skill tool. Not user-invocable.\n\n# x-internal-summarize-epic\n\nDeterministic memory summary generator for completed epics. Parses epic markdown with structured\nheader extraction (not free-form regex), composes `_TEMPLATE-EPIC-MEMORY-SUMMARY.md`, and writes\n`ai\u002Fmemory\u002Fepic-XXXX-summary.md` + updates `ai\u002Fmemory\u002F_index.yaml`.\n\n**Determinism contract:** Same inputs MUST produce bytewise-identical output across runs.\nUse explicit extraction rules; never introduce creative variance.\n\n## Triggers\n\nInvoked by `x-implement-epic` Phase 5 (Rule 33):\n\n    Skill(skill: \"x-internal-summarize-epic\", args: \"--epic-id EPIC-XXXX\")\n\n## Parameters\n\n| Flag | Type | Default | Description |\n| :--- | :--- | :--- | :--- |\n| `--epic-id` | `EPIC-\\d{4}` | required | Epic identifier |\n| `--out-dir` | path | `ai\u002Fmemory\u002F` | Output directory override (tests) |\n| `--dry-run` | bool | false | Print content without writing files or updating index |\n| `--allow-legacy-fallback` | bool | false | For retro-seed (story-0075-0006) only — generates placeholder when v2 Decision sections absent |\n\n## Exit Codes\n\n| Exit | Code | Condition |\n| :--- | :--- | :--- |\n| 0 | OK | Summary written and index updated |\n| 1 | EPIC_NOT_FOUND | `ai\u002Fepics\u002Fepic-XXXX-*\u002F` absent |\n| 2 | SCHEMA_VIOLATION | Generated frontmatter fails `frontmatter-3.0.json` |\n| 3 | MEMORY_SUMMARY_TOO_LONG | Body exceeds 200 lines after composition |\n| 4 | EXTRACTION_FAILED | Section 6 (Decision Rationale) absent on v2 epic and `--allow-legacy-fallback` not set |\n| 5 | INDEX_LOCK_TIMEOUT | Failed to acquire flock on `ai\u002Fmemory\u002F_index.yaml` within 5s |\n| 6 | TEMPLATE_VERSION_MISMATCH | `summary-version` in template changed; mass-regeneration required |\n| 7 | MANUAL_REFINEMENT_PRESENT | Summary file contains `\u003C!-- manually-refined: -->` marker; abort to preserve human override |\n\n## Execution Protocol\n\n### Step 1 — Locate epic\n\n```bash\nfind ai\u002Fepics -maxdepth 1 -type d -name \"epic-XXXX-*\" | head -1\n```\n\nExit 1 `EPIC_NOT_FOUND` when no directory matches.\n\n### Step 2 — Check for manual refinement\n\nRead `ai\u002Fmemory\u002Fepic-XXXX-summary.md` if it exists. If it contains `\u003C!-- manually-refined:`, exit 7\n`MANUAL_REFINEMENT_PRESENT`.\n\n### Step 3 — Extract sections (structured parser — deterministic)\n\nRead `ai\u002Fepics\u002Fepic-XXXX-*\u002Fepic-XXXX.md`. Apply extraction rules below in order:\n\n| Target section | Source | Extraction rule |\n| :--- | :--- | :--- |\n| `## Why this epic existed` | `## 1. Visão & Problema` (v2) or `## Contexto` (v1) | First paragraph only; trim to 5 lines max |\n| `## Hypothesis tested` | `## 3. Hipótese & OKRs` (v2) | Extract `If...then...because` line; append `outcome: pending` if no completion report |\n| `## Decisions taken (with why)` | `## 8. Decision Rationale` or `## 6.*` sub-sections | Lines starting with `**Decisão:**`, `**Motivo:**`, `**Consequência:**`; if absent and `--allow-legacy-fallback` → placeholder |\n| `## Alternatives rejected (with why)` | Same source | Lines starting with `**Alternativa descartada:**` |\n| `## Reusable patterns produced` | Same source + keyword scan | Lines matching `\u002Fpadrão|pattern|convenção\u002Fi`; dedup |\n| `## Anti-patterns observed` | Same source + keyword scan | Lines matching `\u002Fanti-padrão|rejeitado|evitar\u002Fi`; dedup |\n| `## Links` | Deterministic filesystem + ADR frontmatter | Epic path, `adrs-referenced`, story list, `reports\u002F` dir |\n\n### Step 4 — Assemble frontmatter\n\nExtract deterministically:\n- `tags`: normalize headers to taxonomy IDs from `tags-catalog.md`\n- `capabilities-affected`: grep `requires-capabilities:` in story files\n- `rules-affected`: grep `Rule \\d+` in epic markdown\n- `adrs-referenced`: grep `ADR-\\d{4}` in epic markdown\n- `patterns-introduced` \u002F `antipatterns-rejected`: mirror Step 3 extraction\n- `dependencies-of` \u002F `dependencies-for`: grep `Depende de:` \u002F `Blocks:`\n\n### Step 5 — Validate and write\n\n1. Count lines in composed summary. If > 200 → exit 3 `MEMORY_SUMMARY_TOO_LONG`.\n2. Validate frontmatter against schema. If fails → exit 2 `SCHEMA_VIOLATION`.\n3. If `--dry-run`: print to stdout, exit 0.\n4. Write `{out-dir}\u002Fepic-XXXX-summary.md`.\n5. Acquire flock on `{out-dir}\u002F_index.yaml` (5s timeout → exit 5). Update entry:\n   - If entry exists: preserve `indexable` and `archived` flags; update `last-updated`.\n   - If new entry: add with `indexable: true`, `archived: false`.\n6. Release flock. Exit 0.\n\n## Integration Notes\n\n- Invoked by `x-implement-epic` Phase 5 (Rule 33 — MANDATORY TOOL CALL).\n- `--allow-legacy-fallback` is for `x-internal-summarize-epic` called from retro-seed (story-0075-0006);\n  normal Phase 5 invocations MUST NOT pass this flag.\n- Idempotent: re-execution regenerates the summary completely (no append).\n- Uses `_TEMPLATE-EPIC-MEMORY-SUMMARY.md` from `.claude\u002Ftemplates\u002F` (present when `governance.ai-memory` active).\n",{"name":5,"model":24,"visibility":25,"description":7,"allowed-tools":26,"context-budget":32,"user-invocable":20,"requires-capabilities":33},"haiku","internal",[27,28,29,30,31],"Read","Write","Bash","Grep","Glob","light",[34],"governance.ai-memory","main","952a630c6f38d193a349d86fa18db1de8843e837","src\u002Ftest\u002Fresources\u002Fgolden\u002Fjava-spring\u002Fplatform-claude-code\u002F.claude\u002Fskills\u002Fx-internal-summarize-epic",1,"https:\u002F\u002Fgithub.com\u002Freview-bench\u002Federcnj_ia-dev-environment","https:\u002F\u002Fgithub.com\u002Freview-bench","https:\u002F\u002Freview-bench.ai","An open benchmark for AI code review.","2026-10-27 06:56:37",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add review-bench\u002Federcnj_ia-dev-environment --skill x-internal-summarize-epic",{"tool":50,"command":51},"bunx","bunx skills add review-bench\u002Federcnj_ia-dev-environment --skill x-internal-summarize-epic",{"tool":53,"command":54},"pnpm","pnpm dlx skills add review-bench\u002Federcnj_ia-dev-environment --skill x-internal-summarize-epic","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Freview-bench\u002Federcnj_ia-dev-environment\u002Fblob\u002Fmain\u002Fsrc\u002Ftest\u002Fresources\u002Fgolden\u002Fjava-spring\u002Fplatform-claude-code\u002F.claude\u002Fskills\u002Fx-internal-summarize-epic\u002FSKILL.md",true,[],[59,66,73,80,87,94],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M757M8J48TQ1Y3X25GSJBXAS","x-parallel-eval","Detects and classifies file-collision risks between work units (tasks, stories, or epic phases) before parallel execution. Reads ## File Footprint blocks produced by x-task-plan \u002F x-story-plan, applies the parallelism-heuristics knowledge pack (hard \u002F regen \u002F soft categories + hotspot overrides), and emits a collision matrix + serialization recommendation in Markdown (default) or JSON.","https:\u002F\u002Fgithub.com\u002Freview-bench\u002Federcnj_ia-dev-environment\u002Fblob\u002Fmain\u002Fsrc\u002Ftest\u002Fresources\u002Fgolden\u002Fx-parallel-eval\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M757M57XMR9546S69466HDWT","parallelism-heuristics","Canonical catalog of file-collision heuristics for parallel task, story, and epic execution. Defines the File Footprint block format, the three Conflict Categories (hard \u002F regen \u002F soft), a hotspot list of high-contention paths, and the degrade-with-warning policy. Consumed by x-task-plan, x-story-plan, x-epic-map, x-parallel-eval, and x-dev-*-implement.","https:\u002F\u002Fgithub.com\u002Freview-bench\u002Federcnj_ia-dev-environment\u002Fblob\u002Fmain\u002Fsrc\u002Ftest\u002Fresources\u002Fgolden\u002Fparallelism-heuristics\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M757M11SZ8P1VCQABT08QVYA","x-watch-pr-ci","Polls a PR's CI checks and Copilot review status, blocking until checks complete or timeout. Returns one of 8 stable exit codes (SUCCESS=0, CI_PENDING_PROCEED=10, CI_FAILED=20, TIMEOUT=30, PR_ALREADY_MERGED=40, NO_CI_CONFIGURED=50, PR_CLOSED=60, PR_NOT_FOUND=70). Writes a versioned state-file for session resume.","https:\u002F\u002Fgithub.com\u002Freview-bench\u002Federcnj_ia-dev-environment\u002Fblob\u002Fmain\u002Fsrc\u002Ftest\u002Fresources\u002Fgolden\u002Fjava-spring\u002Fplatform-claude-code\u002F.claude\u002Fskills\u002Fx-watch-pr-ci\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M757KW53K8KFPGADFB4PH949","x-validate-docs","Documentation freshness gate: validates 6 dimensions (readme, api-specs, grpc-proto, adr, skill-docs, system-architecture) against code changes in a PR. Stack-aware — only validates targets declared\u002Fauto-detected from ProjectConfig.documentation.targets. Returns exit non-zero on staleness; produces structured report.","https:\u002F\u002Fgithub.com\u002Freview-bench\u002Federcnj_ia-dev-environment\u002Fblob\u002Fmain\u002Fsrc\u002Ftest\u002Fresources\u002Fgolden\u002Fjava-spring\u002Fplatform-claude-code\u002F.claude\u002Fskills\u002Fx-validate-docs\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M757KQZHSA10MKC0CR571D60","x-update-system-architecture","Incrementally updates docs\u002Farchitecture\u002Fsystem.md after an epic completes. Appends new entries to the Decision Log (§11) using x-internal-write-report --append (dedup by ## ID: marker) and surgically inserts component\u002Fintegration changes into sections 1-10 via Edit. Idempotent: re-running with the same epic produces a byte-identical system.md.","https:\u002F\u002Fgithub.com\u002Freview-bench\u002Federcnj_ia-dev-environment\u002Fblob\u002Fmain\u002Fsrc\u002Ftest\u002Fresources\u002Fgolden\u002Fjava-spring\u002Fplatform-claude-code\u002F.claude\u002Fskills\u002Fx-update-system-architecture\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M757KKBT5Q1SVF8DMJBVF46M","x-update-architecture","Incrementally updates the service architecture document with changes from architecture plans. Adds new components, integrations, flows, and ADR references without rewriting existing content. Use after implementation to keep architecture documentation current.","https:\u002F\u002Fgithub.com\u002Freview-bench\u002Federcnj_ia-dev-environment\u002Fblob\u002Fmain\u002Fsrc\u002Ftest\u002Fresources\u002Fgolden\u002Fjava-spring\u002Fplatform-claude-code\u002F.claude\u002Fskills\u002Fx-update-architecture\u002FSKILL.md",[],[]]