[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M753Z8ZP6HFD9QSPKMKZ51K2":3,"skill-same:01M753Z8ZP6HFD9QSPKMKZ51K2":61},{"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":29,"commitSha":30,"skillDirectory":31,"forksCount":32,"repositoryHtmlUrl":33,"repositoryHomepageUrl":6,"ownerHtmlUrl":34,"ownerBlogUrl":35,"ownerDescription":36,"updatedAt":37,"install":38,"resources":50},"01M753Z8ZP6HFD9QSPKMKZ51K2","x-drive-tdd",null,"Executes systematic Red-Green-Refactor TDD cycles for a task. Reads the task plan generated by x-plan-task, runs each cycle in TPP order, validates RED\u002FGREEN\u002FREFACTOR phases, delegates atomic commits to x-commit-changes with TDD tags, and supports resume and dry-run.","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-event-driven\u002F.claude\u002Fskills\u002Fx-drive-tdd\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: x-drive-tdd\ndescription: \"Executes systematic Red-Green-Refactor TDD cycles for a task. Reads the task plan generated by x-plan-task, runs each cycle in TPP order, validates RED\u002FGREEN\u002FREFACTOR phases, delegates atomic commits to x-commit-changes with TDD tags, and supports resume and dry-run.\"\nuser-invocable: true\nallowed-tools: Bash, Read, Write, Edit, Grep, Glob, Skill\nargument-hint: \"TASK-XXXX-YYYY-NNN [--from-cycle N] [--dry-run] [--warn-only-coverage] [--orchestrated]\"\ncontext-budget: light\nrequires-capabilities: []\n---\n\n## Global Output Policy\n\n- **Language**: English ONLY.\n- **Tone**: Technical, Direct, and Concise.\n- **Efficiency**: Remove all conversational fillers and greetings to save tokens.\n\n# Skill: TDD Execution with Atomic Cycles (slim — ADR-0012)\n\nExecutes systematic Red-Green-Refactor TDD cycles for {{PROJECT_NAME}} tasks. Reads the task plan produced by `\u002Fx-plan-task`, iterates TDD cycles in strict Transformation Priority Premise (TPP) order, validates each phase (RED must fail, GREEN must pass with minimum code, REFACTOR must preserve behavior), and delegates atomic commits to `x-commit-changes` with TDD tags (`[TDD:RED]`, `[TDD:GREEN]`, `[TDD:REFACTOR]`). Enforces RULE-008 (TDD Strict) and RULE-016 (Conventional Commits with Task ID).\n\n## Triggers\n\n- `\u002Fx-drive-tdd TASK-0029-0001-001` -- execute all TDD cycles for the task\n- `\u002Fx-drive-tdd TASK-0029-0001-001 --from-cycle 3` -- resume from cycle 3\n- `\u002Fx-drive-tdd TASK-0029-0001-001 --dry-run` -- list cycles without executing\n- `\u002Fx-drive-tdd TASK-0029-0001-001 --warn-only-coverage` -- legacy mode: sub-threshold coverage warns instead of blocks\n- `\u002Fx-drive-tdd TASK-0029-0001-001 --orchestrated` -- compact single-line cycle log (called from x-implement-story \u002F x-implement-epic)\n\n## Parameters\n\n| Parameter | Required | Default | Description |\n|-----------|----------|---------|-------------|\n| `TASK-ID` | Yes | — | Task identifier `TASK-XXXX-YYYY-NNN` (epic-story-task) |\n| `--from-cycle` | No | `1` | Resume from a specific cycle number (≥ 1). Cycles before this are skipped. |\n| `--dry-run` | No | `false` | List all cycles with descriptions and TPP levels; execute nothing. |\n| `--warn-only-coverage` | No | `false` | Legacy override (EPIC-0042). When set, coverage \u003C 95% line \u002F \u003C 90% branch emits WARNING instead of blocking the cycle. Default is blocking. |\n| `--orchestrated` | No | `false` | Emit one-line-per-cycle compact log. Passed explicitly by parent orchestrators (Story 0033-0003) so the decision is deterministic, not inferred. |\n\n## Output Contract\n\n- **Per-cycle artifacts:** each TDD cycle produces up to three atomic commits via `x-commit-changes` — `[TDD:RED]` (test-only), `[TDD:GREEN]` (minimum implementation), optional `[TDD:REFACTOR]` (if the task plan declares opportunities and tests still pass afterward).\n- **Final report to stdout:** cycles executed, commits created with SHA + message first-line per cycle, final coverage line\u002Fbranch %, warnings list. Under `--orchestrated`, one compact line per cycle: `Cycle {n}\u002F{m}: RED FAIL_EXPECTED GREEN PASS REFACTOR {skipped|PASS} → {sha7}`.\n- **Exit codes:** `0` on clean completion of all requested cycles; `1` on any ABORT condition (see `## Error Envelope`).\n- **Commit cadence:** each phase is one atomic commit; batching multiple phases into one commit is forbidden (see anti-patterns in `references\u002Ffull-protocol.md` §6).\n\n## Double-Loop Role\n\nThis skill is the **inner loop** of Double-Loop TDD. The outer loop (failing acceptance test) is driven by `x-implement-story` \u002F `x-implement-task`; each inner cycle produces one or more unit commits that compose toward the acceptance green. Full workflow diagram and Double-Loop context live in `references\u002Ffull-protocol.md` §5.\n\n## Error Envelope\n\n| Scenario | Action |\n|----------|--------|\n| Invalid task ID format (pattern mismatch) | ABORT: `\"Task ID invalid -- expected format: TASK-XXXX-YYYY-NNN\"` |\n| Task plan file not found | ABORT: `\"Task plan not found: task-plan-XXXX-YYYY-NNN.md\"` |\n| No `TDD Cycles` section in plan | ABORT: `\"No TDD Cycles section found in task plan\"` |\n| `--from-cycle N` out of range (N \u003C 1 or N > total cycles) | ABORT: `\"Invalid --from-cycle: N (task plan has M cycles)\"` |\n| RED test PASSES before implementation | ABORT: `\"RED phase failed: test passes before implementation\"` (tautology \u002F stale test \u002F behavior already exists) |\n| GREEN compile fails | Retry up to 3 times with minimum fix only; ABORT after |\n| GREEN tests fail | Retry up to 3 times with minimum fix only; ABORT after |\n| REFACTOR tests fail after change | REVERT (`git checkout -- .`), skip REFACTOR commit, log warning, continue to next cycle |\n| Coverage below 95% line \u002F 90% branch after GREEN (default, EPIC-0042) | BLOCK cycle; max 2 retry attempts writing additional tests; ABORT after. Override: `--warn-only-coverage` demotes to WARNING. |\n| `x-commit-changes` fails at any phase | ABORT: `\"Commit failed at Cycle N, phase [RED|GREEN|REFACTOR]: {error}\"` |\n| Cycles not in strict TPP order in plan | WARN `\"Cycles not in strict TPP order -- proceeding but review recommended\"`; continue |\n\n## Full Protocol\n\nMinimum viable contract above. The complete 4-phase workflow (Validate → Load Plan → Dry-Run Check → Execute Cycles), the parse format for task plan cycles, the TPP reference table with all 8 priority levels, per-phase validation algorithms (RED fail validation, GREEN minimum + coverage gate, REFACTOR revert-on-fail), the compact-vs-full log rendering rules, the Double-Loop TDD diagram, and anti-patterns live in [`references\u002Ffull-protocol.md`](references\u002Ffull-protocol.md) per ADR-0012 (skill body slim-by-default). Standalone invocation from a chat prompt (happy path: given a valid task plan, produce N commits) needs only this SKILL.md; the full protocol is consulted when diagnosing a failed cycle or authoring a new task plan.\n\n## Integration Notes\n\n| Skill | Relationship | Context |\n|-------|-------------|---------|\n| `x-plan-task` | reads from | Task plan provides TDD cycle definitions |\n| `x-commit-changes` | delegates to | Each phase produces an atomic commit via x-commit-changes |\n| `x-format-code` | invoked via x-commit-changes chain | Format runs before commit |\n| `x-lint-code` | invoked via x-commit-changes chain | Lint runs before commit |\n| `x-execute-tests` | complementary | Coverage analysis helper; this skill uses `{{TEST_COMMAND}}` + `{{COVERAGE_COMMAND}}` directly |\n| `x-implement-story` | orchestrated by | Lifecycle invokes x-drive-tdd for inner-loop TDD execution (Phase 2) |\n| `x-implement-task` | complementary | Full-task orchestrator; this skill handles per-task TDD only |\n\n## Template Variables\n\n| Variable | Description | Example |\n|----------|-------------|---------|\n| `{{TEST_COMMAND}}` | Run project tests | `mvn test -q` |\n| `{{COMPILE_COMMAND}}` | Compile the project | `mvn compile -q` |\n| `{{COVERAGE_COMMAND}}` | Run tests with coverage | `mvn verify -Pcoverage -q` |\n| `{{LANGUAGE}}` | Project language | `java` |\n| `{{PROJECT_NAME}}` | Project name | `my-java-cli` |\n| `{{BUILD_TOOL}}` | Project build tool | `maven` |\n","## Global Output Policy\n\n- **Language**: English ONLY.\n- **Tone**: Technical, Direct, and Concise.\n- **Efficiency**: Remove all conversational fillers and greetings to save tokens.\n\n# Skill: TDD Execution with Atomic Cycles (slim — ADR-0012)\n\nExecutes systematic Red-Green-Refactor TDD cycles for {{PROJECT_NAME}} tasks. Reads the task plan produced by `\u002Fx-plan-task`, iterates TDD cycles in strict Transformation Priority Premise (TPP) order, validates each phase (RED must fail, GREEN must pass with minimum code, REFACTOR must preserve behavior), and delegates atomic commits to `x-commit-changes` with TDD tags (`[TDD:RED]`, `[TDD:GREEN]`, `[TDD:REFACTOR]`). Enforces RULE-008 (TDD Strict) and RULE-016 (Conventional Commits with Task ID).\n\n## Triggers\n\n- `\u002Fx-drive-tdd TASK-0029-0001-001` -- execute all TDD cycles for the task\n- `\u002Fx-drive-tdd TASK-0029-0001-001 --from-cycle 3` -- resume from cycle 3\n- `\u002Fx-drive-tdd TASK-0029-0001-001 --dry-run` -- list cycles without executing\n- `\u002Fx-drive-tdd TASK-0029-0001-001 --warn-only-coverage` -- legacy mode: sub-threshold coverage warns instead of blocks\n- `\u002Fx-drive-tdd TASK-0029-0001-001 --orchestrated` -- compact single-line cycle log (called from x-implement-story \u002F x-implement-epic)\n\n## Parameters\n\n| Parameter | Required | Default | Description |\n|-----------|----------|---------|-------------|\n| `TASK-ID` | Yes | — | Task identifier `TASK-XXXX-YYYY-NNN` (epic-story-task) |\n| `--from-cycle` | No | `1` | Resume from a specific cycle number (≥ 1). Cycles before this are skipped. |\n| `--dry-run` | No | `false` | List all cycles with descriptions and TPP levels; execute nothing. |\n| `--warn-only-coverage` | No | `false` | Legacy override (EPIC-0042). When set, coverage \u003C 95% line \u002F \u003C 90% branch emits WARNING instead of blocking the cycle. Default is blocking. |\n| `--orchestrated` | No | `false` | Emit one-line-per-cycle compact log. Passed explicitly by parent orchestrators (Story 0033-0003) so the decision is deterministic, not inferred. |\n\n## Output Contract\n\n- **Per-cycle artifacts:** each TDD cycle produces up to three atomic commits via `x-commit-changes` — `[TDD:RED]` (test-only), `[TDD:GREEN]` (minimum implementation), optional `[TDD:REFACTOR]` (if the task plan declares opportunities and tests still pass afterward).\n- **Final report to stdout:** cycles executed, commits created with SHA + message first-line per cycle, final coverage line\u002Fbranch %, warnings list. Under `--orchestrated`, one compact line per cycle: `Cycle {n}\u002F{m}: RED FAIL_EXPECTED GREEN PASS REFACTOR {skipped|PASS} → {sha7}`.\n- **Exit codes:** `0` on clean completion of all requested cycles; `1` on any ABORT condition (see `## Error Envelope`).\n- **Commit cadence:** each phase is one atomic commit; batching multiple phases into one commit is forbidden (see anti-patterns in `references\u002Ffull-protocol.md` §6).\n\n## Double-Loop Role\n\nThis skill is the **inner loop** of Double-Loop TDD. The outer loop (failing acceptance test) is driven by `x-implement-story` \u002F `x-implement-task`; each inner cycle produces one or more unit commits that compose toward the acceptance green. Full workflow diagram and Double-Loop context live in `references\u002Ffull-protocol.md` §5.\n\n## Error Envelope\n\n| Scenario | Action |\n|----------|--------|\n| Invalid task ID format (pattern mismatch) | ABORT: `\"Task ID invalid -- expected format: TASK-XXXX-YYYY-NNN\"` |\n| Task plan file not found | ABORT: `\"Task plan not found: task-plan-XXXX-YYYY-NNN.md\"` |\n| No `TDD Cycles` section in plan | ABORT: `\"No TDD Cycles section found in task plan\"` |\n| `--from-cycle N` out of range (N \u003C 1 or N > total cycles) | ABORT: `\"Invalid --from-cycle: N (task plan has M cycles)\"` |\n| RED test PASSES before implementation | ABORT: `\"RED phase failed: test passes before implementation\"` (tautology \u002F stale test \u002F behavior already exists) |\n| GREEN compile fails | Retry up to 3 times with minimum fix only; ABORT after |\n| GREEN tests fail | Retry up to 3 times with minimum fix only; ABORT after |\n| REFACTOR tests fail after change | REVERT (`git checkout -- .`), skip REFACTOR commit, log warning, continue to next cycle |\n| Coverage below 95% line \u002F 90% branch after GREEN (default, EPIC-0042) | BLOCK cycle; max 2 retry attempts writing additional tests; ABORT after. Override: `--warn-only-coverage` demotes to WARNING. |\n| `x-commit-changes` fails at any phase | ABORT: `\"Commit failed at Cycle N, phase [RED|GREEN|REFACTOR]: {error}\"` |\n| Cycles not in strict TPP order in plan | WARN `\"Cycles not in strict TPP order -- proceeding but review recommended\"`; continue |\n\n## Full Protocol\n\nMinimum viable contract above. The complete 4-phase workflow (Validate → Load Plan → Dry-Run Check → Execute Cycles), the parse format for task plan cycles, the TPP reference table with all 8 priority levels, per-phase validation algorithms (RED fail validation, GREEN minimum + coverage gate, REFACTOR revert-on-fail), the compact-vs-full log rendering rules, the Double-Loop TDD diagram, and anti-patterns live in [`references\u002Ffull-protocol.md`](references\u002Ffull-protocol.md) per ADR-0012 (skill body slim-by-default). Standalone invocation from a chat prompt (happy path: given a valid task plan, produce N commits) needs only this SKILL.md; the full protocol is consulted when diagnosing a failed cycle or authoring a new task plan.\n\n## Integration Notes\n\n| Skill | Relationship | Context |\n|-------|-------------|---------|\n| `x-plan-task` | reads from | Task plan provides TDD cycle definitions |\n| `x-commit-changes` | delegates to | Each phase produces an atomic commit via x-commit-changes |\n| `x-format-code` | invoked via x-commit-changes chain | Format runs before commit |\n| `x-lint-code` | invoked via x-commit-changes chain | Lint runs before commit |\n| `x-execute-tests` | complementary | Coverage analysis helper; this skill uses `{{TEST_COMMAND}}` + `{{COVERAGE_COMMAND}}` directly |\n| `x-implement-story` | orchestrated by | Lifecycle invokes x-drive-tdd for inner-loop TDD execution (Phase 2) |\n| `x-implement-task` | complementary | Full-task orchestrator; this skill handles per-task TDD only |\n\n## Template Variables\n\n| Variable | Description | Example |\n|----------|-------------|---------|\n| `{{TEST_COMMAND}}` | Run project tests | `mvn test -q` |\n| `{{COMPILE_COMMAND}}` | Compile the project | `mvn compile -q` |\n| `{{COVERAGE_COMMAND}}` | Run tests with coverage | `mvn verify -Pcoverage -q` |\n| `{{LANGUAGE}}` | Project language | `java` |\n| `{{PROJECT_NAME}}` | Project name | `my-java-cli` |\n| `{{BUILD_TOOL}}` | Project build tool | `maven` |\n",{"name":5,"description":7,"allowed-tools":24,"argument-hint":25,"context-budget":26,"user-invocable":27,"requires-capabilities":28},"Bash, Read, Write, Edit, Grep, Glob, Skill","TASK-XXXX-YYYY-NNN [--from-cycle N] [--dry-run] [--warn-only-coverage] [--orchestrated]","light",true,[],"main","952a630c6f38d193a349d86fa18db1de8843e837","src\u002Ftest\u002Fresources\u002Fgolden\u002Fjava-spring-event-driven\u002F.claude\u002Fskills\u002Fx-drive-tdd",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":39,"prompt":49,"zipAvailable":27},[40,43,46],{"tool":41,"command":42},"npx","npx skills add review-bench\u002Federcnj_ia-dev-environment --skill x-drive-tdd",{"tool":44,"command":45},"bunx","bunx skills add review-bench\u002Federcnj_ia-dev-environment --skill x-drive-tdd",{"tool":47,"command":48},"pnpm","pnpm dlx skills add review-bench\u002Federcnj_ia-dev-environment --skill x-drive-tdd","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-event-driven\u002F.claude\u002Fskills\u002Fx-drive-tdd\u002FSKILL.md",[51,57],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"README.md","REFERENCE","参考文档",4064,"https:\u002F\u002Fgithub.com\u002Freview-bench\u002Federcnj_ia-dev-environment\u002Fblob\u002Fmain\u002Fsrc\u002Ftest\u002Fresources\u002Fgolden\u002Fjava-spring-event-driven\u002F.claude\u002Fskills\u002Fx-drive-tdd\u002FREADME.md",{"path":58,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ffull-protocol.md",14185,"https:\u002F\u002Fgithub.com\u002Freview-bench\u002Federcnj_ia-dev-environment\u002Fblob\u002Fmain\u002Fsrc\u002Ftest\u002Fresources\u002Fgolden\u002Fjava-spring-event-driven\u002F.claude\u002Fskills\u002Fx-drive-tdd\u002Freferences\u002Ffull-protocol.md",[62,69,76,83,90,97],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"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":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"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":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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",[],[]]