[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M751QKQRXX6YG09NET69GN24":3,"skill-same:01M751QKQRXX6YG09NET69GN24":53},{"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":31,"commitSha":32,"skillDirectory":33,"forksCount":34,"repositoryHtmlUrl":35,"repositoryHomepageUrl":6,"ownerHtmlUrl":36,"ownerBlogUrl":37,"ownerDescription":38,"updatedAt":39,"install":40,"resources":52},"01M751QKQRXX6YG09NET69GN24","x-evaluate-parallelism",null,"Detects and classifies file-collision risks between work units (tasks, stories, or epic phases) before parallel execution. Reads ## File Footprint blocks produced by x-plan-task \u002F x-plan-story, 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.","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\u002Fmain\u002Fresources\u002Ftargets\u002Fclaude\u002Fskills\u002Fcore\u002Fplan\u002Fx-evaluate-parallelism\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: x-evaluate-parallelism\ndescription: \"Detects and classifies file-collision risks between work units (tasks, stories, or epic phases) before parallel execution. Reads ## File Footprint blocks produced by x-plan-task \u002F x-plan-story, 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.\"\nuser-invocable: true\nargument-hint: \"--scope=epic|story|task [--epic PATH] [--a ID --b ID] [--out PATH] [--format markdown|json]\"\nallowed-tools:\n  - Bash\n  - Read\n  - Skill\nrequires-capabilities: []\n---\n\n# Skill: x-evaluate-parallelism\n\n## Purpose\n\nEvaluate the merge-conflict risk of running two or more work units in parallel,\nusing the canonical file-collision heuristics catalogued in the\n`parallelism-heuristics` knowledge pack. The skill is intentionally cascading:\nit consumes the structured `## File Footprint` blocks already emitted by\n`x-plan-task` (Phase 4.5) and `x-plan-story` (Phase 6), so the output is\ndeterministic and independent of prose parsing (RULE-008).\n\nThe primary consumers are:\n\n- Operators validating an epic before dispatching `x-implement-epic` in parallel.\n- `x-epic-map` Step 8.5 (`story-0041-0005`), which invokes this skill as a gate.\n- `x-dev-*-implement` future gates (`story-0041-0006`).\n\n## When to Use\n\n- Before approving an Implementation Map to confirm that declared parallel\n  phases are actually conflict-free.\n- When comparing two stories or two tasks in isolation to decide whether\n  they can be coalesced into the same wave.\n- As a read-only audit after the fact (\"did we ship these in parallel safely?\").\n\n## CLI Arguments\n\n| Flag | Required | Description |\n| :--- | :--- | :--- |\n| `--scope` | Yes | `epic`, `story`, or `task` |\n| `--epic` | If `--scope=epic` | Path to the epic directory (e.g., `ai\u002Fepics\u002Fepic-XXXX`) |\n| `--a` \u002F `--b` | If `--scope=story\\|task` | IDs of the pair to compare |\n| `--out` | No | Output file path (writes to stdout by default) |\n| `--format` | No | `markdown` (default) or `json` |\n| `--map` | No | Implementation map path; when supplied its declared phases override the topological derivation |\n| `--include-soft` | No | Include SOFT (read-only) overlaps in the output |\n\n## Exit Codes\n\n| Code | Meaning |\n| :--- | :--- |\n| 0 | No conflicts detected |\n| 1 | Warnings only (e.g., legacy footprints missing) |\n| 2 | Hard or regen conflicts detected |\n\n## Workflow\n\n### Phase 1 — Resolve scope and load footprints\n\n1. Parse the CLI arguments and classify scope (`epic` \u002F `story` \u002F `task`).\n2. For `--scope=epic`: enumerate `story-XXXX-YYYY.md` files under the epic\n   directory, extract the `## File Footprint` block and the `Blocked By`\n   column, and derive phases topologically.\n3. For `--scope=story|task`: read the two artefacts directly.\n4. Any artefact lacking a `## File Footprint` block is reported as a warning\n   (RULE-005 — Degrade with Warning) and flagged as non-parallel.\n\n### Phase 2 — Classify collisions\n\nFor every pair within the same phase, apply the rules in the\n`parallelism-heuristics` KP (RULE-003):\n\n- `hard` — both units write the same path → must be serialized.\n- `regen` — one writes, the other regenerates (or both regenerate) the same\n  path → must be serialized.\n- `soft` — overlap only in `read:` → safe to run in parallel (ignored unless\n  `--include-soft` is passed).\n\nHotspot paths from the KP catalogue (RULE-004) force a `hard` classification\nregardless of the nominal write \u002F regen sets.\n\n### Phase 3 — Emit report\n\n1. Render the report in Markdown (default) or JSON (`--format=json`). The\n   Markdown shape is:\n\n       # Parallelism Evaluation — EPIC-XXXX\n\n       **Scope:** epic | **Items analyzed:** N | **Conflicts:** H hard, R regen, S soft\n\n       ## Collision Matrix\n       | A | B | Category | Shared paths |\n       | :--- | :--- | :--- | :--- |\n       ...\n\n       ## Recommended Serialization Groups\n       - **Group N (serialize):** story-... → story-...\n       - **Group N (parallel):** story-..., story-...\n\n       ## Hotspot Touches\n       - `path` touched by: story-X, story-Y\n\n2. Write to stdout by default, or to `--out` when supplied.\n3. Return the exit code derived from `hardCount + regenCount + warnings`\n   (see table above).\n\n## Invocation Examples\n\n```bash\n\u002Fx-evaluate-parallelism --scope=epic --epic ai\u002Fepics\u002Fepic-XXXX\n\u002Fx-evaluate-parallelism --scope=epic --epic ai\u002Fepics\u002Fepic-XXXX --out reports\u002Fparallelism.md\n\u002Fx-evaluate-parallelism --scope=story --a story-0041-0002 --b story-0041-0003\n\u002Fx-evaluate-parallelism --scope=task --a TASK-0041-0002-001 --b TASK-0041-0003-001\n```\n\nThe skill shells out to the project CLI (`parallel-eval` subcommand backed by\n`dev.iadev.parallelism.cli.ParallelEvalCli`). It is side-effect-free except\nwhen `--out` is supplied.\n\n## Knowledge Pack Reference\n\n- `parallelism-heuristics` — canonical catalogue of the File Footprint block\n  format, conflict categories (hard \u002F regen \u002F soft), hotspot list, and\n  degrade-with-warning policy. Read before modifying collision rules.\n\n## Integration Notes\n\n| Consumer | Relationship | Context |\n| :--- | :--- | :--- |\n| `x-epic-map` | Invokes (Step 8.5) | Parallel-dispatch gate before an epic plan is approved |\n| `x-plan-story` | Produces input | Emits the `## File Footprint` blocks read here |\n| `x-plan-task` | Produces input | Emits the per-task footprints used in `--scope=task` |\n| `x-dev-*-implement` | Invokes (future, EPIC-0041 §5+) | Pre-dispatch safety check before parallel worktrees |\n\n## Determinism (RULE-008)\n\nRunning the skill twice with the same inputs MUST produce byte-identical\noutputs. Implementation rules that enforce this:\n\n- All sets are stored as `TreeSet` (alphabetical iteration).\n- Collisions are sorted by `(a, b)` ascending before rendering.\n- Phase derivation is lexicographic when ties appear in the topological\n  ordering.\n\n## Forbidden\n\n- Inferring footprints from prose — the skill MUST use the structured\n  `## File Footprint` block only (RULE-001).\n- Hard-failing when a footprint is missing — degrade with warning (RULE-005).\n- Mutating any file other than the `--out` target.\n","# Skill: x-evaluate-parallelism\n\n## Purpose\n\nEvaluate the merge-conflict risk of running two or more work units in parallel,\nusing the canonical file-collision heuristics catalogued in the\n`parallelism-heuristics` knowledge pack. The skill is intentionally cascading:\nit consumes the structured `## File Footprint` blocks already emitted by\n`x-plan-task` (Phase 4.5) and `x-plan-story` (Phase 6), so the output is\ndeterministic and independent of prose parsing (RULE-008).\n\nThe primary consumers are:\n\n- Operators validating an epic before dispatching `x-implement-epic` in parallel.\n- `x-epic-map` Step 8.5 (`story-0041-0005`), which invokes this skill as a gate.\n- `x-dev-*-implement` future gates (`story-0041-0006`).\n\n## When to Use\n\n- Before approving an Implementation Map to confirm that declared parallel\n  phases are actually conflict-free.\n- When comparing two stories or two tasks in isolation to decide whether\n  they can be coalesced into the same wave.\n- As a read-only audit after the fact (\"did we ship these in parallel safely?\").\n\n## CLI Arguments\n\n| Flag | Required | Description |\n| :--- | :--- | :--- |\n| `--scope` | Yes | `epic`, `story`, or `task` |\n| `--epic` | If `--scope=epic` | Path to the epic directory (e.g., `ai\u002Fepics\u002Fepic-XXXX`) |\n| `--a` \u002F `--b` | If `--scope=story\\|task` | IDs of the pair to compare |\n| `--out` | No | Output file path (writes to stdout by default) |\n| `--format` | No | `markdown` (default) or `json` |\n| `--map` | No | Implementation map path; when supplied its declared phases override the topological derivation |\n| `--include-soft` | No | Include SOFT (read-only) overlaps in the output |\n\n## Exit Codes\n\n| Code | Meaning |\n| :--- | :--- |\n| 0 | No conflicts detected |\n| 1 | Warnings only (e.g., legacy footprints missing) |\n| 2 | Hard or regen conflicts detected |\n\n## Workflow\n\n### Phase 1 — Resolve scope and load footprints\n\n1. Parse the CLI arguments and classify scope (`epic` \u002F `story` \u002F `task`).\n2. For `--scope=epic`: enumerate `story-XXXX-YYYY.md` files under the epic\n   directory, extract the `## File Footprint` block and the `Blocked By`\n   column, and derive phases topologically.\n3. For `--scope=story|task`: read the two artefacts directly.\n4. Any artefact lacking a `## File Footprint` block is reported as a warning\n   (RULE-005 — Degrade with Warning) and flagged as non-parallel.\n\n### Phase 2 — Classify collisions\n\nFor every pair within the same phase, apply the rules in the\n`parallelism-heuristics` KP (RULE-003):\n\n- `hard` — both units write the same path → must be serialized.\n- `regen` — one writes, the other regenerates (or both regenerate) the same\n  path → must be serialized.\n- `soft` — overlap only in `read:` → safe to run in parallel (ignored unless\n  `--include-soft` is passed).\n\nHotspot paths from the KP catalogue (RULE-004) force a `hard` classification\nregardless of the nominal write \u002F regen sets.\n\n### Phase 3 — Emit report\n\n1. Render the report in Markdown (default) or JSON (`--format=json`). The\n   Markdown shape is:\n\n       # Parallelism Evaluation — EPIC-XXXX\n\n       **Scope:** epic | **Items analyzed:** N | **Conflicts:** H hard, R regen, S soft\n\n       ## Collision Matrix\n       | A | B | Category | Shared paths |\n       | :--- | :--- | :--- | :--- |\n       ...\n\n       ## Recommended Serialization Groups\n       - **Group N (serialize):** story-... → story-...\n       - **Group N (parallel):** story-..., story-...\n\n       ## Hotspot Touches\n       - `path` touched by: story-X, story-Y\n\n2. Write to stdout by default, or to `--out` when supplied.\n3. Return the exit code derived from `hardCount + regenCount + warnings`\n   (see table above).\n\n## Invocation Examples\n\n```bash\n\u002Fx-evaluate-parallelism --scope=epic --epic ai\u002Fepics\u002Fepic-XXXX\n\u002Fx-evaluate-parallelism --scope=epic --epic ai\u002Fepics\u002Fepic-XXXX --out reports\u002Fparallelism.md\n\u002Fx-evaluate-parallelism --scope=story --a story-0041-0002 --b story-0041-0003\n\u002Fx-evaluate-parallelism --scope=task --a TASK-0041-0002-001 --b TASK-0041-0003-001\n```\n\nThe skill shells out to the project CLI (`parallel-eval` subcommand backed by\n`dev.iadev.parallelism.cli.ParallelEvalCli`). It is side-effect-free except\nwhen `--out` is supplied.\n\n## Knowledge Pack Reference\n\n- `parallelism-heuristics` — canonical catalogue of the File Footprint block\n  format, conflict categories (hard \u002F regen \u002F soft), hotspot list, and\n  degrade-with-warning policy. Read before modifying collision rules.\n\n## Integration Notes\n\n| Consumer | Relationship | Context |\n| :--- | :--- | :--- |\n| `x-epic-map` | Invokes (Step 8.5) | Parallel-dispatch gate before an epic plan is approved |\n| `x-plan-story` | Produces input | Emits the `## File Footprint` blocks read here |\n| `x-plan-task` | Produces input | Emits the per-task footprints used in `--scope=task` |\n| `x-dev-*-implement` | Invokes (future, EPIC-0041 §5+) | Pre-dispatch safety check before parallel worktrees |\n\n## Determinism (RULE-008)\n\nRunning the skill twice with the same inputs MUST produce byte-identical\noutputs. Implementation rules that enforce this:\n\n- All sets are stored as `TreeSet` (alphabetical iteration).\n- Collisions are sorted by `(a, b)` ascending before rendering.\n- Phase derivation is lexicographic when ties appear in the topological\n  ordering.\n\n## Forbidden\n\n- Inferring footprints from prose — the skill MUST use the structured\n  `## File Footprint` block only (RULE-001).\n- Hard-failing when a footprint is missing — degrade with warning (RULE-005).\n- Mutating any file other than the `--out` target.\n",{"name":5,"description":7,"allowed-tools":24,"argument-hint":28,"user-invocable":29,"requires-capabilities":30},[25,26,27],"Bash","Read","Skill","--scope=epic|story|task [--epic PATH] [--a ID --b ID] [--out PATH] [--format markdown|json]",true,[],"main","952a630c6f38d193a349d86fa18db1de8843e837","src\u002Fmain\u002Fresources\u002Ftargets\u002Fclaude\u002Fskills\u002Fcore\u002Fplan\u002Fx-evaluate-parallelism",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":41,"prompt":51,"zipAvailable":29},[42,45,48],{"tool":43,"command":44},"npx","npx skills add review-bench\u002Federcnj_ia-dev-environment --skill x-evaluate-parallelism",{"tool":46,"command":47},"bunx","bunx skills add review-bench\u002Federcnj_ia-dev-environment --skill x-evaluate-parallelism",{"tool":49,"command":50},"pnpm","pnpm dlx skills add review-bench\u002Federcnj_ia-dev-environment --skill x-evaluate-parallelism","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Freview-bench\u002Federcnj_ia-dev-environment\u002Fblob\u002Fmain\u002Fsrc\u002Fmain\u002Fresources\u002Ftargets\u002Fclaude\u002Fskills\u002Fcore\u002Fplan\u002Fx-evaluate-parallelism\u002FSKILL.md",[],[54,61,68,75,82,89],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"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":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},"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":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},"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":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},"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":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},"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":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},"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",[],[]]