[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6XD52R22Z5QK3VBK18QY3BP":3,"skill-same:01M6XD52R22Z5QK3VBK18QY3BP":106},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":14,"repositoryHtmlUrl":50,"repositoryHomepageUrl":6,"ownerHtmlUrl":51,"ownerBlogUrl":6,"ownerDescription":52,"updatedAt":53,"install":54,"resources":67},"01M6XD52R22Z5QK3VBK18QY3BP","plan-grader",null,"Grade implementation plans on a 0-10 scale without mutating the workspace. Accepts plan files, quoted inline plans, or best-effort latest-plan discovery for Claude, Codex, Copilot, and Gemini.","kaiohenricunha\u002Fdotbabel","kaiohenricunha","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F69804490?v=4","01M6XCZD37W0KPCDGEA40Y610V","Kaio Cunha","01M6XCZD7SX714D114H3ZPNW09",0,"MIT","https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fexamples\u002Fminimal-consumer\u002F.claude\u002Fskills\u002Fplan-grader\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"plan grader","plan","grader","read","quoted","inline","for","path","latest","plans","files","gemini","workspace","text","json","Bash","discovery","file","copilot","codex","2026-11-10 10:12:30",false,"---\n# dotbabel:generated projection=sha256:48fafb297c2b84273c2179d6babef02b3f26292b7ec633f46a6adbe4f3cf475e source=skills\u002Fplan-grader\u002FSKILL.md — do not edit directly\nallowed-tools: Read Grep Glob Bash\nargument-hint: '[--json] [--blind] \u003Cplan-path | file:\u003Cpath> | text:\"plan\" | \"plan\" | latest \u003Cagent> plan>'\ndescription: |\n  Grade implementation plans on a 0-10 scale without mutating the workspace. Accepts plan files, quoted inline plans, or best-effort latest-plan discovery for Claude, Codex, Copilot, and Gemini.\nname: plan-grader\n---\n\nGrade an implementation plan on a 0-10 scale using the plan-grader rubric. This skill is\ncontent-only: inspect, score, explain, and produce a paste-back prompt. Do not edit files, run\nformatters, commit changes, or implement the plan being graded.\n\nUse when the user asks to grade, score, review, evaluate, improve, or calibrate a plan, especially\nplans produced by Claude Code, Codex, GitHub Copilot, Gemini CLI, or similar agentic CLIs. Also\ntrigger directly via `\u002Fplan-grader`.\n\n## Inputs\n\n`$ARGUMENTS` may be any of:\n\n- `\u003Cpath>` or `file:\u003Cpath>`: read the plan from a local Markdown\u002Ftext file.\n- `\"...\"` or `text:\"...\"`: grade the quoted inline plan text exactly as provided.\n- `latest claude plan`, `latest codex plan`, `latest copilot plan`, or `latest gemini plan`:\n  discover candidate plan\u002Fsession files using `references\u002Fplan-discovery.md`.\n- Optional `--json`: emit only the structured JSON object described below.\n- Optional `--blind`: strip source-agent attribution before scoring. Keep explicit harness context\n  that affects safety, validation, or repo fit.\n\nIf the input is ambiguous, ask for the plan path or paste. Do not guess a plan from unrelated chat.\n\n## Reference Order\n\nBefore grading, read these references:\n\n1. `references\u002Frubric.md`\n2. `references\u002Fcontext-resolution.md`\n3. `references\u002Fplan-discovery.md` when discovery, imports, symlinks, oversized content, or\n   transcript extraction are involved\n4. `references\u002Fagent-formats.md` when the source agent is known or a paste-back prompt is needed\n5. Relevant examples in `references\u002Fcalibration-plans\u002F`\n\n## Workflow\n\n1. Parse flags and input mode.\n   - `--json` changes output format only.\n   - `--blind` removes agent identity from the plan before scoring.\n   - `file:` forces file mode.\n   - `text:` forces inline text mode.\n   - Top-level quoted text is inline plan text, not a path.\n\n2. Resolve the plan text.\n   - For file inputs, read the target file.\n   - For inline text, use the supplied text verbatim.\n   - For `latest \u003Cagent> plan`, follow `references\u002Fplan-discovery.md`.\n   - If discovery returns multiple candidates, present the top three most recent candidate paths and\n     ask the user to choose.\n   - Refuse oversized inputs that cannot fit the context budget. Do not silently truncate.\n\n3. Resolve intent sources.\n   - Treat files mentioned by the plan as intent evidence, especially `@roadmap.md`,\n     `@spec.md`, `file:docs\u002Ffoo.md`, or explicit local paths.\n   - Resolve transitive `@` imports to the depth documented in `references\u002Fplan-discovery.md`.\n   - If a referenced intent file is unreadable, record the missing file and lower confidence.\n   - If a readable intent file contradicts the plan, apply the relevant rubric cap.\n\n4. Resolve harness context.\n   - Read project-level `AGENTS.md` first as the cross-agent baseline when present.\n   - Layer agent-specific project overrides: `CLAUDE.md`, `GEMINI.md`,\n     `.github\u002Fcopilot-instructions.md`, `.github\u002Finstructions\u002F*.instructions.md`, and\n     `AGENTS.override.md`.\n   - Consider user\u002Fglobal harness files only as preference context. They cannot weaken repo-local\n     safety, validation, protected-path, release, or CI rules.\n   - Detect whether the plan violates configured harnesses or protected gates.\n\n5. Calibrate before scoring.\n   - Read at least the two calibration anchors closest to the expected score band.\n   - Use the anchors to normalize severity and avoid over-rewarding format polish.\n\n6. Score the plan.\n   - Score each rubric dimension from 0 to 10.\n   - Compute the weighted score using rubric version `2.0.0`.\n   - Apply caps, then auto-reject rules, then floor at 0, then round to one decimal.\n   - Record `confidence` as `high`, `medium`, or `low`.\n\n7. Produce output.\n   - Default: concise human-readable report with score, verdict, dimension table, caps, blocking\n     gaps, non-blocking polish, and a paste-back prompt.\n   - `--json`: emit only valid JSON with exactly these top-level keys:\n     `rubric_version`, `score`, `verdict`, `confidence`, `dimensions`, `caps_fired`,\n     `blocking_gaps`, `non_blocking`, `paste_back_prompt`.\n\n## Human Output Shape\n\n```markdown\nPlan grade: X.X \u002F 10\nVerdict: \u003Capprove | approve with minor changes | revise before execution | reject>\nConfidence: \u003Chigh | medium | low>\n\n\u003COne short paragraph explaining the main reason for the grade.>\n\n| Dimension | Weight | Score | Reasoning              |\n| --------- | -----: | ----: | ---------------------- |\n| ...       |   0.XX |  N\u002F10 | Evidence-backed reason |\n\nCaps fired:\n\n- \u003Ccap id or \"None\">\n\nBlocking gaps:\n\n1. \u003Cgap>\n\nNon-blocking improvements:\n\n- \u003Cimprovement>\n\nPaste-back prompt:\n\u003Cagent-aware prompt from references\u002Fagent-formats.md>\n```\n\n## JSON Output Shape\n\n```json\n{\n  \"rubric_version\": \"2.0.0\",\n  \"score\": 8.4,\n  \"verdict\": \"approve with minor changes\",\n  \"confidence\": \"high\",\n  \"dimensions\": [\n    {\n      \"name\": \"Goal and scope clarity\",\n      \"weight\": 0.15,\n      \"score\": 9,\n      \"reasoning\": \"The plan defines the output contract and non-goals.\",\n      \"evidence\": [\"plan.md:12\"]\n    }\n  ],\n  \"caps_fired\": [],\n  \"blocking_gaps\": [],\n  \"non_blocking\": [\"Add one explicit smoke test for malformed input.\"],\n  \"paste_back_prompt\": \"Revise the plan to add one malformed-input smoke test...\"\n}\n```\n\n## Rules\n\n- Do not mutate files or implement the plan being graded.\n- Do not score from vibes. Cite concrete evidence from the plan, intent files, harness files,\n  repo paths, tests, CI, or explicit missing evidence.\n- Mention when the grade is based on incomplete transcript extraction rather than a real plan file.\n- Auto-reject dangerous caps even when the weighted score is high.\n- Keep all weights from `references\u002Frubric.md` exactly. Do not silently reweight.\n- For `--blind`, do not penalize or reward the plan because it came from Claude, Codex, Copilot, or\n  Gemini. Grade the content and repo fit.\n- If a plan references images or diagrams, do not OCR them. Mark that portion partially ungradable.\n- If a plan would touch protected paths, verify it includes the required Spec ID or No-spec\n  rationale in the PR plan.\n- Always include a paste-back prompt unless the user explicitly asks for only the numeric grade.\n","Grade an implementation plan on a 0-10 scale using the plan-grader rubric. This skill is\ncontent-only: inspect, score, explain, and produce a paste-back prompt. Do not edit files, run\nformatters, commit changes, or implement the plan being graded.\n\nUse when the user asks to grade, score, review, evaluate, improve, or calibrate a plan, especially\nplans produced by Claude Code, Codex, GitHub Copilot, Gemini CLI, or similar agentic CLIs. Also\ntrigger directly via `\u002Fplan-grader`.\n\n## Inputs\n\n`$ARGUMENTS` may be any of:\n\n- `\u003Cpath>` or `file:\u003Cpath>`: read the plan from a local Markdown\u002Ftext file.\n- `\"...\"` or `text:\"...\"`: grade the quoted inline plan text exactly as provided.\n- `latest claude plan`, `latest codex plan`, `latest copilot plan`, or `latest gemini plan`:\n  discover candidate plan\u002Fsession files using `references\u002Fplan-discovery.md`.\n- Optional `--json`: emit only the structured JSON object described below.\n- Optional `--blind`: strip source-agent attribution before scoring. Keep explicit harness context\n  that affects safety, validation, or repo fit.\n\nIf the input is ambiguous, ask for the plan path or paste. Do not guess a plan from unrelated chat.\n\n## Reference Order\n\nBefore grading, read these references:\n\n1. `references\u002Frubric.md`\n2. `references\u002Fcontext-resolution.md`\n3. `references\u002Fplan-discovery.md` when discovery, imports, symlinks, oversized content, or\n   transcript extraction are involved\n4. `references\u002Fagent-formats.md` when the source agent is known or a paste-back prompt is needed\n5. Relevant examples in `references\u002Fcalibration-plans\u002F`\n\n## Workflow\n\n1. Parse flags and input mode.\n   - `--json` changes output format only.\n   - `--blind` removes agent identity from the plan before scoring.\n   - `file:` forces file mode.\n   - `text:` forces inline text mode.\n   - Top-level quoted text is inline plan text, not a path.\n\n2. Resolve the plan text.\n   - For file inputs, read the target file.\n   - For inline text, use the supplied text verbatim.\n   - For `latest \u003Cagent> plan`, follow `references\u002Fplan-discovery.md`.\n   - If discovery returns multiple candidates, present the top three most recent candidate paths and\n     ask the user to choose.\n   - Refuse oversized inputs that cannot fit the context budget. Do not silently truncate.\n\n3. Resolve intent sources.\n   - Treat files mentioned by the plan as intent evidence, especially `@roadmap.md`,\n     `@spec.md`, `file:docs\u002Ffoo.md`, or explicit local paths.\n   - Resolve transitive `@` imports to the depth documented in `references\u002Fplan-discovery.md`.\n   - If a referenced intent file is unreadable, record the missing file and lower confidence.\n   - If a readable intent file contradicts the plan, apply the relevant rubric cap.\n\n4. Resolve harness context.\n   - Read project-level `AGENTS.md` first as the cross-agent baseline when present.\n   - Layer agent-specific project overrides: `CLAUDE.md`, `GEMINI.md`,\n     `.github\u002Fcopilot-instructions.md`, `.github\u002Finstructions\u002F*.instructions.md`, and\n     `AGENTS.override.md`.\n   - Consider user\u002Fglobal harness files only as preference context. They cannot weaken repo-local\n     safety, validation, protected-path, release, or CI rules.\n   - Detect whether the plan violates configured harnesses or protected gates.\n\n5. Calibrate before scoring.\n   - Read at least the two calibration anchors closest to the expected score band.\n   - Use the anchors to normalize severity and avoid over-rewarding format polish.\n\n6. Score the plan.\n   - Score each rubric dimension from 0 to 10.\n   - Compute the weighted score using rubric version `2.0.0`.\n   - Apply caps, then auto-reject rules, then floor at 0, then round to one decimal.\n   - Record `confidence` as `high`, `medium`, or `low`.\n\n7. Produce output.\n   - Default: concise human-readable report with score, verdict, dimension table, caps, blocking\n     gaps, non-blocking polish, and a paste-back prompt.\n   - `--json`: emit only valid JSON with exactly these top-level keys:\n     `rubric_version`, `score`, `verdict`, `confidence`, `dimensions`, `caps_fired`,\n     `blocking_gaps`, `non_blocking`, `paste_back_prompt`.\n\n## Human Output Shape\n\n```markdown\nPlan grade: X.X \u002F 10\nVerdict: \u003Capprove | approve with minor changes | revise before execution | reject>\nConfidence: \u003Chigh | medium | low>\n\n\u003COne short paragraph explaining the main reason for the grade.>\n\n| Dimension | Weight | Score | Reasoning              |\n| --------- | -----: | ----: | ---------------------- |\n| ...       |   0.XX |  N\u002F10 | Evidence-backed reason |\n\nCaps fired:\n\n- \u003Ccap id or \"None\">\n\nBlocking gaps:\n\n1. \u003Cgap>\n\nNon-blocking improvements:\n\n- \u003Cimprovement>\n\nPaste-back prompt:\n\u003Cagent-aware prompt from references\u002Fagent-formats.md>\n```\n\n## JSON Output Shape\n\n```json\n{\n  \"rubric_version\": \"2.0.0\",\n  \"score\": 8.4,\n  \"verdict\": \"approve with minor changes\",\n  \"confidence\": \"high\",\n  \"dimensions\": [\n    {\n      \"name\": \"Goal and scope clarity\",\n      \"weight\": 0.15,\n      \"score\": 9,\n      \"reasoning\": \"The plan defines the output contract and non-goals.\",\n      \"evidence\": [\"plan.md:12\"]\n    }\n  ],\n  \"caps_fired\": [],\n  \"blocking_gaps\": [],\n  \"non_blocking\": [\"Add one explicit smoke test for malformed input.\"],\n  \"paste_back_prompt\": \"Revise the plan to add one malformed-input smoke test...\"\n}\n```\n\n## Rules\n\n- Do not mutate files or implement the plan being graded.\n- Do not score from vibes. Cite concrete evidence from the plan, intent files, harness files,\n  repo paths, tests, CI, or explicit missing evidence.\n- Mention when the grade is based on incomplete transcript extraction rather than a real plan file.\n- Auto-reject dangerous caps even when the weighted score is high.\n- Keep all weights from `references\u002Frubric.md` exactly. Do not silently reweight.\n- For `--blind`, do not penalize or reward the plan because it came from Claude, Codex, Copilot, or\n  Gemini. Grade the content and repo fit.\n- If a plan references images or diagrams, do not OCR them. Mark that portion partially ungradable.\n- If a plan would touch protected paths, verify it includes the required Spec ID or No-spec\n  rationale in the PR plan.\n- Always include a paste-back prompt unless the user explicitly asks for only the numeric grade.\n",{"name":5,"description":44,"allowed-tools":45,"argument-hint":46},"Grade implementation plans on a 0-10 scale without mutating the workspace. Accepts plan files, quoted inline plans, or best-effort latest-plan discovery for Claude, Codex, Copilot, and Gemini.\n","Read Grep Glob Bash","[--json] [--blind] \u003Cplan-path | file:\u003Cpath> | text:\"plan\" | \"plan\" | latest \u003Cagent> plan>","main","91c337164997b99943fbcc64e8e362577b67bc81","examples\u002Fminimal-consumer\u002F.claude\u002Fskills\u002Fplan-grader","https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel","https:\u002F\u002Fgithub.com\u002Fkaiohenricunha","I'm a Platform\u002FInfra engineer who happens to work in cybersec and write Go code.","2026-10-26 14:12:51",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add kaiohenricunha\u002Fdotbabel --skill plan-grader",{"tool":60,"command":61},"bunx","bunx skills add kaiohenricunha\u002Fdotbabel --skill plan-grader",{"tool":63,"command":64},"pnpm","pnpm dlx skills add kaiohenricunha\u002Fdotbabel --skill plan-grader","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fexamples\u002Fminimal-consumer\u002F.claude\u002Fskills\u002Fplan-grader\u002FSKILL.md",true,[68,74,78,82,86,90,94,98,102],{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Fagent-formats.md","REFERENCE","参考文档",1834,"https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fexamples\u002Fminimal-consumer\u002F.claude\u002Fskills\u002Fplan-grader\u002Freferences\u002Fagent-formats.md",{"path":75,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fcalibration-plans\u002F35-dangerous.md",1964,"https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fexamples\u002Fminimal-consumer\u002F.claude\u002Fskills\u002Fplan-grader\u002Freferences\u002Fcalibration-plans\u002F35-dangerous.md",{"path":79,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Fcalibration-plans\u002F55-rework.md",1907,"https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fexamples\u002Fminimal-consumer\u002F.claude\u002Fskills\u002Fplan-grader\u002Freferences\u002Fcalibration-plans\u002F55-rework.md",{"path":83,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Fcalibration-plans\u002F75-solid.md",2222,"https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fexamples\u002Fminimal-consumer\u002F.claude\u002Fskills\u002Fplan-grader\u002Freferences\u002Fcalibration-plans\u002F75-solid.md",{"path":87,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Fcalibration-plans\u002F95-excellent.md",3096,"https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fexamples\u002Fminimal-consumer\u002F.claude\u002Fskills\u002Fplan-grader\u002Freferences\u002Fcalibration-plans\u002F95-excellent.md",{"path":91,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002Fcontext-resolution.md",2074,"https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fexamples\u002Fminimal-consumer\u002F.claude\u002Fskills\u002Fplan-grader\u002Freferences\u002Fcontext-resolution.md",{"path":95,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":96,"sourceHtmlUrl":97},"references\u002Fplan-discovery.md",3211,"https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fexamples\u002Fminimal-consumer\u002F.claude\u002Fskills\u002Fplan-grader\u002Freferences\u002Fplan-discovery.md",{"path":99,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":100,"sourceHtmlUrl":101},"references\u002Frubric.md",6935,"https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fexamples\u002Fminimal-consumer\u002F.claude\u002Fskills\u002Fplan-grader\u002Freferences\u002Frubric.md",{"path":103,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":104,"sourceHtmlUrl":105},"references\u002Ftest-plan.md",2622,"https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fexamples\u002Fminimal-consumer\u002F.claude\u002Fskills\u002Fplan-grader\u002Freferences\u002Ftest-plan.md",[107,137,170,191,213,236],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":118,"publishedAt":39},"01M6XDQ7QMASPFZ355MYKCD06T","yolo","Start temporary autonomy for the current task or an explicit scope with a required --for expiry. Codex permits scoped pushes, merges, deploys, and releases after strict testing and validation; Full access is a separate runtime setting. Claude Code uses a session permission hook with a protected-action denylist.","https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fskills\u002Fyolo\u002FSKILL.md",[113],{"categoryNo":114,"categoryName":115,"taxonomyType":116,"taxonomyTypeDesc":117},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[109,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,25,136],"testing","merge","code","start","access","session","ops","autonomy","releases","permission","full","runtime","scope","devex","hook","true","action","scoped",{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":151,"publishedAt":39},"01M6XDQ1N21VE4KH98JWGZ7GN9","veracity-audit","Audit a data pipeline for Veracity and Value. Dispatches data-scientist, compliance-auditor, and data-engineer agents with project context injected at dispatch time. All source paths are supplied via flags — no defaults, no project assumptions. Subcommands: audit (full pipeline walk), score-check (scoring math only), gate-check (gate coverage only), source-trace \u003Clabel> (single source end-to-end). Invoke when: \"audit pipeline\", \"veracity check\", \"scoring math correct?\", \"check gates\", \"trace source\", \"verify quality gates\", \"formula correct?\".","https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fskills\u002Fveracity-audit\u002FSKILL.md",[143,148],{"categoryNo":144,"categoryName":145,"taxonomyType":146,"taxonomyTypeDesc":147},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":149,"categoryName":150,"taxonomyType":116,"taxonomyTypeDesc":117},"01JBSEEDCAT000000000000037","律师与法务",[152,153,119,154,155,156,34,157,158,159,160,161,162,163,164,165,166,167,168,169],"audit","veracity audit","review","data pipeline","pipeline","math","coverage","only","engineer","formula","scoring","time","project","worker","end","at","invoke","when",{"skillNo":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":176,"publishedAt":39},"01M6XDPVDKBR376C06CEK9BC5S","validate-spec","Audit an already-implemented spec against the codebase. Walks each constraint (ARCH-N, PERF-N, KD-N, etc.) and acceptance criterion, grounds findings in file:line evidence, runs the spec.json acceptance_commands, and writes a single audit doc to docs\u002Faudits\u002F. Use whenever the user asks to \"validate a spec\", \"audit a spec\", \"check if spec is implemented\", \"verify the spec is done\", \"is this spec really done\", or otherwise wants closure on spec-driven work. Read-only against the spec — produces an audit, never modifies the spec itself.","https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fskills\u002Fvalidate-spec\u002FSKILL.md",[],[177,178,179,119,154,180,181,152,34,182,22,183,159,184,185,186,187,188,189,190],"spec","validate","validate spec","run","acceptance","work","never","max","done","arch","line","2025","spec-driven","closure",{"skillNo":192,"name":193,"nameZh":6,"description":194,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":195,"categories":196,"keywords":200,"publishedAt":39},"01M6XDPMMECH82RAW553Y94HDS","terragrunt-specialist","Deep-dive Terragrunt hierarchy review, DRY pattern audits, and run-all orchestration analysis. Use for structured investigations of multi-environment Terragrunt layouts, dependency graphs, remote state config, and hook correctness. Triggers on: \"Terragrunt audit\", \"run-all review\", \"dependency block\", \"DRY pattern review\", \"env hierarchy audit\", \"mock_outputs\", \"terragrunt hooks\".","https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fskills\u002Fterragrunt-specialist\u002FSKILL.md",[197],{"categoryNo":198,"categoryName":199,"taxonomyType":146,"taxonomyTypeDesc":147},"01JBSEEDCAT000000000000011","运维与部署",[201,202,203,154,204,205,180,152,206,34,22,207,208,184,209,210,188,211,167,212],"terragrunt","specialist","terragrunt specialist","orchestration","debugging","analysis","dependency","hooks","deep","dry","remote","hierarchy",{"skillNo":214,"name":215,"nameZh":6,"description":216,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":217,"categories":218,"keywords":226,"publishedAt":39},"01M6XDPFJS2HGSE13RXF1HV8S7","terraform-specialist","Deep-dive Terraform architecture review, module design, state management, and migration. Use for structured investigations of Terraform workspaces, provider configuration, module coupling, import workflows, and test coverage. Triggers on: \"Terraform audit\", \"module review\", \"state management\", \"Terraform import\", \"workspace design\", \"provider config review\", \"Terraform testing\".","https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fskills\u002Fterraform-specialist\u002FSKILL.md",[219,222,223],{"categoryNo":220,"categoryName":221,"taxonomyType":146,"taxonomyTypeDesc":147},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":198,"categoryName":199,"taxonomyType":146,"taxonomyTypeDesc":147},{"categoryNo":224,"categoryName":225,"taxonomyType":146,"taxonomyTypeDesc":147},"01JBSEEDCAT000000000000015","视觉设计",[227,228,202,119,229,154,230,231,232,205,152,34,22,158,233,234,209,235,188,167],"terraform","terraform specialist","design","workflows","architecture","architecture review","test coverage","workspaces","problem",{"skillNo":237,"name":177,"nameZh":6,"description":238,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":239,"categories":240,"keywords":245,"publishedAt":39},"01M6XDP7V6H8WYPSXVEKYE6HJ6","Create structured engineering specs through interactive pairing. Use when the user wants to create a spec, design doc, technical specification, architecture document, RFC, or engineering plan. Triggers on \"let's spec this out\", \"create a spec\", \"design doc\", \"write a technical plan\", \"plan the architecture\". Works for greenfield and brownfield projects. Outputs to docs\u002Fspecs\u002F.","https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fskills\u002Fspec\u002FSKILL.md",[241,242],{"categoryNo":224,"categoryName":225,"taxonomyType":146,"taxonomyTypeDesc":147},{"categoryNo":243,"categoryName":244,"taxonomyType":116,"taxonomyTypeDesc":117},"01JBSEEDCAT000000000000032","设计师",[177,229,246,231,247,20,248,249,250,251,252,253,254,255,256,25,257,258,259,260],"component","create","projects","write","interactive","use","document","specification","triggers","opus","technical specification","trade-offs","technical plan","outputs","frontier"]