[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DXQ82PXAE3M0TC3ED5BQM8":3,"skill-same:01M6DXQ82PXAE3M0TC3ED5BQM8":102},{"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":23,"publishedAt":51,"linkOnly":52,"markdownContent":53,"markdownBody":54,"frontMatter":55,"refName":62,"commitSha":63,"skillDirectory":64,"forksCount":65,"repositoryHtmlUrl":66,"repositoryHomepageUrl":67,"ownerHtmlUrl":68,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":69,"install":70,"resources":83},"01M6DXQ82PXAE3M0TC3ED5BQM8","extract-adrs",null,"Extract architecture decision records from existing meta documents (research, plans). Scans documents for implicit or explicit architectural decisions and converts selected ones into formal ADRs. Use when decisions are buried in research or planning documents and need to be captured formally.","atomicinnovation\u002Faccelerator","atomicinnovation","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F65866524?v=4","01M6DXP513JV585FN2QPNR6079","Atomic","01M6DXP55MPK99YVZ2HGMEN991",34,"MIT","https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator\u002Fblob\u002Fmain\u002Fskills\u002Fdecisions\u002Fextract-adrs\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50],"extract adrs","extract","when","research","architecture decision","Existing","for","number","records","adr next","paths","plans","next","scan","use","decisions","decision","adr","Bash","doc","architecture decision records","Meta","planning","documents","config","architecture","validate","2026-11-10 10:12:30",false,"---\nname: extract-adrs\ndescription: Extract architecture decision records from existing meta documents\n  (research, plans). Scans documents for implicit or explicit architectural\n  decisions and converts selected ones into formal ADRs. Use when decisions are\n  buried in research or planning documents and need to be captured formally.\nargument-hint: \"[research doc paths...] or leave empty to scan all\"\nallowed-tools:\n  - Bash(accelerator config *)\n  - Bash(accelerator corpus adr next-number)\n  - Bash(accelerator corpus metadata derive)\n  - Bash(accelerator corpus frontmatter validate *)\n---\n\n# Extract ADRs from Meta Documents\n\n!`accelerator config context --skill extract-adrs --fail-safe`\n!`accelerator config agents --fail-safe`\n\nIf no \"Agent Names\" section appears above, use these defaults:\naccelerator:reviewer, accelerator:codebase-locator,\naccelerator:codebase-analyser, accelerator:codebase-pattern-finder,\naccelerator:documents-locator, accelerator:documents-analyser,\naccelerator:web-search-researcher.\n\n**Decisions directory**: !`accelerator config path decisions --fail-safe`\n**Codebase research directory**: !`accelerator config path research_codebase --fail-safe`\n**Plans directory**: !`accelerator config path plans --fail-safe`\n\nYou are tasked with identifying architectural decisions within existing meta\ndocuments and helping the user capture them as formal ADRs.\n\n## Initial Setup\n\nWhen this command is invoked:\n\n1. **Check if parameters were provided**:\n\n- If one or more file paths were provided, note them as the target documents\n- If no parameters provided, respond with:\n\n```\nI'll help you extract architectural decisions from existing documents.\n\nYou can:\n1. Specify documents to scan: `\u002Faccelerator:extract-adrs @{research directory}\u002F2026-03-18-auth-flow.md`\n2. Let me scan all documents in the configured directories for decisions (this may take a moment)\n\nWhich would you prefer?\n```\n\nWait for user input.\n\n## Process Steps\n\n### Step 1: Identify Source Documents\n\n1. If specific files were provided, read them FULLY\n2. If scanning all meta documents:\n   - Spawn a **{documents locator agent}** agent to find all documents in the\n     configured research, plans, and decisions directories (shown above)\n   - Present the discovered documents and let the user select which to scan:\n     ```\n     I found the following documents:\n\n     **Research:**\n     - `{research directory}\u002F2026-03-18-auth-flow.md` — Authentication flow research\n     - ...\n\n     **Plans:**\n     - `{plans directory}\u002F2026-03-18-api-redesign.md` — API redesign plan\n     - ...\n\n     Which documents should I scan for decisions? (enter numbers, \"all\", or\n     specific paths)\n     ```\n   - Wait for user selection\n\n### Step 2: Analyse Documents for Decisions\n\n1. **Spawn {documents analyser agent} agents** (one per document, in parallel) with\n   instructions to identify architectural decisions. Look for:\n\n   - Explicit decision statements (\"We decided...\", \"We will use...\",\n     \"The approach is...\")\n   - Option comparisons and tradeoffs (\"Option A vs Option B\",\n     \"We considered...\")\n   - Technology selections (\"We chose X\", \"Using Y because...\")\n   - Pattern\u002Fapproach choices (\"The pattern for this is...\",\n     \"We'll follow the X approach\")\n   - Constraint acknowledgements (\"Due to X, we must...\",\n     \"Given the constraint of...\")\n   - Recommendations with rationale (\"Recommendation: Use X because...\")\n\n2. **Wait for all agents to complete**\n\n3. **Present discovered decisions** as Y-statement summaries:\n\n```\nI found the following architectural decisions in the scanned documents:\n\n1. **[Short title]** — In the context of [X], facing [Y], we decided for [Z]\n   to achieve [Q], accepting [D].\n   Source: `{research directory}\u002F2026-03-18-topic.md`\n\n2. **[Short title]** — In the context of [X], facing [Y], we decided for [Z]\n   to achieve [Q], accepting [D].\n   Source: `{plans directory}\u002F2026-03-18-topic.md`\n\n3. ...\n\nWhich decisions would you like to capture as ADRs? (enter numbers, \"all\",\nor \"none\")\n```\n\nWait for user selection.\n\n### Step 3: Generate ADRs\n\n1. **Gather metadata** by running\n   `accelerator corpus metadata derive`.\n\n2. **For each selected decision**, generate a draft ADR using the create-adr\n   template with:\n   - Context pre-filled from the source document\n   - Decision drivers extracted from the document's analysis\n   - Considered options populated if the source discusses alternatives\n   - Consequences derived from the document's findings\n   - References linking back to the source document\n   - Use a placeholder number (e.g., `ADR-XXXX`) in the draft — final numbers\n     are assigned after approval to avoid gaps from skipped ADRs\n\n3. **Present each generated ADR** for user review:\n   ```\n   Here's draft ADR #N of M:\n\n   [ADR content with placeholder number]\n\n   Does this look good? (yes \u002F revise \u002F skip \u002F approve all remaining)\n   ```\n\n   Wait for approval before proceeding. If the user selects \"approve all\n   remaining\", accept all subsequent drafts without further prompts.\n\n4. **Assign final ADR numbers** to approved ADRs only, by running:\n   ```\n   accelerator corpus adr next-number --count N\n   ```\n   where N is the number of approved (not skipped) ADRs. Replace placeholder\n   numbers with the assigned sequential numbers. This ensures no gaps from\n   skipped decisions.\n\n### Step 4: Write ADRs\n\n1. Create the configured decisions directory if it doesn't exist\n\n2. **Populate frontmatter** for each approved ADR. Before writing the\n   file, capture metadata and substitute the unified base fields into\n   the template's frontmatter block:\n\n   1. Invoke `accelerator corpus metadata derive`\n      once for the batch to obtain `Current Date\u002FTime (UTC):`.\n   2. For each approved ADR, **substitute** every field below with the\n      indicated value:\n      - `type:` ← `adr`\n      - `id:` ← the ADR identifier `ADR-NNNN`, always quoted as a\n        YAML string\n      - `title:` ← the ADR title (without the `ADR-NNNN:` prefix)\n      - `date:` ← the `Current Date\u002FTime (UTC):` value\n      - `author:` ← the author resolved per the standard chain\n        (config → VCS user → prompt)\n      - `producer:` ← `extract-adrs`\n      - `status:` ← `proposed`\n      - `last_updated:` ← the same `Current Date\u002FTime (UTC):` value\n      - `last_updated_by:` ← the same value resolved for `author`\n      - `schema_version:` ← `1` (bare integer)\n\n      Optional linkage \u002F decision-maker keys are omit-by-default:\n      the template shows each as `\"\"`\u002F`[]`, but write a key\n      into the artifact **only** when it has a value, and omit it\n      entirely otherwise (do not carry the empty placeholder through).\n\n      - `parent:` ← the owning work item as a typed-linkage ref\n        (`\"work-item:NNNN\"`). Fill when the source names an owning work\n        item; otherwise omit the key.\n      - `supersedes:` ← a YAML list of typed-linkage refs of the form\n        `\"adr:ADR-NNNN\"` to the ADR(s) this one replaces. Fill when the\n        source records a supersession; otherwise omit the key.\n      - `relates_to:` ← list of typed-linkage refs to loosely related\n        ADRs (`[\"adr:ADR-NNNN\", ...]`). Fill when related decisions are\n        explicit in the source; otherwise omit the key.\n      - `decision_makers:` ← a YAML list of the people who agreed. Fill\n        when the source names them; otherwise omit the key.\n\n3. Write each approved ADR to:\n   `{decisions directory}\u002FADR-NNNN-description.md`\n\n4. Present summary:\n   ```\n   Created the following ADRs:\n   - `{decisions directory}\u002FADR-0001-description.md` — [title]\n   - `{decisions directory}\u002FADR-0002-description.md` — [title]\n   - ...\n\n   All ADRs are in \"proposed\" status. Use `\u002Faccelerator:review-adr` to\n   review and accept them.\n   ```\n\n**Validate the frontmatter**: after writing each ADR, run\n\n```bash\naccelerator corpus frontmatter validate --file {decisions directory}\u002FADR-NNNN-description.md\n```\n\nIf it exits non-zero, that ADR violates the canonical frontmatter standard;\nreport the emitted violation and fix the frontmatter before completing.\n\n## ADR Template\n\nThe ADR template is loaded directly via the template loader so the\nshape stays in sync with `create-adr`:\n\n!`accelerator config template adr --fail-safe`\n\nWhen populating the template from extracted decisions:\n\n- **Context**: Extracted from the source document's forces and constraints\n- **Decision Drivers**: Extracted from the document's analysis\n- **Considered Options**: Populated if the source discusses alternatives\n- **Decision**: Stated or implied decision, rewritten in active voice\n- **Consequences**: Derived from the document's findings\n- **References**: Always link back to the source document\n\n## Important Notes\n\n- Decisions should be **architecturally significant** — not every choice is\n  worth an ADR. Help the user distinguish between significant decisions and\n  routine implementation choices.\n- Extracted ADRs always start with status `proposed` — extraction is discovery,\n  not acceptance.\n- Preserve the source document's context faithfully — don't invent rationale\n  that wasn't in the original.\n- Cross-reference bidirectionally: the ADR references the source, and the user\n  may wish to note the ADR in the source document.\n- When extracting from a single document, multiple decisions may be found —\n  each becomes a separate ADR.\n- Use sequential numbering: determine the starting number once, then increment\n  for batch creation.\n\n!`accelerator config instructions extract-adrs --fail-safe`\n","# Extract ADRs from Meta Documents\n\n!`accelerator config context --skill extract-adrs --fail-safe`\n!`accelerator config agents --fail-safe`\n\nIf no \"Agent Names\" section appears above, use these defaults:\naccelerator:reviewer, accelerator:codebase-locator,\naccelerator:codebase-analyser, accelerator:codebase-pattern-finder,\naccelerator:documents-locator, accelerator:documents-analyser,\naccelerator:web-search-researcher.\n\n**Decisions directory**: !`accelerator config path decisions --fail-safe`\n**Codebase research directory**: !`accelerator config path research_codebase --fail-safe`\n**Plans directory**: !`accelerator config path plans --fail-safe`\n\nYou are tasked with identifying architectural decisions within existing meta\ndocuments and helping the user capture them as formal ADRs.\n\n## Initial Setup\n\nWhen this command is invoked:\n\n1. **Check if parameters were provided**:\n\n- If one or more file paths were provided, note them as the target documents\n- If no parameters provided, respond with:\n\n```\nI'll help you extract architectural decisions from existing documents.\n\nYou can:\n1. Specify documents to scan: `\u002Faccelerator:extract-adrs @{research directory}\u002F2026-03-18-auth-flow.md`\n2. Let me scan all documents in the configured directories for decisions (this may take a moment)\n\nWhich would you prefer?\n```\n\nWait for user input.\n\n## Process Steps\n\n### Step 1: Identify Source Documents\n\n1. If specific files were provided, read them FULLY\n2. If scanning all meta documents:\n   - Spawn a **{documents locator agent}** agent to find all documents in the\n     configured research, plans, and decisions directories (shown above)\n   - Present the discovered documents and let the user select which to scan:\n     ```\n     I found the following documents:\n\n     **Research:**\n     - `{research directory}\u002F2026-03-18-auth-flow.md` — Authentication flow research\n     - ...\n\n     **Plans:**\n     - `{plans directory}\u002F2026-03-18-api-redesign.md` — API redesign plan\n     - ...\n\n     Which documents should I scan for decisions? (enter numbers, \"all\", or\n     specific paths)\n     ```\n   - Wait for user selection\n\n### Step 2: Analyse Documents for Decisions\n\n1. **Spawn {documents analyser agent} agents** (one per document, in parallel) with\n   instructions to identify architectural decisions. Look for:\n\n   - Explicit decision statements (\"We decided...\", \"We will use...\",\n     \"The approach is...\")\n   - Option comparisons and tradeoffs (\"Option A vs Option B\",\n     \"We considered...\")\n   - Technology selections (\"We chose X\", \"Using Y because...\")\n   - Pattern\u002Fapproach choices (\"The pattern for this is...\",\n     \"We'll follow the X approach\")\n   - Constraint acknowledgements (\"Due to X, we must...\",\n     \"Given the constraint of...\")\n   - Recommendations with rationale (\"Recommendation: Use X because...\")\n\n2. **Wait for all agents to complete**\n\n3. **Present discovered decisions** as Y-statement summaries:\n\n```\nI found the following architectural decisions in the scanned documents:\n\n1. **[Short title]** — In the context of [X], facing [Y], we decided for [Z]\n   to achieve [Q], accepting [D].\n   Source: `{research directory}\u002F2026-03-18-topic.md`\n\n2. **[Short title]** — In the context of [X], facing [Y], we decided for [Z]\n   to achieve [Q], accepting [D].\n   Source: `{plans directory}\u002F2026-03-18-topic.md`\n\n3. ...\n\nWhich decisions would you like to capture as ADRs? (enter numbers, \"all\",\nor \"none\")\n```\n\nWait for user selection.\n\n### Step 3: Generate ADRs\n\n1. **Gather metadata** by running\n   `accelerator corpus metadata derive`.\n\n2. **For each selected decision**, generate a draft ADR using the create-adr\n   template with:\n   - Context pre-filled from the source document\n   - Decision drivers extracted from the document's analysis\n   - Considered options populated if the source discusses alternatives\n   - Consequences derived from the document's findings\n   - References linking back to the source document\n   - Use a placeholder number (e.g., `ADR-XXXX`) in the draft — final numbers\n     are assigned after approval to avoid gaps from skipped ADRs\n\n3. **Present each generated ADR** for user review:\n   ```\n   Here's draft ADR #N of M:\n\n   [ADR content with placeholder number]\n\n   Does this look good? (yes \u002F revise \u002F skip \u002F approve all remaining)\n   ```\n\n   Wait for approval before proceeding. If the user selects \"approve all\n   remaining\", accept all subsequent drafts without further prompts.\n\n4. **Assign final ADR numbers** to approved ADRs only, by running:\n   ```\n   accelerator corpus adr next-number --count N\n   ```\n   where N is the number of approved (not skipped) ADRs. Replace placeholder\n   numbers with the assigned sequential numbers. This ensures no gaps from\n   skipped decisions.\n\n### Step 4: Write ADRs\n\n1. Create the configured decisions directory if it doesn't exist\n\n2. **Populate frontmatter** for each approved ADR. Before writing the\n   file, capture metadata and substitute the unified base fields into\n   the template's frontmatter block:\n\n   1. Invoke `accelerator corpus metadata derive`\n      once for the batch to obtain `Current Date\u002FTime (UTC):`.\n   2. For each approved ADR, **substitute** every field below with the\n      indicated value:\n      - `type:` ← `adr`\n      - `id:` ← the ADR identifier `ADR-NNNN`, always quoted as a\n        YAML string\n      - `title:` ← the ADR title (without the `ADR-NNNN:` prefix)\n      - `date:` ← the `Current Date\u002FTime (UTC):` value\n      - `author:` ← the author resolved per the standard chain\n        (config → VCS user → prompt)\n      - `producer:` ← `extract-adrs`\n      - `status:` ← `proposed`\n      - `last_updated:` ← the same `Current Date\u002FTime (UTC):` value\n      - `last_updated_by:` ← the same value resolved for `author`\n      - `schema_version:` ← `1` (bare integer)\n\n      Optional linkage \u002F decision-maker keys are omit-by-default:\n      the template shows each as `\"\"`\u002F`[]`, but write a key\n      into the artifact **only** when it has a value, and omit it\n      entirely otherwise (do not carry the empty placeholder through).\n\n      - `parent:` ← the owning work item as a typed-linkage ref\n        (`\"work-item:NNNN\"`). Fill when the source names an owning work\n        item; otherwise omit the key.\n      - `supersedes:` ← a YAML list of typed-linkage refs of the form\n        `\"adr:ADR-NNNN\"` to the ADR(s) this one replaces. Fill when the\n        source records a supersession; otherwise omit the key.\n      - `relates_to:` ← list of typed-linkage refs to loosely related\n        ADRs (`[\"adr:ADR-NNNN\", ...]`). Fill when related decisions are\n        explicit in the source; otherwise omit the key.\n      - `decision_makers:` ← a YAML list of the people who agreed. Fill\n        when the source names them; otherwise omit the key.\n\n3. Write each approved ADR to:\n   `{decisions directory}\u002FADR-NNNN-description.md`\n\n4. Present summary:\n   ```\n   Created the following ADRs:\n   - `{decisions directory}\u002FADR-0001-description.md` — [title]\n   - `{decisions directory}\u002FADR-0002-description.md` — [title]\n   - ...\n\n   All ADRs are in \"proposed\" status. Use `\u002Faccelerator:review-adr` to\n   review and accept them.\n   ```\n\n**Validate the frontmatter**: after writing each ADR, run\n\n```bash\naccelerator corpus frontmatter validate --file {decisions directory}\u002FADR-NNNN-description.md\n```\n\nIf it exits non-zero, that ADR violates the canonical frontmatter standard;\nreport the emitted violation and fix the frontmatter before completing.\n\n## ADR Template\n\nThe ADR template is loaded directly via the template loader so the\nshape stays in sync with `create-adr`:\n\n!`accelerator config template adr --fail-safe`\n\nWhen populating the template from extracted decisions:\n\n- **Context**: Extracted from the source document's forces and constraints\n- **Decision Drivers**: Extracted from the document's analysis\n- **Considered Options**: Populated if the source discusses alternatives\n- **Decision**: Stated or implied decision, rewritten in active voice\n- **Consequences**: Derived from the document's findings\n- **References**: Always link back to the source document\n\n## Important Notes\n\n- Decisions should be **architecturally significant** — not every choice is\n  worth an ADR. Help the user distinguish between significant decisions and\n  routine implementation choices.\n- Extracted ADRs always start with status `proposed` — extraction is discovery,\n  not acceptance.\n- Preserve the source document's context faithfully — don't invent rationale\n  that wasn't in the original.\n- Cross-reference bidirectionally: the ADR references the source, and the user\n  may wish to note the ADR in the source document.\n- When extracting from a single document, multiple decisions may be found —\n  each becomes a separate ADR.\n- Use sequential numbering: determine the starting number once, then increment\n  for batch creation.\n\n!`accelerator config instructions extract-adrs --fail-safe`\n",{"name":5,"description":7,"allowed-tools":56,"argument-hint":61},[57,58,59,60],"Bash(accelerator config *)","Bash(accelerator corpus adr next-number)","Bash(accelerator corpus metadata derive)","Bash(accelerator corpus frontmatter validate *)","[research doc paths...] or leave empty to scan all","main","007b2dd695b63c2f097cdc40e54229b6e8b4596a","skills\u002Fdecisions\u002Fextract-adrs",2,"https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator","https:\u002F\u002Fgo-atomic.io","https:\u002F\u002Fgithub.com\u002Fatomicinnovation","2026-11-13 08:45:04",{"source":8,"skillName":5,"commands":71,"prompt":81,"zipAvailable":82},[72,75,78],{"tool":73,"command":74},"npx","npx skills add atomicinnovation\u002Faccelerator --skill extract-adrs",{"tool":76,"command":77},"bunx","bunx skills add atomicinnovation\u002Faccelerator --skill extract-adrs",{"tool":79,"command":80},"pnpm","pnpm dlx skills add atomicinnovation\u002Faccelerator --skill extract-adrs","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator\u002Fblob\u002Fmain\u002Fskills\u002Fdecisions\u002Fextract-adrs\u002FSKILL.md",true,[84,90,94,98],{"path":85,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Fevidence-and-so-what.md","REFERENCE","参考文档",9063,"https:\u002F\u002Fgithub.com\u002Ffranklee16\u002Facademic-research-skills\u002Fblob\u002Fmaster\u002Fpaper-writing\u002Fpractitioner-finance-voice\u002Freferences\u002Fevidence-and-so-what.md",{"path":91,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002Fexemplars.md",17000,"https:\u002F\u002Fgithub.com\u002Ffranklee16\u002Facademic-research-skills\u002Fblob\u002Fmaster\u002Fpaper-writing\u002Fpractitioner-finance-voice\u002Freferences\u002Fexemplars.md",{"path":95,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":96,"sourceHtmlUrl":97},"references\u002Fstructure-and-framing.md",9712,"https:\u002F\u002Fgithub.com\u002Ffranklee16\u002Facademic-research-skills\u002Fblob\u002Fmaster\u002Fpaper-writing\u002Fpractitioner-finance-voice\u002Freferences\u002Fstructure-and-framing.md",{"path":99,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":100,"sourceHtmlUrl":101},"references\u002Fvoice-and-register.md",9497,"https:\u002F\u002Fgithub.com\u002Ffranklee16\u002Facademic-research-skills\u002Fblob\u002Fmaster\u002Fpaper-writing\u002Fpractitioner-finance-voice\u002Freferences\u002Fvoice-and-register.md",[103,134,155,176,193,218],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":117,"publishedAt":51},"01M70S7PFGVATJREBFEGPJB718","explore-pr","Build an interactive, design-first and picture-first exploration page for a pull request — its architecture, abstractions and design decisions drawn as diagrams, a guided tour in reading order with code as the evidence, an attention map of where the risk sits, a ledger of its riskiest operations, prior review findings re-checked against the code, and simulations specific to the PR — with the reviewer's verdicts and notes saved. Use when the user wants to explore, understand or review a large pull request or its design, asks for a review page, walkthrough or visual explanation of a PR, or is struggling to review a big change.","https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fexplore-pr\u002FSKILL.md",[109,112],{"categoryNo":110,"categoryName":111,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":113,"categoryName":114,"taxonomyType":115,"taxonomyTypeDesc":116},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[118,119,120,121,122,123,124,125,126,127,26,31,128,42,129,49,130,131,132,133],"explore pr","explore","pr","diagrams","exploration","re","review findings","walkthrough","design","map","URL","code","reviewer","review","notes","change",{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":140,"publishedAt":51},"01M6DY04WBTMFV96JMBP5ZXVFX","update-work-item","Update fields (status, priority, tags, parent, etc.) of an existing work item. Use to transition status, change priority, manage tags, or edit any frontmatter field. No transition enforcement — arbitrary changes are allowed.","https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator\u002Fblob\u002Fmain\u002Fskills\u002Fwork\u002Fupdate-work-item\u002FSKILL.md",[],[141,142,143,144,145,146,38,42,133,48,147,50,148,149,150,29,151,152,153,154],"work","update","update work item","work item","enforcement","manage","edit","status","transition","frontmatter","tags","changes","fields","op",{"skillNo":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":161,"publishedAt":51},"01M6DY0106CF15CYEJHZM14GBZ","sync-work-items","Reconcile local work items in meta\u002Fwork\u002F with the active remote tracker named by work.integration. Use when the user wants to sync, push, or pull work items to or from Jira or Linear, preview what a sync would change, or reconcile divergent local and remote state.","https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator\u002Fblob\u002Fmain\u002Fskills\u002Fwork\u002Fsync-work-items\u002FSKILL.md",[],[141,162,163,164,45,165,166,42,167,133,168,169,170,171,172,173,174,48,175,150,26],"sync","sync work items","promote","local","only","preview","active","tracker","max","jira","remote","create","adopt","reconcile",{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":182,"publishedAt":51},"01M6HNF86984S4XK21Q26VZA21","sync-work-items-recovery","Recovery procedures for work sync failures that need a person — terminal rows, refused pending pushes and refused orders. Read by sync-work-items — not invoked directly.","https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator\u002Fblob\u002Fmain\u002Fskills\u002Fwork\u002Fsync-work-items-recovery\u002FSKILL.md",[],[183,141,184,162,163,185,30,186,187,188,189,190,191,192],"sync work items recovery","recovery","work-items","terminal","read","person","true","false","orders","pending",{"skillNo":194,"name":195,"nameZh":6,"description":196,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":197,"categories":198,"keywords":202,"publishedAt":51},"01M6DXZWH7PR72VCEXSSD4XNK4","stress-test-work-item","Interactively stress-test a work item by grilling the user on scope, assumptions, acceptance criteria, edge cases, and dependencies to surface issues, gaps, and flawed assumptions before implementation is planned.","https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator\u002Fblob\u002Fmain\u002Fskills\u002Fwork\u002Fstress-test-work-item\u002FSKILL.md",[199],{"categoryNo":200,"categoryName":201,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[203,204,141,205,144,206,207,208,209,210,211,42,212,213,48,50,214,215,216,31,217,150],"stress test","test","stress test work item","stress","scope","issues","edge","stress-test","acceptance","acceptance criteria","dependencies","implementation","grilling","user","gaps",{"skillNo":219,"name":220,"nameZh":6,"description":221,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":222,"categories":223,"keywords":224,"publishedAt":51},"01M6DXZRQWHTWV1G9PTTHCGGYA","review-work-item","Review a work item through multiple quality lenses and collaboratively iterate based on findings. Use when the user wants to evaluate a work item before implementation or escalation.","https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator\u002Fblob\u002Fmain\u002Fskills\u002Fwork\u002Freview-work-item\u002FSKILL.md",[],[131,141,225,144,226,227,38,42,228,229,48,50,214,216,230,26,231,232,150,233],"review work item","review work","escalation","file","quality","metadata","iterate","evaluate","path"]