[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DXQEXW6135RHSF8JXP6VAT":3,"skill-same:01M6DXQEXW6135RHSF8JXP6VAT":101},{"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":28,"publishedAt":58,"linkOnly":59,"markdownContent":60,"markdownBody":61,"frontMatter":62,"refName":70,"commitSha":71,"skillDirectory":72,"forksCount":73,"repositoryHtmlUrl":74,"repositoryHomepageUrl":75,"ownerHtmlUrl":76,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":77,"install":78,"resources":90},"01M6DXQEXW6135RHSF8JXP6VAT","analyse-design-gaps",null,"Compare two design inventories produced by inventory-design and emit a structured gap artefact whose prose paragraphs satisfy the extract-work-items cue-phrase contract. Use after running inventory-design for both a current and target design surface. The resulting gap artefact under meta\u002Fdesign-gaps\u002F feeds directly into \u002Faccelerator:extract-work-items to produce actionable work items.","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\u002Fdesign\u002Fanalyse-design-gaps\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57],"analyse","gaps","analyse design gaps","design","structured","running","frontmatter","source","for","true","work-items","actionable","id","gap","cue","contract","prose","use","extract","work","Bash","inventory","feeds","Meta","metadata","produce","target design","config","validate","2026-11-10 10:12:30",false,"---\nname: analyse-design-gaps\ndescription: Compare two design inventories produced by inventory-design and emit\n  a structured gap artefact whose prose paragraphs satisfy the extract-work-items\n  cue-phrase contract. Use after running inventory-design for both a current and\n  target design surface. The resulting gap artefact under meta\u002Fdesign-gaps\u002F feeds\n  directly into \u002Faccelerator:extract-work-items to produce actionable work items.\nargument-hint: \"[current-source-id] [target-source-id]\"\ndisable-model-invocation: true\nallowed-tools:\n  - Bash(accelerator config *)\n  - Bash(accelerator design *)\n  - Bash(accelerator corpus metadata derive *)\n  - Bash(accelerator corpus frontmatter validate *)\n---\n\n# Analyse Design Gaps\n\n!`accelerator config context --skill analyse-design-gaps --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**Design inventories directory**: !`accelerator config path research_design_inventories --fail-safe`\n**Design gaps directory**: !`accelerator config path research_design_gaps --fail-safe`\n\nYou are tasked with comparing two design inventories and producing a structured\n`design-gap` artifact. The artifact's prose paragraphs must satisfy the\n`extract-work-items` cue-phrase contract so they flow into the work-item\nlifecycle without manual editing.\n\n## Steps\n\n### 1. Resolve Each Source-Id to Its Inventory\n\nFor each of `[current-source-id]` and `[target-source-id]`:\n\n**a. Validate format**: must match `^[a-z0-9][a-z0-9-]*$`. Report a clear error\nnaming offending characters if not.\n\n**b. Glob** `\u003Cdesign_inventories>\u002F*-{source-id}\u002F` (excluding leading-dot directories).\n\n**c. Zero matches**: exit non-zero with:\n> `error: source-id '\u003Cid>' did not match any inventory under \u003Croot>. Available\n> source-ids: \u003Ccomma-separated list>. Run \u002Faccelerator:inventory-design \u003Cid>\n> \u003Clocation> first.`\n\n**d. Read frontmatter** for each match. If an `inventory.md` is missing,\nunparseable, or lacks a `status` field, treat it as `superseded` and log a\none-line warning naming the directory.\n\n**e. Filter to `status != superseded`** (also exclude leading-dot directories).\nIf multiple remain (crashed prior supersede step), apply the resolver tiebreaker:\n1. Highest `sequence` number in frontmatter (primary — robust against clock skew)\n2. Directory mtime, newest first (secondary — for equal-sequence concurrent writes)\n3. `YYYY-MM-DD-HHMMSS` directory-name prefix, newest first (final)\n\nEmit a one-line warning naming any non-selected directories when more than one\nremained after filtering.\n\n**f. Record** the resolved absolute paths in the gap artifact frontmatter as\n`current_inventory` and `target_inventory`.\n\n### 2. Read Both Inventories\n\nRead each resolved `inventory.md` in full into context.\n\n### 3. Compute Structural Diff\n\nCompare the two inventories across five categories:\n\n1. **Token Drift** — colour, typography, spacing tokens present in current but\n   missing from target, or vice-versa; tokens with changed values\n2. **Component Drift** — components present in both but with structural changes\n   (variant count, prop changes, composition changes)\n3. **Screen Drift** — screens\u002Froutes that have changed navigation structure,\n   state matrix, or layout\n4. **Net-New Features** — features present in target but not in current\n5. **Removed Features** — features present in current but not in target\n\nIf a category has no differences, omit its H2 section from the artifact rather\nthan writing an empty section.\n\n### 4. Write Gap Prose\n\nFor each non-empty category, write at least one paragraph whose prose satisfies\nthe cue-phrase contract used by `extract-work-items`. Each paragraph must contain\none or more of:\n- \"we need to …\" \u002F \"we need a …\"\n- \"users need …\"\n- \"the system must …\"\n- \"Implement \u003CProperNoun> …\" (capital letter on the named feature)\n\n**Guidance per category**:\n- **Token Drift**: describe specific tokens to migrate, add, or remove. Example:\n  \"We need to migrate the 14-colour primary scale to the 8-token system defined\n  in the target.\"\n- **Component Drift**: describe the structural changes needed. Example:\n  \"Users need a five-variant Button — the current implementation has two variants\n  while the target design specifies five.\"\n- **Screen Drift**: describe changes to navigation structure or states. Example:\n  \"The system must support a redesigned Settings navigation pattern matching the\n  target's two-level sidebar.\"\n- **Net-New Features**: introduce the feature and its scope. Example:\n  \"Implement Search to expose Cmd+K activation, query input, and recent-history\n  preview panels.\"\n- **Removed Features**: flag for confirmation before removal. Example:\n  \"The legacy Analytics tab is present in the current implementation but absent\n  from the target. We need to confirm with stakeholders whether it should be\n  removed before proceeding.\"\n\nAvoid bare structural headings without actionable content. Every non-empty H2\nmust contain at least one paragraph meeting the cue-phrase contract.\n\n### 5. Run Cue-Phrase Audit\n\nAfter generating the gap body, run:\n```bash\naccelerator design audit-cue-phrases \"\u003Cdraft-body-path>\"\n```\n\n**On exit 2** (usage error — the file could not be read at all): report the\nerror to the user and stop. There are no offending sections to revise.\n\n**On exit 1**: the audit names the offending H2 sections. Revise only those\nsections while keeping passing sections byte-identical. Re-run the audit. After\nthree consecutive failures, write the rejected body to:\n```\n\u003Cdesign_gaps>\u002F.YYYY-MM-DD-{current-source-id}-vs-{target-source-id}.draft.md\n```\nwith a note at the top naming the failed sections, then report the failure and\nthe draft path to the user. Do not write the artifact to its final path.\n\nThe frontmatter timestamp is generated once before the first write attempt and\nreused across retries.\n\n### 6. Generate Metadata\n\nRun:\n```bash\naccelerator corpus metadata derive --filename-timestamp-format date-only\n```\n\n### 7. Populate frontmatter and write artifact\n\nUse the `design-gap` template:\n```\n!`accelerator config template design-gap --fail-safe`\n```\n\nBefore writing the artifact file, **substitute** every field below\nwith the indicated value, using the helper output captured in\nStep 6 (`Current Date\u002FTime (UTC):`):\n\n- `type:` ← `design-gap`\n- `id:` ← the filename stem (the file path computed below without\n  `.md`), always quoted as a YAML string\n- `title:` ← `Design Gap Analysis: {current-source} → {target-source}`\n- `date:` ← the `Current Date\u002FTime (UTC):` value\n- `author:` ← the author resolved per the standard chain (config →\n  VCS user → prompt)\n- `producer:` ← `analyse-design-gaps`\n- `status:` ← `draft`\n- `current_inventory:` ← the resolved absolute path to the current\n  inventory's `inventory.md`\n- `target_inventory:` ← the resolved absolute path to the target\n  inventory's `inventory.md`\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\nOptional linkage keys are omit-by-default (ADR-0040): the template shows\neach as `\"\"`\u002F`[]`, but write a key into the artifact **only** when it has\na value, and omit it entirely otherwise (do not carry the empty\nplaceholder through). The `current_inventory:` \u002F `target_inventory:`\nkeys above are always-valued and not subject to this rule.\n\n- `parent:` ← the work item this gap analysis supports, as a\n  typed-linkage ref (`\"work-item:NNNN\"`). Fill when the analysis has an\n  owning work item; otherwise omit the key.\n- `relates_to:` ← list of typed-linkage refs to related artifacts\n  (`[\"design-inventory:NNNN\", ...]`). Fill when relationships are\n  explicit; otherwise omit the key.\n\nThe design-gap artifact is not code-state-anchored — the helper's\n`Current Revision:` and `Repository Name:` output is ignored here\neven when present.\n\nWrite to:\n```\n\u003Cdesign_gaps>\u002FYYYY-MM-DD-{current-source-id}-vs-{target-source-id}.md\n```\n\nThe `References` section must record:\n- The resolved inventory directory path for each source-id\n- Any resolver warnings emitted in Step 1\n\n**Validate the frontmatter**: after writing the artifact, run\n\n```bash\naccelerator corpus frontmatter validate --file \u003Cpath>\n```\n\nIf it exits non-zero, the document violates the canonical frontmatter\nstandard; report the emitted violation and fix the frontmatter before\ncompleting.\n\n### 8. Present Summary\n\nReport:\n- The artifact path\n- Count of non-empty drift categories\n- Any resolver warnings (multi-match or corrupt-frontmatter)\n- Whether the cue-phrase audit required revisions\n\nSuggest next steps:\n- Run `\u002Faccelerator:extract-work-items \u003Cgap-file>` to generate work items\n\n## Important Guidelines\n\n- Empty drift categories are omitted — do not write placeholder sections.\n- The `sequence` tiebreaker is authoritative; do not rely on directory-name date\n  alone.\n- Never fabricate observations. Write only what differs between the two inventories.\n- The cue-phrase audit is programmatic enforcement, not a style suggestion. Revise\n  failing sections until the audit passes or the three-attempt limit is reached.\n\n!`accelerator config instructions analyse-design-gaps --fail-safe`\n","# Analyse Design Gaps\n\n!`accelerator config context --skill analyse-design-gaps --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**Design inventories directory**: !`accelerator config path research_design_inventories --fail-safe`\n**Design gaps directory**: !`accelerator config path research_design_gaps --fail-safe`\n\nYou are tasked with comparing two design inventories and producing a structured\n`design-gap` artifact. The artifact's prose paragraphs must satisfy the\n`extract-work-items` cue-phrase contract so they flow into the work-item\nlifecycle without manual editing.\n\n## Steps\n\n### 1. Resolve Each Source-Id to Its Inventory\n\nFor each of `[current-source-id]` and `[target-source-id]`:\n\n**a. Validate format**: must match `^[a-z0-9][a-z0-9-]*$`. Report a clear error\nnaming offending characters if not.\n\n**b. Glob** `\u003Cdesign_inventories>\u002F*-{source-id}\u002F` (excluding leading-dot directories).\n\n**c. Zero matches**: exit non-zero with:\n> `error: source-id '\u003Cid>' did not match any inventory under \u003Croot>. Available\n> source-ids: \u003Ccomma-separated list>. Run \u002Faccelerator:inventory-design \u003Cid>\n> \u003Clocation> first.`\n\n**d. Read frontmatter** for each match. If an `inventory.md` is missing,\nunparseable, or lacks a `status` field, treat it as `superseded` and log a\none-line warning naming the directory.\n\n**e. Filter to `status != superseded`** (also exclude leading-dot directories).\nIf multiple remain (crashed prior supersede step), apply the resolver tiebreaker:\n1. Highest `sequence` number in frontmatter (primary — robust against clock skew)\n2. Directory mtime, newest first (secondary — for equal-sequence concurrent writes)\n3. `YYYY-MM-DD-HHMMSS` directory-name prefix, newest first (final)\n\nEmit a one-line warning naming any non-selected directories when more than one\nremained after filtering.\n\n**f. Record** the resolved absolute paths in the gap artifact frontmatter as\n`current_inventory` and `target_inventory`.\n\n### 2. Read Both Inventories\n\nRead each resolved `inventory.md` in full into context.\n\n### 3. Compute Structural Diff\n\nCompare the two inventories across five categories:\n\n1. **Token Drift** — colour, typography, spacing tokens present in current but\n   missing from target, or vice-versa; tokens with changed values\n2. **Component Drift** — components present in both but with structural changes\n   (variant count, prop changes, composition changes)\n3. **Screen Drift** — screens\u002Froutes that have changed navigation structure,\n   state matrix, or layout\n4. **Net-New Features** — features present in target but not in current\n5. **Removed Features** — features present in current but not in target\n\nIf a category has no differences, omit its H2 section from the artifact rather\nthan writing an empty section.\n\n### 4. Write Gap Prose\n\nFor each non-empty category, write at least one paragraph whose prose satisfies\nthe cue-phrase contract used by `extract-work-items`. Each paragraph must contain\none or more of:\n- \"we need to …\" \u002F \"we need a …\"\n- \"users need …\"\n- \"the system must …\"\n- \"Implement \u003CProperNoun> …\" (capital letter on the named feature)\n\n**Guidance per category**:\n- **Token Drift**: describe specific tokens to migrate, add, or remove. Example:\n  \"We need to migrate the 14-colour primary scale to the 8-token system defined\n  in the target.\"\n- **Component Drift**: describe the structural changes needed. Example:\n  \"Users need a five-variant Button — the current implementation has two variants\n  while the target design specifies five.\"\n- **Screen Drift**: describe changes to navigation structure or states. Example:\n  \"The system must support a redesigned Settings navigation pattern matching the\n  target's two-level sidebar.\"\n- **Net-New Features**: introduce the feature and its scope. Example:\n  \"Implement Search to expose Cmd+K activation, query input, and recent-history\n  preview panels.\"\n- **Removed Features**: flag for confirmation before removal. Example:\n  \"The legacy Analytics tab is present in the current implementation but absent\n  from the target. We need to confirm with stakeholders whether it should be\n  removed before proceeding.\"\n\nAvoid bare structural headings without actionable content. Every non-empty H2\nmust contain at least one paragraph meeting the cue-phrase contract.\n\n### 5. Run Cue-Phrase Audit\n\nAfter generating the gap body, run:\n```bash\naccelerator design audit-cue-phrases \"\u003Cdraft-body-path>\"\n```\n\n**On exit 2** (usage error — the file could not be read at all): report the\nerror to the user and stop. There are no offending sections to revise.\n\n**On exit 1**: the audit names the offending H2 sections. Revise only those\nsections while keeping passing sections byte-identical. Re-run the audit. After\nthree consecutive failures, write the rejected body to:\n```\n\u003Cdesign_gaps>\u002F.YYYY-MM-DD-{current-source-id}-vs-{target-source-id}.draft.md\n```\nwith a note at the top naming the failed sections, then report the failure and\nthe draft path to the user. Do not write the artifact to its final path.\n\nThe frontmatter timestamp is generated once before the first write attempt and\nreused across retries.\n\n### 6. Generate Metadata\n\nRun:\n```bash\naccelerator corpus metadata derive --filename-timestamp-format date-only\n```\n\n### 7. Populate frontmatter and write artifact\n\nUse the `design-gap` template:\n```\n!`accelerator config template design-gap --fail-safe`\n```\n\nBefore writing the artifact file, **substitute** every field below\nwith the indicated value, using the helper output captured in\nStep 6 (`Current Date\u002FTime (UTC):`):\n\n- `type:` ← `design-gap`\n- `id:` ← the filename stem (the file path computed below without\n  `.md`), always quoted as a YAML string\n- `title:` ← `Design Gap Analysis: {current-source} → {target-source}`\n- `date:` ← the `Current Date\u002FTime (UTC):` value\n- `author:` ← the author resolved per the standard chain (config →\n  VCS user → prompt)\n- `producer:` ← `analyse-design-gaps`\n- `status:` ← `draft`\n- `current_inventory:` ← the resolved absolute path to the current\n  inventory's `inventory.md`\n- `target_inventory:` ← the resolved absolute path to the target\n  inventory's `inventory.md`\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\nOptional linkage keys are omit-by-default (ADR-0040): the template shows\neach as `\"\"`\u002F`[]`, but write a key into the artifact **only** when it has\na value, and omit it entirely otherwise (do not carry the empty\nplaceholder through). The `current_inventory:` \u002F `target_inventory:`\nkeys above are always-valued and not subject to this rule.\n\n- `parent:` ← the work item this gap analysis supports, as a\n  typed-linkage ref (`\"work-item:NNNN\"`). Fill when the analysis has an\n  owning work item; otherwise omit the key.\n- `relates_to:` ← list of typed-linkage refs to related artifacts\n  (`[\"design-inventory:NNNN\", ...]`). Fill when relationships are\n  explicit; otherwise omit the key.\n\nThe design-gap artifact is not code-state-anchored — the helper's\n`Current Revision:` and `Repository Name:` output is ignored here\neven when present.\n\nWrite to:\n```\n\u003Cdesign_gaps>\u002FYYYY-MM-DD-{current-source-id}-vs-{target-source-id}.md\n```\n\nThe `References` section must record:\n- The resolved inventory directory path for each source-id\n- Any resolver warnings emitted in Step 1\n\n**Validate the frontmatter**: after writing the artifact, run\n\n```bash\naccelerator corpus frontmatter validate --file \u003Cpath>\n```\n\nIf it exits non-zero, the document violates the canonical frontmatter\nstandard; report the emitted violation and fix the frontmatter before\ncompleting.\n\n### 8. Present Summary\n\nReport:\n- The artifact path\n- Count of non-empty drift categories\n- Any resolver warnings (multi-match or corrupt-frontmatter)\n- Whether the cue-phrase audit required revisions\n\nSuggest next steps:\n- Run `\u002Faccelerator:extract-work-items \u003Cgap-file>` to generate work items\n\n## Important Guidelines\n\n- Empty drift categories are omitted — do not write placeholder sections.\n- The `sequence` tiebreaker is authoritative; do not rely on directory-name date\n  alone.\n- Never fabricate observations. Write only what differs between the two inventories.\n- The cue-phrase audit is programmatic enforcement, not a style suggestion. Revise\n  failing sections until the audit passes or the three-attempt limit is reached.\n\n!`accelerator config instructions analyse-design-gaps --fail-safe`\n",{"name":5,"description":7,"allowed-tools":63,"argument-hint":68,"disable-model-invocation":69},[64,65,66,67],"Bash(accelerator config *)","Bash(accelerator design *)","Bash(accelerator corpus metadata derive *)","Bash(accelerator corpus frontmatter validate *)","[current-source-id] [target-source-id]",true,"main","007b2dd695b63c2f097cdc40e54229b6e8b4596a","skills\u002Fdesign\u002Fanalyse-design-gaps",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":79,"prompt":89,"zipAvailable":69},[80,83,86],{"tool":81,"command":82},"npx","npx skills add atomicinnovation\u002Faccelerator --skill analyse-design-gaps",{"tool":84,"command":85},"bunx","bunx skills add atomicinnovation\u002Faccelerator --skill analyse-design-gaps",{"tool":87,"command":88},"pnpm","pnpm dlx skills add atomicinnovation\u002Faccelerator --skill analyse-design-gaps","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator\u002Fblob\u002Fmain\u002Fskills\u002Fdesign\u002Fanalyse-design-gaps\u002FSKILL.md",[91,97],{"path":92,"resourceType":93,"resourceTypeDesc":94,"sizeBytes":95,"sourceHtmlUrl":96},"evals\u002Fbenchmark.json","REFERENCE","参考文档",26949,"https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator\u002Fblob\u002Fmain\u002Fskills\u002Fdesign\u002Fanalyse-design-gaps\u002Fevals\u002Fbenchmark.json",{"path":98,"resourceType":93,"resourceTypeDesc":94,"sizeBytes":99,"sourceHtmlUrl":100},"evals\u002Fevals.json",10866,"https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator\u002Fblob\u002Fmain\u002Fskills\u002Fdesign\u002Fanalyse-design-gaps\u002Fevals\u002Fevals.json",[102,129,149,170,185,209],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":110,"publishedAt":58},"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",[108,109],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},[111,112,113,114,115,116,117,118,32,119,120,121,122,49,123,124,125,126,127,128],"explore pr","explore","pr","diagrams","exploration","re","review findings","walkthrough","map","when","number","URL","code","architecture","reviewer","review","notes","change",{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":135,"publishedAt":58},"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",[],[48,136,137,138,139,140,46,49,128,56,141,57,142,143,35,144,145,146,147,148],"update","update work item","work item","enforcement","manage","edit","status","transition","Existing","tags","changes","fields","op",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":155,"publishedAt":58},"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",[],[48,156,157,158,52,159,160,49,161,128,162,163,164,165,166,167,168,56,169,35,120],"sync","sync work items","promote","local","only","preview","active","tracker","max","jira","remote","create","adopt","reconcile",{"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":58},"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",[],[177,48,178,156,157,39,37,179,180,181,38,182,183,184],"sync work items recovery","recovery","terminal","read","person","false","orders","pending",{"skillNo":186,"name":187,"nameZh":6,"description":188,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":189,"categories":190,"keywords":194,"publishedAt":58},"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",[191],{"categoryNo":192,"categoryName":193,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[195,196,48,197,138,198,199,200,201,202,203,49,204,205,56,57,206,207,208,121,30,35],"stress test","test","stress test work item","stress","scope","issues","edge","stress-test","acceptance","acceptance criteria","dependencies","implementation","grilling","user",{"skillNo":210,"name":211,"nameZh":6,"description":212,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":213,"categories":214,"keywords":215,"publishedAt":58},"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",[],[126,48,216,138,217,218,46,49,219,220,56,57,206,208,53,120,221,222,35,223],"review work item","review work","escalation","file","quality","iterate","evaluate","path"]