[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71KCSYXS9K7Y6YD00TBDGZR":3,"skill-same:01M71KCSYXS9K7Y6YD00TBDGZR":74},{"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":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":56,"ownerHtmlUrl":57,"ownerBlogUrl":58,"ownerDescription":59,"updatedAt":60,"install":61,"resources":73},"01M71KCSYXS9K7Y6YD00TBDGZR","index",null,"Use when indexing codebase components or external resources for future specs.","mugsun\u002Fcurdx-flow","mugsun","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F100790155?v=4","01M6KJSAN2W4WRPDFBKTJTDDQ2","Mugsun","01M71K65VJXA4C1KPJAHZ6ZVHC",4,"MIT","https:\u002F\u002Fgithub.com\u002Fmugsun\u002Fcurdx-flow\u002Fblob\u002Fmain\u002Fplugins\u002Fcurdx-flow\u002Fskills\u002Findex\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[5,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"read","codebase","webfetch","type","use","true","for","path","patterns","write","run","indexing","dry","components","Bash","when","types","resources","quick","2026-11-10 10:12:30",false,"---\nname: index\ndescription: Use when indexing codebase components or external resources for future specs.\nargument-hint: \"[--path=dir] [--type=types] [--exclude=patterns] [--dry-run] [--force] [--changed] [--quick]\"\nallowed-tools: \"Read Write Agent Bash AskUserQuestion Glob Grep WebFetch ListMcpResourcesTool\"\ndisable-model-invocation: true\n---\n\n\n# Index Command\n\nYou are running the codebase indexing command. This scans the repository to generate component specs in `specs\u002F.index\u002F`.\n\n## Checklist\n\nUse native task UI tracking if `TaskCreate` is available; otherwise keep this checklist inline:\n\n- [ ] Parse arguments and validate\n- [ ] Generate project topology snapshot\n- [ ] Pre-scan interview (skip if --quick)\n- [ ] Scan codebase components\n- [ ] Fetch external resources (URLs, MCP, skills)\n- [ ] Generate component and external specs\n- [ ] Build index summary\n- [ ] Post-scan review (skip if --quick)\n\n## Step 1: Parse Arguments\n\nParse from `$ARGUMENTS`:\n\n| Option | Format | Default | Description |\n|--------|--------|---------|-------------|\n| `--path` | `--path=\u003Cdir>` | Project root | Limit scan to directory |\n| `--type` | `--type=\u003Ctypes>` | All | Comma-separated: controllers,services,models,helpers,migrations |\n| `--exclude` | `--exclude=\u003Cpatterns>` | See below | Comma-separated exclude patterns |\n| `--dry-run` | Flag | false | Preview without writing |\n| `--force` | Flag | false | Regenerate all (ignore existing) |\n| `--changed` | Flag | false | Only git-changed files |\n| `--quick` | Flag | false | Skip interviews, batch only |\n\n**Default excludes**: `node_modules, vendor, dist, build, .git, __pycache__, *.test.*, *.spec.*, *_test.*, test\u002F, tests\u002F, spec\u002F, specs\u002F`\n\n**Validation**: `--force` + `--changed` together is an error. `--path` must exist. `--type` values must be valid. `--changed` requires git (`git rev-parse --git-dir`).\n\n## Step 2: Project Topology Snapshot\n\nGenerate the cheap topology cache before component scanning:\n\n```bash\nmkdir -p specs\u002F.index\nnode \"${CLAUDE_PLUGIN_ROOT}\u002Fhooks\u002Fscripts\u002Flib\u002Fproject-topology.mjs\" \\\n  --goal \"$ARGUMENTS\" > specs\u002F.index\u002Fproject-topology.json\nnode \"${CLAUDE_PLUGIN_ROOT}\u002Fhooks\u002Fscripts\u002Flib\u002Fproject-topology.mjs\" \\\n  --goal \"$ARGUMENTS\" \\\n  --format context-map > specs\u002F.index\u002Fcontext-map.md\n```\n\nUse this snapshot to decide which roots are relevant. If `project-topology.json` contains `missingRoots`, stop indexing and show the `accessFix` value exactly.\n\n## Step 3: Pre-Scan Interview\n\n\u003Cmandatory>\n**Skip if --quick flag is detected.**\n\u003C\u002Fmandatory>\n\nAsk via AskUserQuestion:\n\n| # | Question | Key |\n|---|----------|-----|\n| 1 | External documentation URLs to index? | `externalUrls` |\n| 2 | MCP servers or skills to document? | `externalTools` |\n| 3 | Specific directories to focus on? | `focusAreas` |\n| 4 | Code areas lacking comments needing extra attention? | `sparseAreas` |\n\nStore responses in `.\u002Fspecs\u002F.index\u002F.index-state.json` under `interviewResponses`.\n\n## Step 4: Component Scanner\n\n### Detection Patterns\n\n| Category | Glob Pattern | File Pattern |\n|----------|-------------|--------------|\n| Controllers | `**\u002Fcontrollers\u002F**\u002F*.{ts,js,py,go}` | `*controller*`, `*Controller*` |\n| Services | `**\u002Fservices\u002F**\u002F*.{ts,js,py,go}` | `*service*`, `*Service*` |\n| Models | `**\u002Fmodels\u002F**\u002F*.{ts,js,py,go}` | `*model*`, `*Model*` |\n| Helpers | `**\u002Fhelpers\u002F**\u002F*.{ts,js,py,go}` | `*helper*`, `*Helper*`, `*util*` |\n| Migrations | `**\u002Fmigrations\u002F**\u002F*.{ts,js,sql}` | `*migration*` |\n\n### Scanning Process\n\n1. For each category (filtered by `--type` if set), run Glob with `--path` as base. If no `--path` is provided, scan each accessible code root from `project-topology.json`. Filter out excludes.\n2. If `--changed`: filter to `git diff --name-only HEAD` results only\n3. If not `--force` and spec exists: compare SHA-256 hash (first 8 chars via `shasum -a 256`), skip if unchanged\n4. For each matched file, extract metadata using language-appropriate Grep patterns:\n   - **Exports**: `export (const|function|class|interface|type) \\w+` (TS\u002FJS), `^def \\w+\\(` \u002F `^class \\w+` (Python), `^func \\w+\\(` (Go)\n   - **Methods**: Class method signatures per language\n   - **Dependencies**: import\u002Frequire\u002Ffrom statements per language\n5. For large codebases (>100 files): process in batches of 50, update state after each batch\n\n## Step 5: External Resource Fetcher\n\nProcess resources from interview responses. Classify each: URL (`http(s):\u002F\u002F`), MCP server (`mcp-*`\u002F`mcp_*`), or Skill (`\u002F` prefix or contains \"skill\").\n\n### URL Processing\n\nFor each URL in `externalUrls`:\n1. WebFetch with prompt to extract key sections, API endpoints, config options\n2. Generate external spec from `templates\u002Fexternal-spec.md`\n3. Write to `specs\u002F.index\u002Fexternal\u002Furl-\u003Csanitized-name>.md`\n4. On timeout\u002Ferror: warn and skip, continue processing\n\n### MCP Server Processing\n\nFor each MCP server in `externalTools`:\n1. ListMcpResourcesTool to discover tools and resources\n2. Document each tool\u002Fresource in external spec\n3. Write to `specs\u002F.index\u002Fexternal\u002Fmcp-\u003Cserver-name>.md`\n\n### Skill Processing\n\nFor each skill in `externalTools`:\n1. Read plugin manifests: `plugins\u002F*\u002F.claude-plugin\u002Fplugin.json`\n2. Extract commands, agents, hooks from manifest\n3. Write to `specs\u002F.index\u002Fexternal\u002Fskill-\u003Cplugin>-\u003Ccommand>.md`\n\n### File Naming\n\nPattern: `\u003Ctype>-\u003Csanitized-name>.md`. Sanitize: lowercase, replace non-alphanumeric with hyphens, collapse consecutive hyphens, max 50 chars.\n\n## Step 6: Generate Specs\n\nEnsure directories: `mkdir -p specs\u002F.index\u002Fcomponents specs\u002F.index\u002Fexternal`\n\n### Component Specs\n\nFor each scanned component:\n1. If `--dry-run`: collect for preview, do NOT write\n2. Load `templates\u002Fcomponent-spec.md`, fill template variables:\n   - `{{SOURCE_PATH}}`, `{{CONTENT_HASH}}`, `{{CATEGORY}}`, `{{TIMESTAMP}}`\n   - `{{COMPONENT_NAME}}`, `{{AUTO_GENERATED_SUMMARY}}`, `{{EXPORTS}}`, `{{METHODS}}`\n   - `{{DEPENDENCIES}}`, `{{KEYWORDS}}`, `{{RELATED_FILES}}`\n3. Write to `specs\u002F.index\u002Fcomponents\u002F\u003Ccategory>-\u003Cbasename>.md`\n4. Update hash in `.index-state.json`\n\n**Naming**: `\u003Csingular-category>-\u003Clowercase-basename>.md` (e.g., `controller-users.md`)\n\n### External Specs\n\nLoad `templates\u002Fexternal-spec.md`, fill `{{SOURCE_TYPE}}`, `{{SOURCE_ID}}`, `{{FETCH_TIMESTAMP}}`, `{{RESOURCE_NAME}}`, `{{CONTENT_SUMMARY}}`, `{{SECTIONS}}`, `{{KEYWORDS}}`, `{{RELATED_COMPONENTS}}`.\n\n### Index Summary\n\nLoad `templates\u002Findex-summary.md`, aggregate counts by category, list all components and externals. Write to `specs\u002F.index\u002Findex.md`.\n\n### Dry-Run Mode\n\nIf `--dry-run`: write nothing. Display preview table:\n\n```text\nDry Run - Would generate:\n| File | Category | Source | Status |\n|------|----------|--------|--------|\nTotal: N files\n```\n\n## Step 7: Post-Scan Review\n\n\u003Cmandatory>\n**Skip if --quick flag is detected.**\n\u003C\u002Fmandatory>\n\nAsk via AskUserQuestion:\n\n| # | Question | Key |\n|---|----------|-----|\n| 1 | Found {{count}} components. Seem complete? | `componentCount` |\n| 2 | External resources look correct? | `externalResources` |\n| 3 | Any areas to re-scan or adjust? | `adjustments` |\n\nHandle feedback: re-scan missing areas, re-filter if too many, re-process changed externals.\n\n## Step 8: Update State and Output\n\nUpdate `specs\u002F.index\u002F.index-state.json` with `lastIndexed`, `componentCount`, `externalCount`, `categories`, `hashes`.\n\nDisplay:\n\n```text\nIndex complete for '{{project_name}}'.\nOutput: specs\u002F.index\u002F\n\n| Category | Count |\n|----------|-------|\n| Controllers | {{count}} |\n| Services | {{count}} |\n| Models | {{count}} |\n| Helpers | {{count}} |\n| Migrations | {{count}} |\n| External Resources | {{count}} |\n| **Total** | **{{total}}** |\n\nNext: Run \u002Fcurdx-flow:start to create specs that reference indexed components.\n```\n\n## Error Handling\n\n| Scenario | Action |\n|----------|--------|\n| No components found | Warn, suggest `--path=src\u002F` or broader patterns. Still create `specs\u002F.index\u002F` |\n| External URL unreachable | Warn and skip, continue others |\n| MCP server unavailable | Warn and skip, continue others |\n| Git unavailable + `--changed` | Fatal error, suggest `--force` |\n| Permission denied on file | Skip file with warning, continue |\n| Hash unchanged (no `--force`) | Skip silently, count in summary |\n| Template missing | Use inline minimal fallback |\n| State file corrupted | Reset state, full scan |\n| Monorepo detected | Preserve package context in paths, group by package in summary |\n\nNever abort the entire index for recoverable errors. Show error\u002Fwarning summary at end.\n","# Index Command\n\nYou are running the codebase indexing command. This scans the repository to generate component specs in `specs\u002F.index\u002F`.\n\n## Checklist\n\nUse native task UI tracking if `TaskCreate` is available; otherwise keep this checklist inline:\n\n- [ ] Parse arguments and validate\n- [ ] Generate project topology snapshot\n- [ ] Pre-scan interview (skip if --quick)\n- [ ] Scan codebase components\n- [ ] Fetch external resources (URLs, MCP, skills)\n- [ ] Generate component and external specs\n- [ ] Build index summary\n- [ ] Post-scan review (skip if --quick)\n\n## Step 1: Parse Arguments\n\nParse from `$ARGUMENTS`:\n\n| Option | Format | Default | Description |\n|--------|--------|---------|-------------|\n| `--path` | `--path=\u003Cdir>` | Project root | Limit scan to directory |\n| `--type` | `--type=\u003Ctypes>` | All | Comma-separated: controllers,services,models,helpers,migrations |\n| `--exclude` | `--exclude=\u003Cpatterns>` | See below | Comma-separated exclude patterns |\n| `--dry-run` | Flag | false | Preview without writing |\n| `--force` | Flag | false | Regenerate all (ignore existing) |\n| `--changed` | Flag | false | Only git-changed files |\n| `--quick` | Flag | false | Skip interviews, batch only |\n\n**Default excludes**: `node_modules, vendor, dist, build, .git, __pycache__, *.test.*, *.spec.*, *_test.*, test\u002F, tests\u002F, spec\u002F, specs\u002F`\n\n**Validation**: `--force` + `--changed` together is an error. `--path` must exist. `--type` values must be valid. `--changed` requires git (`git rev-parse --git-dir`).\n\n## Step 2: Project Topology Snapshot\n\nGenerate the cheap topology cache before component scanning:\n\n```bash\nmkdir -p specs\u002F.index\nnode \"${CLAUDE_PLUGIN_ROOT}\u002Fhooks\u002Fscripts\u002Flib\u002Fproject-topology.mjs\" \\\n  --goal \"$ARGUMENTS\" > specs\u002F.index\u002Fproject-topology.json\nnode \"${CLAUDE_PLUGIN_ROOT}\u002Fhooks\u002Fscripts\u002Flib\u002Fproject-topology.mjs\" \\\n  --goal \"$ARGUMENTS\" \\\n  --format context-map > specs\u002F.index\u002Fcontext-map.md\n```\n\nUse this snapshot to decide which roots are relevant. If `project-topology.json` contains `missingRoots`, stop indexing and show the `accessFix` value exactly.\n\n## Step 3: Pre-Scan Interview\n\n\u003Cmandatory>\n**Skip if --quick flag is detected.**\n\u003C\u002Fmandatory>\n\nAsk via AskUserQuestion:\n\n| # | Question | Key |\n|---|----------|-----|\n| 1 | External documentation URLs to index? | `externalUrls` |\n| 2 | MCP servers or skills to document? | `externalTools` |\n| 3 | Specific directories to focus on? | `focusAreas` |\n| 4 | Code areas lacking comments needing extra attention? | `sparseAreas` |\n\nStore responses in `.\u002Fspecs\u002F.index\u002F.index-state.json` under `interviewResponses`.\n\n## Step 4: Component Scanner\n\n### Detection Patterns\n\n| Category | Glob Pattern | File Pattern |\n|----------|-------------|--------------|\n| Controllers | `**\u002Fcontrollers\u002F**\u002F*.{ts,js,py,go}` | `*controller*`, `*Controller*` |\n| Services | `**\u002Fservices\u002F**\u002F*.{ts,js,py,go}` | `*service*`, `*Service*` |\n| Models | `**\u002Fmodels\u002F**\u002F*.{ts,js,py,go}` | `*model*`, `*Model*` |\n| Helpers | `**\u002Fhelpers\u002F**\u002F*.{ts,js,py,go}` | `*helper*`, `*Helper*`, `*util*` |\n| Migrations | `**\u002Fmigrations\u002F**\u002F*.{ts,js,sql}` | `*migration*` |\n\n### Scanning Process\n\n1. For each category (filtered by `--type` if set), run Glob with `--path` as base. If no `--path` is provided, scan each accessible code root from `project-topology.json`. Filter out excludes.\n2. If `--changed`: filter to `git diff --name-only HEAD` results only\n3. If not `--force` and spec exists: compare SHA-256 hash (first 8 chars via `shasum -a 256`), skip if unchanged\n4. For each matched file, extract metadata using language-appropriate Grep patterns:\n   - **Exports**: `export (const|function|class|interface|type) \\w+` (TS\u002FJS), `^def \\w+\\(` \u002F `^class \\w+` (Python), `^func \\w+\\(` (Go)\n   - **Methods**: Class method signatures per language\n   - **Dependencies**: import\u002Frequire\u002Ffrom statements per language\n5. For large codebases (>100 files): process in batches of 50, update state after each batch\n\n## Step 5: External Resource Fetcher\n\nProcess resources from interview responses. Classify each: URL (`http(s):\u002F\u002F`), MCP server (`mcp-*`\u002F`mcp_*`), or Skill (`\u002F` prefix or contains \"skill\").\n\n### URL Processing\n\nFor each URL in `externalUrls`:\n1. WebFetch with prompt to extract key sections, API endpoints, config options\n2. Generate external spec from `templates\u002Fexternal-spec.md`\n3. Write to `specs\u002F.index\u002Fexternal\u002Furl-\u003Csanitized-name>.md`\n4. On timeout\u002Ferror: warn and skip, continue processing\n\n### MCP Server Processing\n\nFor each MCP server in `externalTools`:\n1. ListMcpResourcesTool to discover tools and resources\n2. Document each tool\u002Fresource in external spec\n3. Write to `specs\u002F.index\u002Fexternal\u002Fmcp-\u003Cserver-name>.md`\n\n### Skill Processing\n\nFor each skill in `externalTools`:\n1. Read plugin manifests: `plugins\u002F*\u002F.claude-plugin\u002Fplugin.json`\n2. Extract commands, agents, hooks from manifest\n3. Write to `specs\u002F.index\u002Fexternal\u002Fskill-\u003Cplugin>-\u003Ccommand>.md`\n\n### File Naming\n\nPattern: `\u003Ctype>-\u003Csanitized-name>.md`. Sanitize: lowercase, replace non-alphanumeric with hyphens, collapse consecutive hyphens, max 50 chars.\n\n## Step 6: Generate Specs\n\nEnsure directories: `mkdir -p specs\u002F.index\u002Fcomponents specs\u002F.index\u002Fexternal`\n\n### Component Specs\n\nFor each scanned component:\n1. If `--dry-run`: collect for preview, do NOT write\n2. Load `templates\u002Fcomponent-spec.md`, fill template variables:\n   - `{{SOURCE_PATH}}`, `{{CONTENT_HASH}}`, `{{CATEGORY}}`, `{{TIMESTAMP}}`\n   - `{{COMPONENT_NAME}}`, `{{AUTO_GENERATED_SUMMARY}}`, `{{EXPORTS}}`, `{{METHODS}}`\n   - `{{DEPENDENCIES}}`, `{{KEYWORDS}}`, `{{RELATED_FILES}}`\n3. Write to `specs\u002F.index\u002Fcomponents\u002F\u003Ccategory>-\u003Cbasename>.md`\n4. Update hash in `.index-state.json`\n\n**Naming**: `\u003Csingular-category>-\u003Clowercase-basename>.md` (e.g., `controller-users.md`)\n\n### External Specs\n\nLoad `templates\u002Fexternal-spec.md`, fill `{{SOURCE_TYPE}}`, `{{SOURCE_ID}}`, `{{FETCH_TIMESTAMP}}`, `{{RESOURCE_NAME}}`, `{{CONTENT_SUMMARY}}`, `{{SECTIONS}}`, `{{KEYWORDS}}`, `{{RELATED_COMPONENTS}}`.\n\n### Index Summary\n\nLoad `templates\u002Findex-summary.md`, aggregate counts by category, list all components and externals. Write to `specs\u002F.index\u002Findex.md`.\n\n### Dry-Run Mode\n\nIf `--dry-run`: write nothing. Display preview table:\n\n```text\nDry Run - Would generate:\n| File | Category | Source | Status |\n|------|----------|--------|--------|\nTotal: N files\n```\n\n## Step 7: Post-Scan Review\n\n\u003Cmandatory>\n**Skip if --quick flag is detected.**\n\u003C\u002Fmandatory>\n\nAsk via AskUserQuestion:\n\n| # | Question | Key |\n|---|----------|-----|\n| 1 | Found {{count}} components. Seem complete? | `componentCount` |\n| 2 | External resources look correct? | `externalResources` |\n| 3 | Any areas to re-scan or adjust? | `adjustments` |\n\nHandle feedback: re-scan missing areas, re-filter if too many, re-process changed externals.\n\n## Step 8: Update State and Output\n\nUpdate `specs\u002F.index\u002F.index-state.json` with `lastIndexed`, `componentCount`, `externalCount`, `categories`, `hashes`.\n\nDisplay:\n\n```text\nIndex complete for '{{project_name}}'.\nOutput: specs\u002F.index\u002F\n\n| Category | Count |\n|----------|-------|\n| Controllers | {{count}} |\n| Services | {{count}} |\n| Models | {{count}} |\n| Helpers | {{count}} |\n| Migrations | {{count}} |\n| External Resources | {{count}} |\n| **Total** | **{{total}}** |\n\nNext: Run \u002Fcurdx-flow:start to create specs that reference indexed components.\n```\n\n## Error Handling\n\n| Scenario | Action |\n|----------|--------|\n| No components found | Warn, suggest `--path=src\u002F` or broader patterns. Still create `specs\u002F.index\u002F` |\n| External URL unreachable | Warn and skip, continue others |\n| MCP server unavailable | Warn and skip, continue others |\n| Git unavailable + `--changed` | Fatal error, suggest `--force` |\n| Permission denied on file | Skip file with warning, continue |\n| Hash unchanged (no `--force`) | Skip silently, count in summary |\n| Template missing | Use inline minimal fallback |\n| State file corrupted | Reset state, full scan |\n| Monorepo detected | Preserve package context in paths, group by package in summary |\n\nNever abort the entire index for recoverable errors. Show error\u002Fwarning summary at end.\n",{"name":5,"description":7,"allowed-tools":48,"argument-hint":49,"disable-model-invocation":50},"Read Write Agent Bash AskUserQuestion Glob Grep WebFetch ListMcpResourcesTool","[--path=dir] [--type=types] [--exclude=patterns] [--dry-run] [--force] [--changed] [--quick]",true,"main","7357746802ae7a84cafa93b9dbffd138817b0290","plugins\u002Fcurdx-flow\u002Fskills\u002Findex",0,"https:\u002F\u002Fgithub.com\u002Fmugsun\u002Fcurdx-flow","https:\u002F\u002Fcurdx.org","https:\u002F\u002Fgithub.com\u002Fmugsun","📮 bydongxin@gmail.com","🧑‍💻 AI Builder & Software Engineer\r\n🚀 Turning ideas into software.          \r\n\r\n","2026-08-19 15:19:29",{"source":8,"skillName":5,"commands":62,"prompt":72,"zipAvailable":50},[63,66,69],{"tool":64,"command":65},"npx","npx skills add mugsun\u002Fcurdx-flow --skill index",{"tool":67,"command":68},"bunx","bunx skills add mugsun\u002Fcurdx-flow --skill index",{"tool":70,"command":71},"pnpm","pnpm dlx skills add mugsun\u002Fcurdx-flow --skill index","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmugsun\u002Fcurdx-flow\u002Fblob\u002Fmain\u002Fplugins\u002Fcurdx-flow\u002Fskills\u002Findex\u002FSKILL.md",[],[75,84,102,115,129,139],{"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":82,"publishedAt":43},"01M71KDR5EJP6G4VWFCHNJ35PT","help","Fixture help skill","https:\u002F\u002Fgithub.com\u002Fmugsun\u002Fcurdx-flow\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fruntime-readiness\u002Fclaude-code-plugin-like\u002Fskills\u002Fhelp\u002FSKILL.md",[81],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[77,83],"fixture",{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":43},"01M71KDNAVB000W3MZB1W7CMD8","verification-before-completion","Use when checking fixes, phase exits, completion evidence, or mock-heavy tests before claiming success.","https:\u002F\u002Fgithub.com\u002Fmugsun\u002Fcurdx-flow\u002Fblob\u002Fmain\u002Fplugins\u002Fcurdx-flow\u002Fskills\u002Fverification-before-completion\u002FSKILL.md",[],[91,92,93,94,39,95,96,97,98,99,28,100,101],"verification","verification before completion","only","false","tasks","phase","evidence","fixes","tests","mock","state",{"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":109,"publishedAt":43},"01M71KDKFE975GFYRDC21H1NEE","triage","Use when a large feature should be decomposed into dependency-aware specs.","https:\u002F\u002Fgithub.com\u002Fmugsun\u002Fcurdx-flow\u002Fblob\u002Fmain\u002Fplugins\u002Fcurdx-flow\u002Fskills\u002Ftriage\u002FSKILL.md",[108],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[104,110,29,111,33,24,112,113,38,39,28,114],"goal","feature","dependency","name","EPIC",{"skillNo":116,"name":95,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":121,"publishedAt":43},"01M71KDH7XFQJPKYZ0H9JDNSA5","Use when a spec has design.md and needs implementation tasks.","https:\u002F\u002Fgithub.com\u002Fmugsun\u002Fcurdx-flow\u002Fblob\u002Fmain\u002Fplugins\u002Fcurdx-flow\u002Fskills\u002Ftasks\u002FSKILL.md",[120],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[95,122,123,113,124,28,125,126,127,39,38,24,33,128,29],"implementation","spec","task","standard","design","auto","edit",{"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":136,"publishedAt":43},"01M71KDEV9G51MCXDQWPJH7QST","switch","Use when changing the active spec by name or path.","https:\u002F\u002Fgithub.com\u002Fmugsun\u002Fcurdx-flow\u002Fblob\u002Fmain\u002Fplugins\u002Fcurdx-flow\u002Fskills\u002Fswitch\u002FSKILL.md",[135],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[131,38,137,29,28,39,138,113,24,123,33,31],"by name","active",{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":146,"publishedAt":43},"01M71KDDJFRV09YZ08B3WJ39SC","status","Use when inspecting curdx-flow specs, active state, progress, or index status.","https:\u002F\u002Fgithub.com\u002Fmugsun\u002Fcurdx-flow\u002Fblob\u002Fmain\u002Fplugins\u002Fcurdx-flow\u002Fskills\u002Fstatus\u002FSKILL.md",[145],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[141,29,28,39,38,101,147,138,148,24,149,5],"progress","update","flow"]