[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71KD4R7QQEWYMDSH9866P8T":3,"skill-same:01M71KD4R7QQEWYMDSH9866P8T":67},{"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":36,"linkOnly":37,"markdownContent":38,"markdownBody":39,"frontMatter":40,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":49,"ownerHtmlUrl":50,"ownerBlogUrl":51,"ownerDescription":52,"updatedAt":53,"install":54,"resources":66},"01M71KD4R7QQEWYMDSH9866P8T","requirements",null,"Use when a spec has research or goal context and needs requirements.","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\u002Frequirements\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],"when","Bash","goal","read","write","edit","context","true","use","research","name","spec","2026-11-10 10:12:30",false,"---\nname: requirements\ndescription: Use when a spec has research or goal context and needs requirements.\nargument-hint: \"[spec-name]\"\nallowed-tools: \"Read Write Edit Bash Agent AskUserQuestion\"\ndisable-model-invocation: true\n---\n\n\n# Requirements Phase\n\nGenerate requirements for the active spec. Running this command implicitly approves research. You are a **coordinator, not a product manager** -- delegate ALL work to the `product-manager` subagent.\n\n## Coordinator Checklist\n\nComplete these coordination steps in order; do not create user-facing implementation tasks from this checklist:\n\n1. **Gather context** -- resolve spec, read research and goal\n2. **Interview** -- brainstorming dialogue (skip if `--quick`)\n3. **Execute requirements** -- dispatch product-manager via direct Agent; Agent Teams optional\n4. **Artifact review** -- spec-reviewer validation loop (only if `--quick`)\n5. **Walkthrough & approval** -- display summary, get user approval\n6. **Finalize** -- update state, commit, stop\n\n## Step 1: Gather Context\n\n1. Run `curdx-flow snapshot --spec \"$ARGUMENTS\"` when `$ARGUMENTS` begins with a spec name; otherwise run `curdx-flow snapshot`.\n2. If `snapshot.active` is false, error: \"No active spec. Run \u002Fcurdx-flow:new \u003Cname> first.\"\n3. Use `snapshot.spec.fsPath` as `$SPEC_PATH`.\n4. Clear approval flag:\n   ```bash\n   curdx-flow state merge \"$SPEC_PATH\u002F.curdx-state.json\" '{\"awaitingApproval\":false}'\n   ```\n5. Read context: `research.md` (if exists), `.progress.md`, `snapshot.state`, `snapshot.topology`, original goal.\n6. Read `references\u002Fworkflow-contract.md` and `references\u002Fagent-output-contract.md`.\n\n## Step 2: Interview (skip if --quick)\n\nCheck if `--quick` appears in `$ARGUMENTS`. If present, skip to Step 3.\n\n### Read Context from .progress.md\n\nParse Intent Classification and prior interview responses to skip already-answered questions.\n\n**Intent-Based Question Counts:**\n- TRIVIAL: 1-2 | REFACTOR: 3-5 | GREENFIELD: 5-10 | MID_SIZED: 3-7\n\n### Brainstorming Dialogue\n\nApply adaptive dialogue from `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Finterview-framework\u002FSKILL.md`. Ask context-driven questions one at a time.\n\n**Requirements Exploration Territory** (hints, not a script):\n- **Primary users** -- who will use this feature? Developers, end users, specific roles?\n- **Priority tradeoffs** -- speed of delivery vs code quality vs feature completeness\n- **Success criteria** -- what does success look like? Metrics, behaviors, user outcomes\n- **Scope boundaries** -- what is explicitly out of scope for this iteration?\n- **Compliance or regulatory needs** -- security, privacy, or regulatory considerations?\n\n### Requirements Approach Proposals\n\nAfter dialogue, propose 2-3 scoping approaches. Examples (illustrative only):\n- **(A)** Full feature set -- comprehensive user stories covering all use cases\n- **(B)** MVP scope -- core user stories only, defer edge cases to v2\n- **(C)** Phased delivery -- essential stories now, planned expansion later\n\n### Store Interview & Approach\n\nAppend to `.progress.md` under \"Interview Responses\":\n```markdown\n### Requirements Interview (from requirements.md)\n- [Topic 1]: [response]\n- Chosen approach: [name] -- [brief description]\n```\n\nPass combined context to delegation prompt as \"Interview Context\".\n\n## Step 3: Execute Requirements (Agent-Based, Teams Optional)\n\n\u003Cmandatory>\n**Default path: use the normal `Agent` tool with `product-manager`. Do not require Agent Teams.**\n\nAgent Teams are experimental and disabled by default in Claude Code. Use the team lifecycle only when `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1` is set and the `TeamCreate` \u002F `TaskCreate` \u002F `TaskList` \u002F `SendMessage` tools are visible in the current session. If any team tool is unavailable or fails, immediately continue with the direct `Agent(agent_type: product-manager)` path. Treat this as the normal path, not a degraded path.\n\nDirect path:\n\n1. Optionally create a visible native task with `TaskCreate(subject: \"Generate requirements for $spec\", activeForm: \"Generating requirements\")`. If unavailable or failing, continue without it.\n2. Dispatch `Agent(agent_type: product-manager)` with research context, goal, and interview context. Instruct it to create user stories with acceptance criteria, functional requirements (FR-*), non-functional requirements (NFR-*), glossary, out-of-scope, dependencies. Output to `.\u002Fspecs\u002F$spec\u002Frequirements.md`.\n3. Wait for the Agent result, then read `.\u002Fspecs\u002F$spec\u002Frequirements.md`.\n\nOptional Agent Teams path:\n\n1. `TeamDelete()` once to release any stale team; errors are harmless.\n2. `TeamCreate(team_name: \"requirements-$spec\")`\n3. `TaskCreate(subject: \"Generate requirements for $spec\", activeForm: \"Generating requirements\")`\n4. `Agent(agent_type: product-manager, team_name: \"requirements-$spec\", name: \"pm-1\")` with the same prompt as the direct path.\n5. Wait via automatic teammate messages or a single `TaskList` check.\n6. `SendMessage(type: \"shutdown_request\", recipient: \"pm-1\")`\n7. Read `.\u002Fspecs\u002F$spec\u002Frequirements.md`, then `TeamDelete()`.\n\u003C\u002Fmandatory>\n\n## Step 4: Artifact Review (only in --quick mode)\n\n\u003Cmandatory>\n**Review loop must complete before walkthrough. Max 3 iterations.**\n\nIf NOT `--quick`, skip to Step 5.\n\nInvoke `spec-reviewer` via Agent tool. Follow the standard review loop:\n- REVIEW_PASS: log to .progress.md, proceed\n- REVIEW_FAIL (iteration \u003C 3): log, re-invoke product-manager with feedback, loop\n- REVIEW_FAIL (iteration >= 3): graceful degradation, log warning, proceed\n- No signal: treat as REVIEW_PASS (permissive)\n\n**Review delegation**: Include full requirements.md content, iteration count, prior findings. Upstream: research.md.\n\n**Revision delegation**: Re-invoke product-manager with reviewer feedback. Focus on specific issues.\n\n**Error handling**: Reviewer no signal = REVIEW_PASS. Agent failure = retry once, then use original.\n\u003C\u002Fmandatory>\n\n## Step 5: Walkthrough & Approval\n\n\u003Cmandatory>\n**WALKTHROUGH IS REQUIRED - DO NOT SKIP.**\n\nRead `.\u002Fspecs\u002F$spec\u002Frequirements.md` and display:\n\n```\nRequirements complete for '$spec'.\nOutput: $PWD\u002Fspecs\u002F$spec\u002Frequirements.md\n\n## What I Created\n\n**Goal**: [1 sentence summary]\n\n**User Stories** ([count] total):\n- US-1: [title]\n- US-2: [title]\n- US-3: [title]\n[list all, keep titles brief]\n\n**Requirements**: [X] functional, [Y] non-functional\n```\n\u003C\u002Fmandatory>\n\n### User Approval (skip if --quick)\n\nIf `--quick`, skip to Step 6.\n\nAsk ONE question: \"How do you want to proceed?\" with these options via AskUserQuestion:\n1. **Approve** (Recommended) -- Accept artifact as-is, advance to next phase\n2. **Run review** -- Spawn spec-reviewer to validate against rubrics, show findings, then loop back to this choice\n3. **Request changes** -- Provide specific feedback to revise the artifact\n\n**If \"Approve\"**: proceed to Step 6.\n**If \"Run review\"**: Invoke spec-reviewer via Agent tool with full requirements.md content (upstream: research.md). Display findings table. If REVIEW_PASS, note it. If REVIEW_FAIL, show feedback. Then loop back to this same 3-choice question (user decides next action).\n**If \"Request changes\" or \"Other\"**:\n1. Ask what to change\n2. Re-invoke product-manager with direct `Agent(agent_type: product-manager)` and feedback; use the optional team lifecycle only if Agent Teams are enabled and available\n3. Re-display walkthrough, ask again with same 3 choices. Loop until approved.\n\n## Step 6: Finalize\n\n### Update State\n\n1. **Merge** into `.curdx-state.json` (preserve all existing fields):\n   ```bash\n   curdx-flow state merge \\\n     \"$SPEC_PATH\u002F.curdx-state.json\" '{\"phase\":\"requirements\",\"awaitingApproval\":true}'\n   ```\n2. Update `.progress.md`: mark research as implicitly approved, set current phase\n\n### Commit Spec (if enabled)\n\nRead `commitSpec` from `.curdx-state.json`. If true:\n```bash\ngit add .\u002Fspecs\u002F$spec\u002Frequirements.md\ngit commit -m \"spec($spec): add requirements\"\ngit push -u origin $(git branch --show-current)\n```\nIf commit or push fails, display warning but continue.\n\n### Stop\n\n\u003Cmandatory>\n**STOP HERE. DO NOT PROCEED TO DESIGN.**\n\n(Does not apply in `--quick` mode.)\n\n1. Display: `-> Next: Run \u002Fcurdx-flow:design`\n2. End your response immediately\n3. Wait for user to explicitly run `\u002Fcurdx-flow:design`\n\u003C\u002Fmandatory>\n","# Requirements Phase\n\nGenerate requirements for the active spec. Running this command implicitly approves research. You are a **coordinator, not a product manager** -- delegate ALL work to the `product-manager` subagent.\n\n## Coordinator Checklist\n\nComplete these coordination steps in order; do not create user-facing implementation tasks from this checklist:\n\n1. **Gather context** -- resolve spec, read research and goal\n2. **Interview** -- brainstorming dialogue (skip if `--quick`)\n3. **Execute requirements** -- dispatch product-manager via direct Agent; Agent Teams optional\n4. **Artifact review** -- spec-reviewer validation loop (only if `--quick`)\n5. **Walkthrough & approval** -- display summary, get user approval\n6. **Finalize** -- update state, commit, stop\n\n## Step 1: Gather Context\n\n1. Run `curdx-flow snapshot --spec \"$ARGUMENTS\"` when `$ARGUMENTS` begins with a spec name; otherwise run `curdx-flow snapshot`.\n2. If `snapshot.active` is false, error: \"No active spec. Run \u002Fcurdx-flow:new \u003Cname> first.\"\n3. Use `snapshot.spec.fsPath` as `$SPEC_PATH`.\n4. Clear approval flag:\n   ```bash\n   curdx-flow state merge \"$SPEC_PATH\u002F.curdx-state.json\" '{\"awaitingApproval\":false}'\n   ```\n5. Read context: `research.md` (if exists), `.progress.md`, `snapshot.state`, `snapshot.topology`, original goal.\n6. Read `references\u002Fworkflow-contract.md` and `references\u002Fagent-output-contract.md`.\n\n## Step 2: Interview (skip if --quick)\n\nCheck if `--quick` appears in `$ARGUMENTS`. If present, skip to Step 3.\n\n### Read Context from .progress.md\n\nParse Intent Classification and prior interview responses to skip already-answered questions.\n\n**Intent-Based Question Counts:**\n- TRIVIAL: 1-2 | REFACTOR: 3-5 | GREENFIELD: 5-10 | MID_SIZED: 3-7\n\n### Brainstorming Dialogue\n\nApply adaptive dialogue from `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Finterview-framework\u002FSKILL.md`. Ask context-driven questions one at a time.\n\n**Requirements Exploration Territory** (hints, not a script):\n- **Primary users** -- who will use this feature? Developers, end users, specific roles?\n- **Priority tradeoffs** -- speed of delivery vs code quality vs feature completeness\n- **Success criteria** -- what does success look like? Metrics, behaviors, user outcomes\n- **Scope boundaries** -- what is explicitly out of scope for this iteration?\n- **Compliance or regulatory needs** -- security, privacy, or regulatory considerations?\n\n### Requirements Approach Proposals\n\nAfter dialogue, propose 2-3 scoping approaches. Examples (illustrative only):\n- **(A)** Full feature set -- comprehensive user stories covering all use cases\n- **(B)** MVP scope -- core user stories only, defer edge cases to v2\n- **(C)** Phased delivery -- essential stories now, planned expansion later\n\n### Store Interview & Approach\n\nAppend to `.progress.md` under \"Interview Responses\":\n```markdown\n### Requirements Interview (from requirements.md)\n- [Topic 1]: [response]\n- Chosen approach: [name] -- [brief description]\n```\n\nPass combined context to delegation prompt as \"Interview Context\".\n\n## Step 3: Execute Requirements (Agent-Based, Teams Optional)\n\n\u003Cmandatory>\n**Default path: use the normal `Agent` tool with `product-manager`. Do not require Agent Teams.**\n\nAgent Teams are experimental and disabled by default in Claude Code. Use the team lifecycle only when `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1` is set and the `TeamCreate` \u002F `TaskCreate` \u002F `TaskList` \u002F `SendMessage` tools are visible in the current session. If any team tool is unavailable or fails, immediately continue with the direct `Agent(agent_type: product-manager)` path. Treat this as the normal path, not a degraded path.\n\nDirect path:\n\n1. Optionally create a visible native task with `TaskCreate(subject: \"Generate requirements for $spec\", activeForm: \"Generating requirements\")`. If unavailable or failing, continue without it.\n2. Dispatch `Agent(agent_type: product-manager)` with research context, goal, and interview context. Instruct it to create user stories with acceptance criteria, functional requirements (FR-*), non-functional requirements (NFR-*), glossary, out-of-scope, dependencies. Output to `.\u002Fspecs\u002F$spec\u002Frequirements.md`.\n3. Wait for the Agent result, then read `.\u002Fspecs\u002F$spec\u002Frequirements.md`.\n\nOptional Agent Teams path:\n\n1. `TeamDelete()` once to release any stale team; errors are harmless.\n2. `TeamCreate(team_name: \"requirements-$spec\")`\n3. `TaskCreate(subject: \"Generate requirements for $spec\", activeForm: \"Generating requirements\")`\n4. `Agent(agent_type: product-manager, team_name: \"requirements-$spec\", name: \"pm-1\")` with the same prompt as the direct path.\n5. Wait via automatic teammate messages or a single `TaskList` check.\n6. `SendMessage(type: \"shutdown_request\", recipient: \"pm-1\")`\n7. Read `.\u002Fspecs\u002F$spec\u002Frequirements.md`, then `TeamDelete()`.\n\u003C\u002Fmandatory>\n\n## Step 4: Artifact Review (only in --quick mode)\n\n\u003Cmandatory>\n**Review loop must complete before walkthrough. Max 3 iterations.**\n\nIf NOT `--quick`, skip to Step 5.\n\nInvoke `spec-reviewer` via Agent tool. Follow the standard review loop:\n- REVIEW_PASS: log to .progress.md, proceed\n- REVIEW_FAIL (iteration \u003C 3): log, re-invoke product-manager with feedback, loop\n- REVIEW_FAIL (iteration >= 3): graceful degradation, log warning, proceed\n- No signal: treat as REVIEW_PASS (permissive)\n\n**Review delegation**: Include full requirements.md content, iteration count, prior findings. Upstream: research.md.\n\n**Revision delegation**: Re-invoke product-manager with reviewer feedback. Focus on specific issues.\n\n**Error handling**: Reviewer no signal = REVIEW_PASS. Agent failure = retry once, then use original.\n\u003C\u002Fmandatory>\n\n## Step 5: Walkthrough & Approval\n\n\u003Cmandatory>\n**WALKTHROUGH IS REQUIRED - DO NOT SKIP.**\n\nRead `.\u002Fspecs\u002F$spec\u002Frequirements.md` and display:\n\n```\nRequirements complete for '$spec'.\nOutput: $PWD\u002Fspecs\u002F$spec\u002Frequirements.md\n\n## What I Created\n\n**Goal**: [1 sentence summary]\n\n**User Stories** ([count] total):\n- US-1: [title]\n- US-2: [title]\n- US-3: [title]\n[list all, keep titles brief]\n\n**Requirements**: [X] functional, [Y] non-functional\n```\n\u003C\u002Fmandatory>\n\n### User Approval (skip if --quick)\n\nIf `--quick`, skip to Step 6.\n\nAsk ONE question: \"How do you want to proceed?\" with these options via AskUserQuestion:\n1. **Approve** (Recommended) -- Accept artifact as-is, advance to next phase\n2. **Run review** -- Spawn spec-reviewer to validate against rubrics, show findings, then loop back to this choice\n3. **Request changes** -- Provide specific feedback to revise the artifact\n\n**If \"Approve\"**: proceed to Step 6.\n**If \"Run review\"**: Invoke spec-reviewer via Agent tool with full requirements.md content (upstream: research.md). Display findings table. If REVIEW_PASS, note it. If REVIEW_FAIL, show feedback. Then loop back to this same 3-choice question (user decides next action).\n**If \"Request changes\" or \"Other\"**:\n1. Ask what to change\n2. Re-invoke product-manager with direct `Agent(agent_type: product-manager)` and feedback; use the optional team lifecycle only if Agent Teams are enabled and available\n3. Re-display walkthrough, ask again with same 3 choices. Loop until approved.\n\n## Step 6: Finalize\n\n### Update State\n\n1. **Merge** into `.curdx-state.json` (preserve all existing fields):\n   ```bash\n   curdx-flow state merge \\\n     \"$SPEC_PATH\u002F.curdx-state.json\" '{\"phase\":\"requirements\",\"awaitingApproval\":true}'\n   ```\n2. Update `.progress.md`: mark research as implicitly approved, set current phase\n\n### Commit Spec (if enabled)\n\nRead `commitSpec` from `.curdx-state.json`. If true:\n```bash\ngit add .\u002Fspecs\u002F$spec\u002Frequirements.md\ngit commit -m \"spec($spec): add requirements\"\ngit push -u origin $(git branch --show-current)\n```\nIf commit or push fails, display warning but continue.\n\n### Stop\n\n\u003Cmandatory>\n**STOP HERE. DO NOT PROCEED TO DESIGN.**\n\n(Does not apply in `--quick` mode.)\n\n1. Display: `-> Next: Run \u002Fcurdx-flow:design`\n2. End your response immediately\n3. Wait for user to explicitly run `\u002Fcurdx-flow:design`\n\u003C\u002Fmandatory>\n",{"name":5,"description":7,"allowed-tools":41,"argument-hint":42,"disable-model-invocation":43},"Read Write Edit Bash Agent AskUserQuestion","[spec-name]",true,"main","7357746802ae7a84cafa93b9dbffd138817b0290","plugins\u002Fcurdx-flow\u002Fskills\u002Frequirements",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":55,"prompt":65,"zipAvailable":43},[56,59,62],{"tool":57,"command":58},"npx","npx skills add mugsun\u002Fcurdx-flow --skill requirements",{"tool":60,"command":61},"bunx","bunx skills add mugsun\u002Fcurdx-flow --skill requirements",{"tool":63,"command":64},"pnpm","pnpm dlx skills add mugsun\u002Fcurdx-flow --skill requirements","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmugsun\u002Fcurdx-flow\u002Fblob\u002Fmain\u002Fplugins\u002Fcurdx-flow\u002Fskills\u002Frequirements\u002FSKILL.md",[],[68,77,95,106,118,129],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":75,"publishedAt":36},"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",[74],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[70,76],"fixture",{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":36},"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",[],[84,85,86,87,24,88,89,90,91,92,32,93,94],"verification","verification before completion","only","false","tasks","phase","evidence","fixes","tests","mock","state",{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":102,"publishedAt":36},"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",[101],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[97,26,31,103,28,27,104,34,25,24,32,105],"feature","dependency","EPIC",{"skillNo":107,"name":88,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":112,"publishedAt":36},"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",[111],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[88,113,35,34,114,32,115,116,117,24,25,27,28,29,31],"implementation","task","standard","design","auto",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":125,"publishedAt":36},"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",[124],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[120,25,126,31,32,24,127,34,27,35,28,128],"by name","active","path",{"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":36},"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",[135],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[131,31,32,24,25,94,137,127,138,27,139,140],"progress","update","flow","index"]