[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71KD6SYVDENX6KT6MEEPAY3":3,"skill-same:01M71KD6SYVDENX6KT6MEEPAY3":73},{"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":26,"publishedAt":42,"linkOnly":43,"markdownContent":44,"markdownBody":45,"frontMatter":46,"refName":50,"commitSha":51,"skillDirectory":52,"forksCount":53,"repositoryHtmlUrl":54,"repositoryHomepageUrl":55,"ownerHtmlUrl":56,"ownerBlogUrl":57,"ownerDescription":58,"updatedAt":59,"install":60,"resources":72},"01M71KD6SYVDENX6KT6MEEPAY3","research",null,"Use when running or re-running discovery research for the active spec.","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\u002Fresearch\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[5,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41],"spec","discovery","Bash","read","write","edit","use","active","name","re","true","for","discovery research","when","running","2026-11-10 10:12:30",false,"---\nname: research\ndescription: Use when running or re-running discovery research for the active spec.\nargument-hint: \"[spec-name]\"\nallowed-tools: \"Read Write Edit Bash Agent AskUserQuestion\"\ndisable-model-invocation: true\n---\n\n\n# Research Phase\n\nRun parallel research for the active spec. You are a **coordinator, not a researcher** -- delegate ALL work to subagents.\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 goal and existing files\n2. **Interview** -- brainstorming dialogue (skip if `--quick`)\n3. **Execute parallel research** -- dispatch team of research-analyst + Explore agents\n4. **Merge results** -- synthesize partial files into research.md\n5. **Artifact review** -- spec-reviewer validation loop (only if `--quick`)\n6. **Walkthrough & approval** -- display summary, get user approval\n7. **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 `$SPEC_PATH`.\n4. Read `snapshot.state`, `snapshot.topology`, and `.progress.md` to understand the goal.\n5. Read `references\u002Fworkflow-contract.md`, `references\u002Fagent-output-contract.md`, and `references\u002Fcontext-and-dispatch-policy.md`.\n\n## Step 2: Interview (skip if --quick)\n\nCheck if `--quick` appears in `$ARGUMENTS`. If present, skip to Step 3.\n\n### Read Context from .progress.md\n\nRead `.progress.md` and parse:\n1. **Intent Classification** (TRIVIAL, REFACTOR, GREENFIELD, MID_SIZED) for question counts\n2. **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 `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Finterview-framework\u002FSKILL.md`. Ask context-driven questions one at a time, adapting to prior answers.\n\n**Research Exploration Territory** (hints, not a script):\n- **Technical approach preference** -- follow existing patterns or introduce new ones?\n- **Known constraints** -- performance, compatibility, timeline, budget\n- **Integration surface area** -- which systems, services, or APIs does this touch?\n- **Prior knowledge** -- what does the user already know vs what needs discovery?\n- **Technologies to evaluate or avoid** -- specific libraries, frameworks, or patterns\n\n### Research Approach Proposals\n\nAfter dialogue, propose 2-3 research strategies. Examples (illustrative only):\n- **(A)** Deep dive on specific technology\u002Flibrary comparison\n- **(B)** Focus on existing codebase patterns with minimal external research\n- **(C)** Broad survey across multiple alternatives before narrowing\n\n### Store Interview & Approach\n\nAppend to `.progress.md` under \"Interview Responses\":\n```markdown\n### Research Interview (from research.md)\n- [Topic 1]: [response]\n- Chosen approach: [name] -- [brief description]\n```\n\nPass combined context to subagent delegation as \"Interview Context\".\n\n## Step 3: Execute Parallel Research (Direct Agent, Teams Optional)\n\n\u003Cmandatory>\n**PARALLEL EXECUTION IS MANDATORY - NO EXCEPTIONS.**\n\nRead `${CLAUDE_PLUGIN_ROOT}\u002Freferences\u002Fbounded-parallel-dispatch.md` and follow the full dispatch pattern described there.\n\nKey rules:\n- Minimum 2 agents (1 research-analyst + 1 Explore). There are ZERO exceptions.\n- ALL Agent calls MUST be in ONE message for true parallelism\n- Each research-analyst handles ONE external topic; each Explore handles ONE codebase concern\n- Break external research into MULTIPLE research-analyst teammates (do NOT combine)\n\n**Pre-Step**: Identify and output research topics before spawning:\n```\nResearch topics identified for parallel execution:\n1. [Topic name] - [Agent type: research-analyst\u002FExplore]\n2. [Topic name] - [Agent type: research-analyst\u002FExplore]\n...\n```\n\nDefault to direct `Agent(...)` calls. Agent 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. If team tools are unavailable or fail, continue with direct Agent dispatch; this is normal, not degraded.\n\nDirect path:\n- Optional `TaskCreate` for each research topic. If unavailable or failing, continue without it.\n- Spawn ALL research-analyst and Explore `Agent(...)` calls in ONE message, without `team_name`.\n- Wait for Agent results, collect partial files, then continue to Step 4.\n\nOptional Agent Teams path:\n- `TeamDelete()` once -> `TeamCreate(team_name: \"research-$spec\")` -> optional `TaskCreate` per topic.\n- Spawn ALL teammates in ONE message with `team_name: \"research-$spec\"` and unique `name` values.\n- Wait via automatic teammate messages or one `TaskList` check, send `shutdown_request` to teammates, collect results, then `TeamDelete()`.\n\u003C\u002Fmandatory>\n\n## Step 4: Merge Results\n\nAfter ALL parallel tasks complete, merge into unified `.\u002Fspecs\u002F$spec\u002Fresearch.md`.\n\nRead `${CLAUDE_PLUGIN_ROOT}\u002Freferences\u002Fbounded-parallel-dispatch.md` \"Merging Results\" section for the exact merge structure and process.\n\nAfter merge, delete partial files: `rm .\u002Fspecs\u002F$spec\u002F.research-*.md`\n\n## Step 5: Artifact Review (only in --quick mode)\n\n\u003Cmandatory>\n**Review loop must complete before walkthrough. Max 3 iterations.**\n\nIf NOT `--quick`, skip to Step 6.\n\nInvoke `spec-reviewer` via Agent tool to validate research.md. Follow the standard review loop:\n- REVIEW_PASS: log to .progress.md, proceed to walkthrough\n- REVIEW_FAIL (iteration \u003C 3): log, extract feedback, re-invoke research-analyst with revision prompt, re-read, loop\n- REVIEW_FAIL (iteration >= 3): log warning to .progress.md (graceful degradation), proceed\n- No signal: treat as REVIEW_PASS (permissive)\n\n**Review delegation**: Include full research.md content, iteration count, and prior findings. Upstream: none (research is first artifact).\n\n**Revision delegation**: Re-invoke research-analyst with reviewer feedback. Focus on specific issues flagged.\n\n**Error handling**: Reviewer no signal = REVIEW_PASS. Agent failure during revision = retry once, then use original.\n\u003C\u002Fmandatory>\n\n## Step 6: Walkthrough & Approval\n\n\u003Cmandatory>\n**WALKTHROUGH IS REQUIRED - DO NOT SKIP.**\n\nRead `.\u002Fspecs\u002F$spec\u002Fresearch.md` and display:\n\n```\nResearch complete for '$spec'.\nOutput: $PWD\u002Fspecs\u002F$spec\u002Fresearch.md\n\n## What I Found\n\n**Summary**: [1-2 sentences from Executive Summary]\n\n**Key Recommendations**:\n1. [First recommendation]\n2. [Second recommendation]\n3. [Third recommendation]\n\n**Feasibility**: [High\u002FMedium\u002FLow] | **Risk**: [High\u002FMedium\u002FLow] | **Effort**: [brief plain-language estimate]\n```\n\u003C\u002Fmandatory>\n\n### User Approval (skip if --quick)\n\nIf `--quick`, skip to Step 7.\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 7.\n**If \"Run review\"**: Invoke spec-reviewer via Agent tool with full research.md content (upstream: none). 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\"**: Ask what to change, invoke subagents with feedback, re-merge, re-display walkthrough, ask again with same 3 choices. Loop until approved.\n\n## Step 7: Finalize\n\n### Update State\n\n1. Parse \"Related Specs\" table from research.md\n2. **Merge** into `.curdx-state.json` (preserve all existing fields). `$RELATED_SPECS_JSON` is a JSON array literal (e.g. `'[{\"name\":\"foo\",\"path\":\".\u002Fspecs\u002Ffoo\"}]'`):\n   ```bash\n   PATCH=$(node -e 'const s=process.argv[1]||\"[]\"; process.stdout.write(JSON.stringify({phase:\"research\",awaitingApproval:true,relatedSpecs:JSON.parse(s)}))' \"$RELATED_SPECS_JSON\")\n   curdx-flow state merge \\\n     \"$SPEC_PATH\u002F.curdx-state.json\" \"$PATCH\"\n   ```\n3. Update `.progress.md` with research completion\n\n### Commit Spec (if enabled)\n\nRead `commitSpec` from `.curdx-state.json`. If true:\n```bash\ngit add .\u002Fspecs\u002F$spec\u002Fresearch.md\ngit commit -m \"spec($spec): add research findings\"\ngit push -u origin $(git branch --show-current)\n```\nIf commit or push fails, display warning but continue.\n\n### Stop\n\n\u003Cmandatory>\n**STOP HERE. DO NOT PROCEED TO REQUIREMENTS.**\n\n(Does not apply in `--quick` mode.)\n\n1. Display: `-> Next: Run \u002Fcurdx-flow:requirements`\n2. End your response immediately\n3. Wait for user to explicitly run `\u002Fcurdx-flow:requirements`\n\u003C\u002Fmandatory>\n","# Research Phase\n\nRun parallel research for the active spec. You are a **coordinator, not a researcher** -- delegate ALL work to subagents.\n\n## Coordinator Checklist\n\nComplete these coordination steps in order; do not create user-facing implementation tasks from this checklist:\n\n1. **Gather context** -- resolve spec, read goal and existing files\n2. **Interview** -- brainstorming dialogue (skip if `--quick`)\n3. **Execute parallel research** -- dispatch team of research-analyst + Explore agents\n4. **Merge results** -- synthesize partial files into research.md\n5. **Artifact review** -- spec-reviewer validation loop (only if `--quick`)\n6. **Walkthrough & approval** -- display summary, get user approval\n7. **Finalize** -- update state, commit, stop\n\n## Step 1: Gather Context\n\n1. Run `curdx-flow snapshot --spec \"$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. Read `snapshot.state`, `snapshot.topology`, and `.progress.md` to understand the goal.\n5. Read `references\u002Fworkflow-contract.md`, `references\u002Fagent-output-contract.md`, and `references\u002Fcontext-and-dispatch-policy.md`.\n\n## Step 2: Interview (skip if --quick)\n\nCheck if `--quick` appears in `$ARGUMENTS`. If present, skip to Step 3.\n\n### Read Context from .progress.md\n\nRead `.progress.md` and parse:\n1. **Intent Classification** (TRIVIAL, REFACTOR, GREENFIELD, MID_SIZED) for question counts\n2. **Prior interview responses** to skip already-answered questions\n\n**Intent-Based Question Counts:**\n- TRIVIAL: 1-2 | REFACTOR: 3-5 | GREENFIELD: 5-10 | MID_SIZED: 3-7\n\n### Brainstorming Dialogue\n\nApply adaptive dialogue from `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Finterview-framework\u002FSKILL.md`. Ask context-driven questions one at a time, adapting to prior answers.\n\n**Research Exploration Territory** (hints, not a script):\n- **Technical approach preference** -- follow existing patterns or introduce new ones?\n- **Known constraints** -- performance, compatibility, timeline, budget\n- **Integration surface area** -- which systems, services, or APIs does this touch?\n- **Prior knowledge** -- what does the user already know vs what needs discovery?\n- **Technologies to evaluate or avoid** -- specific libraries, frameworks, or patterns\n\n### Research Approach Proposals\n\nAfter dialogue, propose 2-3 research strategies. Examples (illustrative only):\n- **(A)** Deep dive on specific technology\u002Flibrary comparison\n- **(B)** Focus on existing codebase patterns with minimal external research\n- **(C)** Broad survey across multiple alternatives before narrowing\n\n### Store Interview & Approach\n\nAppend to `.progress.md` under \"Interview Responses\":\n```markdown\n### Research Interview (from research.md)\n- [Topic 1]: [response]\n- Chosen approach: [name] -- [brief description]\n```\n\nPass combined context to subagent delegation as \"Interview Context\".\n\n## Step 3: Execute Parallel Research (Direct Agent, Teams Optional)\n\n\u003Cmandatory>\n**PARALLEL EXECUTION IS MANDATORY - NO EXCEPTIONS.**\n\nRead `${CLAUDE_PLUGIN_ROOT}\u002Freferences\u002Fbounded-parallel-dispatch.md` and follow the full dispatch pattern described there.\n\nKey rules:\n- Minimum 2 agents (1 research-analyst + 1 Explore). There are ZERO exceptions.\n- ALL Agent calls MUST be in ONE message for true parallelism\n- Each research-analyst handles ONE external topic; each Explore handles ONE codebase concern\n- Break external research into MULTIPLE research-analyst teammates (do NOT combine)\n\n**Pre-Step**: Identify and output research topics before spawning:\n```\nResearch topics identified for parallel execution:\n1. [Topic name] - [Agent type: research-analyst\u002FExplore]\n2. [Topic name] - [Agent type: research-analyst\u002FExplore]\n...\n```\n\nDefault to direct `Agent(...)` calls. Agent Teams are experimental and disabled by default in Claude Code; use the team lifecycle only when `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1` is set and the `TeamCreate` \u002F `TaskCreate` \u002F `TaskList` \u002F `SendMessage` tools are visible. If team tools are unavailable or fail, continue with direct Agent dispatch; this is normal, not degraded.\n\nDirect path:\n- Optional `TaskCreate` for each research topic. If unavailable or failing, continue without it.\n- Spawn ALL research-analyst and Explore `Agent(...)` calls in ONE message, without `team_name`.\n- Wait for Agent results, collect partial files, then continue to Step 4.\n\nOptional Agent Teams path:\n- `TeamDelete()` once -> `TeamCreate(team_name: \"research-$spec\")` -> optional `TaskCreate` per topic.\n- Spawn ALL teammates in ONE message with `team_name: \"research-$spec\"` and unique `name` values.\n- Wait via automatic teammate messages or one `TaskList` check, send `shutdown_request` to teammates, collect results, then `TeamDelete()`.\n\u003C\u002Fmandatory>\n\n## Step 4: Merge Results\n\nAfter ALL parallel tasks complete, merge into unified `.\u002Fspecs\u002F$spec\u002Fresearch.md`.\n\nRead `${CLAUDE_PLUGIN_ROOT}\u002Freferences\u002Fbounded-parallel-dispatch.md` \"Merging Results\" section for the exact merge structure and process.\n\nAfter merge, delete partial files: `rm .\u002Fspecs\u002F$spec\u002F.research-*.md`\n\n## Step 5: 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 6.\n\nInvoke `spec-reviewer` via Agent tool to validate research.md. Follow the standard review loop:\n- REVIEW_PASS: log to .progress.md, proceed to walkthrough\n- REVIEW_FAIL (iteration \u003C 3): log, extract feedback, re-invoke research-analyst with revision prompt, re-read, loop\n- REVIEW_FAIL (iteration >= 3): log warning to .progress.md (graceful degradation), proceed\n- No signal: treat as REVIEW_PASS (permissive)\n\n**Review delegation**: Include full research.md content, iteration count, and prior findings. Upstream: none (research is first artifact).\n\n**Revision delegation**: Re-invoke research-analyst with reviewer feedback. Focus on specific issues flagged.\n\n**Error handling**: Reviewer no signal = REVIEW_PASS. Agent failure during revision = retry once, then use original.\n\u003C\u002Fmandatory>\n\n## Step 6: Walkthrough & Approval\n\n\u003Cmandatory>\n**WALKTHROUGH IS REQUIRED - DO NOT SKIP.**\n\nRead `.\u002Fspecs\u002F$spec\u002Fresearch.md` and display:\n\n```\nResearch complete for '$spec'.\nOutput: $PWD\u002Fspecs\u002F$spec\u002Fresearch.md\n\n## What I Found\n\n**Summary**: [1-2 sentences from Executive Summary]\n\n**Key Recommendations**:\n1. [First recommendation]\n2. [Second recommendation]\n3. [Third recommendation]\n\n**Feasibility**: [High\u002FMedium\u002FLow] | **Risk**: [High\u002FMedium\u002FLow] | **Effort**: [brief plain-language estimate]\n```\n\u003C\u002Fmandatory>\n\n### User Approval (skip if --quick)\n\nIf `--quick`, skip to Step 7.\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 7.\n**If \"Run review\"**: Invoke spec-reviewer via Agent tool with full research.md content (upstream: none). 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\"**: Ask what to change, invoke subagents with feedback, re-merge, re-display walkthrough, ask again with same 3 choices. Loop until approved.\n\n## Step 7: Finalize\n\n### Update State\n\n1. Parse \"Related Specs\" table from research.md\n2. **Merge** into `.curdx-state.json` (preserve all existing fields). `$RELATED_SPECS_JSON` is a JSON array literal (e.g. `'[{\"name\":\"foo\",\"path\":\".\u002Fspecs\u002Ffoo\"}]'`):\n   ```bash\n   PATCH=$(node -e 'const s=process.argv[1]||\"[]\"; process.stdout.write(JSON.stringify({phase:\"research\",awaitingApproval:true,relatedSpecs:JSON.parse(s)}))' \"$RELATED_SPECS_JSON\")\n   curdx-flow state merge \\\n     \"$SPEC_PATH\u002F.curdx-state.json\" \"$PATCH\"\n   ```\n3. Update `.progress.md` with research completion\n\n### Commit Spec (if enabled)\n\nRead `commitSpec` from `.curdx-state.json`. If true:\n```bash\ngit add .\u002Fspecs\u002F$spec\u002Fresearch.md\ngit commit -m \"spec($spec): add research findings\"\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 REQUIREMENTS.**\n\n(Does not apply in `--quick` mode.)\n\n1. Display: `-> Next: Run \u002Fcurdx-flow:requirements`\n2. End your response immediately\n3. Wait for user to explicitly run `\u002Fcurdx-flow:requirements`\n\u003C\u002Fmandatory>\n",{"name":5,"description":7,"allowed-tools":47,"argument-hint":48,"disable-model-invocation":49},"Read Write Edit Bash Agent AskUserQuestion","[spec-name]",true,"main","7357746802ae7a84cafa93b9dbffd138817b0290","plugins\u002Fcurdx-flow\u002Fskills\u002Fresearch",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":61,"prompt":71,"zipAvailable":49},[62,65,68],{"tool":63,"command":64},"npx","npx skills add mugsun\u002Fcurdx-flow --skill research",{"tool":66,"command":67},"bunx","bunx skills add mugsun\u002Fcurdx-flow --skill research",{"tool":69,"command":70},"pnpm","pnpm dlx skills add mugsun\u002Fcurdx-flow --skill research","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmugsun\u002Fcurdx-flow\u002Fblob\u002Fmain\u002Fplugins\u002Fcurdx-flow\u002Fskills\u002Fresearch\u002FSKILL.md",[],[74,83,101,113,125,135],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":81,"publishedAt":42},"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",[80],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[76,82],"fixture",{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":42},"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",[],[90,91,92,93,40,94,95,96,97,98,33,99,100],"verification","verification before completion","only","false","tasks","phase","evidence","fixes","tests","mock","state",{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":108,"publishedAt":42},"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",[107],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[103,109,37,110,31,30,111,35,29,40,33,112],"goal","feature","dependency","EPIC",{"skillNo":114,"name":94,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":119,"publishedAt":42},"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",[118],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[94,120,27,35,121,33,122,123,124,40,29,30,31,32,37],"implementation","task","standard","design","auto",{"skillNo":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":132,"publishedAt":42},"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",[131],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[127,29,133,37,33,40,34,35,30,27,31,134],"by name","path",{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":142,"publishedAt":42},"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",[141],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[137,37,33,40,29,100,143,34,144,30,145,146],"progress","update","flow","index"]