[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6BVA666QF84FPVQDA7ZA9WJ":3,"skill-same:01M6BVA666QF84FPVQDA7ZA9WJ":64},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":14,"repositoryHtmlUrl":47,"repositoryHomepageUrl":6,"ownerHtmlUrl":48,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":49,"install":50,"resources":63},"01M6BVA666QF84FPVQDA7ZA9WJ","deep-research",null,"Multi-phase research producing detailed reports with citations. Use when the user requests comprehensive, in-depth research on a topic requiring analysis similar to a whitepaper.","bnferguson\u002Fdotfiles","bnferguson","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F47749?v=4","01M6BV4H2TJKK8P14W86V1ZCPP","Brandon Ferguson","01M6BV4H7GJWTZJ1BVHQ1TX11Y",0,"MIT","https:\u002F\u002Fgithub.com\u002Fbnferguson\u002Fdotfiles\u002Fblob\u002Fmain\u002Fcodex\u002Fconfig\u002Fskills\u002Fdeep-research\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"research","deep research","deep","Citations","analysis","user","use","reports","multi","with","requests","whitepaper","depth","phase","when","2026-11-10 10:12:30",false,"---\nname: deep-research\ndescription: \"Multi-phase research producing detailed reports with citations. Use when the user requests comprehensive, in-depth research on a topic requiring analysis similar to a whitepaper.\"\nlicense: MIT\n---\n\n# Deep Research\n\nThis skill conducts comprehensive research on complex topics using a multi-agent architecture, producing detailed reports similar to academic journals or whitepapers.\n\n## Purpose\n\nThe deep-research skill transforms broad research questions into thorough, well-cited reports using a three-agent system:\n\n1. **Lead Agent (You)**: Conducts interviews, plans research, orchestrates subagents\n2. **Researcher Agents**: Execute web searches and save findings to files\n3. **Report-Writer Agent**: Synthesizes research notes into final report\n\n## When to Use This Skill\n\nUse this skill when the user requests:\n- In-depth research on a complex topic\n- A comprehensive report or analysis\n- Research that requires multiple sources and synthesis\n- Deep investigation similar to academic or whitepaper standards\n- Detailed analysis with proper citations\n\nDo NOT use this skill for:\n- Simple fact-finding queries\n- Single-source information lookup\n- Code-only research within repositories\n- Quick exploratory searches\n\n## Agent Architecture\n\n### Lead Agent (You - the Orchestrator)\n\n**Role**: Interview user, plan research threads, spawn and coordinate subagents\n\n**Tools allowed**: `spawn_agent`, direct user questions, and `apply_patch` (for the research plan only)\n\n**Responsibilities**:\n- Conduct user interview to scope research\n- Perform initial reconnaissance\n- Decompose topic into 10+ research threads\n- Spawn researcher agents in parallel\n- Spawn report-writer agent after research completes\n\n### Researcher Agents\n\n**Role**: Execute focused research on assigned subtopic\n\n**Tools allowed**: web search\u002Fpage retrieval and `apply_patch`\n\n**Responsibilities**:\n- Search the web for information on assigned topic\n- Fetch and analyze relevant pages\n- Save structured research notes to `research_notes\u002F` directory\n\n**Output format**: Each researcher saves a markdown file to `research_notes\u002F[subtopic-slug].md` with:\n- Summary of findings\n- Key facts and data points\n- Source URLs with brief descriptions\n- Notable quotes or excerpts\n- Conflicts or gaps identified\n\n### Report-Writer Agent\n\n**Role**: Synthesize all research notes into final report\n\n**Tools allowed**: file search\u002Fread tools and `apply_patch`\n\n**Responsibilities**:\n- Read all files from `research_notes\u002F` directory\n- Identify themes, patterns, and conflicts across sources\n- Structure and write the final report\n- Create the sources bibliography\n\n## Research Process\n\n### Phase 1: Interview and Scope Definition\n\nStart by interviewing the user to understand their research needs. Ask questions about:\n\n1. **Research objectives**: What are they trying to understand or decide?\n2. **Depth and breadth**: How comprehensive should the research be?\n3. **Target audience**: Who will read this report?\n4. **Key questions**: What specific questions need answering?\n5. **Time constraints**: Is this time-sensitive information?\n6. **Scope boundaries**: What should be explicitly included or excluded?\n\nThe interview should be thorough but efficient. Ask the user directly in no more than 2-3 rounds.\n\n### Phase 2: Initial Reconnaissance\n\nAfter the interview, perform initial reconnaissance to identify the research landscape:\n\n1. Conduct 3-5 broad web searches to map the topic space\n2. Identify key subtopics, domains, and areas of focus\n3. Note promising sources, authoritative voices, and research gaps\n4. Create a research plan outlining 10+ specific research threads\n\nSave the research plan to `research_plan.md` documenting:\n- The research threads identified\n- Which researcher will handle each thread\n- Expected output from each researcher\n\n### Phase 3: Parallel Research (Researcher Agents)\n\nLaunch 10+ researcher agents with `spawn_agent`. Run them in batches that respect the current concurrency limit. Each agent receives a focused research assignment and a unique notes file.\n\n**Spawning researcher agents:**\n\n```\n`spawn_agent` call with:\n- `task_name`: a unique short subtopic slug\n- `message`: Include these elements:\n  1. Clear statement: \"You are a RESEARCHER agent\"\n  2. Specific subtopic assignment\n  3. Tool restrictions: \"Only use web search\u002Fpage retrieval and apply_patch\"\n  4. Output instructions: \"Save your findings to research_notes\u002F[subtopic].md\"\n  5. Format requirements for the research notes file\n```\n\n**Example researcher prompt:**\n```\nYou are a RESEARCHER agent investigating: \"Technical implementation of quantum error correction\"\n\nYOUR TOOLS: Only use web search\u002Fpage retrieval and apply_patch.\n\nTASK:\n1. Search the web for authoritative sources on quantum error correction implementation\n2. Open and read promising sources\n3. Save your findings to research_notes\u002Fquantum-error-correction.md\n\nOUTPUT FORMAT (save to research_notes\u002Fquantum-error-correction.md):\n# Quantum Error Correction Implementation\n\n## Summary\n[2-3 paragraph summary of key findings]\n\n## Key Findings\n- [Bullet points of important facts, data, techniques]\n\n## Sources\n1. [URL] - [Brief description of what this source contributed]\n2. [URL] - [Brief description]\n...\n\n## Notable Quotes\n> \"[Relevant quote]\" - Source\n\n## Gaps and Conflicts\n- [Any conflicting information or areas needing more research]\n```\n\nLaunch as many researcher agents as the current concurrency limit permits. Wait for that batch before starting the remainder.\n\n### Phase 4: Report Generation (Report-Writer Agent)\n\nAfter all researcher agents complete, spawn a single report-writer agent:\n\n**Spawning the report-writer agent:**\n\n```\n`spawn_agent` call with:\n- `task_name`: `report_writer`\n- `message`: Include these elements:\n  1. Clear statement: \"You are a REPORT-WRITER agent\"\n  2. Tool restrictions: \"Only use file search\u002Fread tools and apply_patch\"\n  3. Instructions to read all files from research_notes\u002F\n  4. Report structure requirements\n  5. Output file paths for report and sources\n```\n\n**Example report-writer prompt:**\n```\nYou are a REPORT-WRITER agent synthesizing research findings into a final report.\n\nYOUR TOOLS: Only use file search\u002Fread tools and apply_patch.\n\nTASK:\n1. List all files in research_notes\u002F\n2. Read each research notes file\n3. Synthesize findings into a comprehensive report\n4. Write the final report to [topic]-report.md\n5. Write the sources bibliography to [topic]-sources.md\n\nREPORT STRUCTURE:\n- Executive Summary (2-3 paragraphs)\n- [Adaptive middle sections based on topic]\n- Critical Analysis\n- Conclusions\n- References (numbered citations)\n\nSOURCES FILE STRUCTURE:\n# Research Sources for [Topic]\n\n## [1] Source Title\n- **URL**: [url]\n- **Accessed**: [date]\n- **Type**: [Academic paper \u002F Blog post \u002F Documentation \u002F News article]\n- **Key Points**: [bullet points]\n- **Relevance**: [why this source matters]\n\nWRITING GUIDELINES:\n- Use numbered citations [1], [2], etc.\n- Cross-reference findings across multiple researcher notes\n- Note any conflicts or gaps in the research\n- Use clear, precise academic language\n- Include tables for comparisons where appropriate\n```\n\n### Phase 5: Output and Summary\n\nAfter the report-writer completes:\n\n1. Inform the user of the generated files:\n   - `[topic]-report.md`: Main research report\n   - `[topic]-sources.md`: Complete bibliography\n   - `research_notes\u002F`: Directory of raw research (can be deleted)\n\n2. Provide a brief verbal summary of key findings\n\n3. Offer to answer follow-up questions or expand on any section\n\n## File Structure\n\n```\n.\u002F\n├── research_plan.md           # Your research plan (Phase 2)\n├── research_notes\u002F            # Researcher agent outputs (Phase 3)\n│   ├── subtopic-1.md\n│   ├── subtopic-2.md\n│   └── ...\n├── [topic]-report.md          # Final report (Phase 4)\n└── [topic]-sources.md         # Bibliography (Phase 4)\n```\n\n## Logging and Observability\n\nTrack research progress by documenting in `research_plan.md`:\n\n1. **Research threads assigned**: List each subtopic and its researcher\n2. **Status tracking**: Note when each researcher completes\n3. **Issues encountered**: Document any gaps or conflicts found\n\nThis provides transparency into the research process and helps with debugging or expanding research later.\n\n## Best Practices\n\n### Agent Separation\n\n- **Lead agent**: ONLY spawns agents and coordinates - no direct research\n- **Researchers**: ONLY search, fetch, and write notes - no synthesis\n- **Report-writer**: ONLY reads notes and writes report - no new research\n\nThis separation ensures clean handoffs and reproducible results.\n\n### Research Quality\n\n- Prioritize authoritative, recent sources (especially for time-sensitive topics)\n- Cross-reference claims across multiple researcher notes\n- Note conflicting information or perspectives\n- Distinguish between facts, expert opinions, and speculation\n- Be transparent about limitations in available information\n\n### Efficiency\n\n- Fill the available concurrency slots, then launch another batch as agents finish\n- Use `gpt-5.6-luna` for narrow researcher assignments when cost or latency matters\n- Use `gpt-5.6-terra` with high reasoning for the report-writer when synthesis quality matters\n- Clear task delineation prevents redundant research\n\n## Common Patterns\n\n### Comparative Research\nWhen comparing technologies, approaches, or solutions:\n- Assign one researcher per option being compared\n- Assign one researcher for cross-cutting concerns (performance, cost, etc.)\n- Report-writer creates comparison tables\n\n### Technical Deep-Dives\nWhen researching technical topics:\n- Assign researchers to: fundamentals, implementation, case studies, limitations\n- Report-writer structures from basics to advanced\n\n### Market\u002FLandscape Research\nWhen surveying a domain or market:\n- Assign researchers to: major players, emerging players, trends, analysis firms\n- Report-writer categorizes and evaluates the landscape\n\n### Historical\u002FEvolution Research\nWhen investigating how something developed:\n- Assign researchers to different time periods or key events\n- Report-writer creates timeline and connects to present\n","# Deep Research\n\nThis skill conducts comprehensive research on complex topics using a multi-agent architecture, producing detailed reports similar to academic journals or whitepapers.\n\n## Purpose\n\nThe deep-research skill transforms broad research questions into thorough, well-cited reports using a three-agent system:\n\n1. **Lead Agent (You)**: Conducts interviews, plans research, orchestrates subagents\n2. **Researcher Agents**: Execute web searches and save findings to files\n3. **Report-Writer Agent**: Synthesizes research notes into final report\n\n## When to Use This Skill\n\nUse this skill when the user requests:\n- In-depth research on a complex topic\n- A comprehensive report or analysis\n- Research that requires multiple sources and synthesis\n- Deep investigation similar to academic or whitepaper standards\n- Detailed analysis with proper citations\n\nDo NOT use this skill for:\n- Simple fact-finding queries\n- Single-source information lookup\n- Code-only research within repositories\n- Quick exploratory searches\n\n## Agent Architecture\n\n### Lead Agent (You - the Orchestrator)\n\n**Role**: Interview user, plan research threads, spawn and coordinate subagents\n\n**Tools allowed**: `spawn_agent`, direct user questions, and `apply_patch` (for the research plan only)\n\n**Responsibilities**:\n- Conduct user interview to scope research\n- Perform initial reconnaissance\n- Decompose topic into 10+ research threads\n- Spawn researcher agents in parallel\n- Spawn report-writer agent after research completes\n\n### Researcher Agents\n\n**Role**: Execute focused research on assigned subtopic\n\n**Tools allowed**: web search\u002Fpage retrieval and `apply_patch`\n\n**Responsibilities**:\n- Search the web for information on assigned topic\n- Fetch and analyze relevant pages\n- Save structured research notes to `research_notes\u002F` directory\n\n**Output format**: Each researcher saves a markdown file to `research_notes\u002F[subtopic-slug].md` with:\n- Summary of findings\n- Key facts and data points\n- Source URLs with brief descriptions\n- Notable quotes or excerpts\n- Conflicts or gaps identified\n\n### Report-Writer Agent\n\n**Role**: Synthesize all research notes into final report\n\n**Tools allowed**: file search\u002Fread tools and `apply_patch`\n\n**Responsibilities**:\n- Read all files from `research_notes\u002F` directory\n- Identify themes, patterns, and conflicts across sources\n- Structure and write the final report\n- Create the sources bibliography\n\n## Research Process\n\n### Phase 1: Interview and Scope Definition\n\nStart by interviewing the user to understand their research needs. Ask questions about:\n\n1. **Research objectives**: What are they trying to understand or decide?\n2. **Depth and breadth**: How comprehensive should the research be?\n3. **Target audience**: Who will read this report?\n4. **Key questions**: What specific questions need answering?\n5. **Time constraints**: Is this time-sensitive information?\n6. **Scope boundaries**: What should be explicitly included or excluded?\n\nThe interview should be thorough but efficient. Ask the user directly in no more than 2-3 rounds.\n\n### Phase 2: Initial Reconnaissance\n\nAfter the interview, perform initial reconnaissance to identify the research landscape:\n\n1. Conduct 3-5 broad web searches to map the topic space\n2. Identify key subtopics, domains, and areas of focus\n3. Note promising sources, authoritative voices, and research gaps\n4. Create a research plan outlining 10+ specific research threads\n\nSave the research plan to `research_plan.md` documenting:\n- The research threads identified\n- Which researcher will handle each thread\n- Expected output from each researcher\n\n### Phase 3: Parallel Research (Researcher Agents)\n\nLaunch 10+ researcher agents with `spawn_agent`. Run them in batches that respect the current concurrency limit. Each agent receives a focused research assignment and a unique notes file.\n\n**Spawning researcher agents:**\n\n```\n`spawn_agent` call with:\n- `task_name`: a unique short subtopic slug\n- `message`: Include these elements:\n  1. Clear statement: \"You are a RESEARCHER agent\"\n  2. Specific subtopic assignment\n  3. Tool restrictions: \"Only use web search\u002Fpage retrieval and apply_patch\"\n  4. Output instructions: \"Save your findings to research_notes\u002F[subtopic].md\"\n  5. Format requirements for the research notes file\n```\n\n**Example researcher prompt:**\n```\nYou are a RESEARCHER agent investigating: \"Technical implementation of quantum error correction\"\n\nYOUR TOOLS: Only use web search\u002Fpage retrieval and apply_patch.\n\nTASK:\n1. Search the web for authoritative sources on quantum error correction implementation\n2. Open and read promising sources\n3. Save your findings to research_notes\u002Fquantum-error-correction.md\n\nOUTPUT FORMAT (save to research_notes\u002Fquantum-error-correction.md):\n# Quantum Error Correction Implementation\n\n## Summary\n[2-3 paragraph summary of key findings]\n\n## Key Findings\n- [Bullet points of important facts, data, techniques]\n\n## Sources\n1. [URL] - [Brief description of what this source contributed]\n2. [URL] - [Brief description]\n...\n\n## Notable Quotes\n> \"[Relevant quote]\" - Source\n\n## Gaps and Conflicts\n- [Any conflicting information or areas needing more research]\n```\n\nLaunch as many researcher agents as the current concurrency limit permits. Wait for that batch before starting the remainder.\n\n### Phase 4: Report Generation (Report-Writer Agent)\n\nAfter all researcher agents complete, spawn a single report-writer agent:\n\n**Spawning the report-writer agent:**\n\n```\n`spawn_agent` call with:\n- `task_name`: `report_writer`\n- `message`: Include these elements:\n  1. Clear statement: \"You are a REPORT-WRITER agent\"\n  2. Tool restrictions: \"Only use file search\u002Fread tools and apply_patch\"\n  3. Instructions to read all files from research_notes\u002F\n  4. Report structure requirements\n  5. Output file paths for report and sources\n```\n\n**Example report-writer prompt:**\n```\nYou are a REPORT-WRITER agent synthesizing research findings into a final report.\n\nYOUR TOOLS: Only use file search\u002Fread tools and apply_patch.\n\nTASK:\n1. List all files in research_notes\u002F\n2. Read each research notes file\n3. Synthesize findings into a comprehensive report\n4. Write the final report to [topic]-report.md\n5. Write the sources bibliography to [topic]-sources.md\n\nREPORT STRUCTURE:\n- Executive Summary (2-3 paragraphs)\n- [Adaptive middle sections based on topic]\n- Critical Analysis\n- Conclusions\n- References (numbered citations)\n\nSOURCES FILE STRUCTURE:\n# Research Sources for [Topic]\n\n## [1] Source Title\n- **URL**: [url]\n- **Accessed**: [date]\n- **Type**: [Academic paper \u002F Blog post \u002F Documentation \u002F News article]\n- **Key Points**: [bullet points]\n- **Relevance**: [why this source matters]\n\nWRITING GUIDELINES:\n- Use numbered citations [1], [2], etc.\n- Cross-reference findings across multiple researcher notes\n- Note any conflicts or gaps in the research\n- Use clear, precise academic language\n- Include tables for comparisons where appropriate\n```\n\n### Phase 5: Output and Summary\n\nAfter the report-writer completes:\n\n1. Inform the user of the generated files:\n   - `[topic]-report.md`: Main research report\n   - `[topic]-sources.md`: Complete bibliography\n   - `research_notes\u002F`: Directory of raw research (can be deleted)\n\n2. Provide a brief verbal summary of key findings\n\n3. Offer to answer follow-up questions or expand on any section\n\n## File Structure\n\n```\n.\u002F\n├── research_plan.md           # Your research plan (Phase 2)\n├── research_notes\u002F            # Researcher agent outputs (Phase 3)\n│   ├── subtopic-1.md\n│   ├── subtopic-2.md\n│   └── ...\n├── [topic]-report.md          # Final report (Phase 4)\n└── [topic]-sources.md         # Bibliography (Phase 4)\n```\n\n## Logging and Observability\n\nTrack research progress by documenting in `research_plan.md`:\n\n1. **Research threads assigned**: List each subtopic and its researcher\n2. **Status tracking**: Note when each researcher completes\n3. **Issues encountered**: Document any gaps or conflicts found\n\nThis provides transparency into the research process and helps with debugging or expanding research later.\n\n## Best Practices\n\n### Agent Separation\n\n- **Lead agent**: ONLY spawns agents and coordinates - no direct research\n- **Researchers**: ONLY search, fetch, and write notes - no synthesis\n- **Report-writer**: ONLY reads notes and writes report - no new research\n\nThis separation ensures clean handoffs and reproducible results.\n\n### Research Quality\n\n- Prioritize authoritative, recent sources (especially for time-sensitive topics)\n- Cross-reference claims across multiple researcher notes\n- Note conflicting information or perspectives\n- Distinguish between facts, expert opinions, and speculation\n- Be transparent about limitations in available information\n\n### Efficiency\n\n- Fill the available concurrency slots, then launch another batch as agents finish\n- Use `gpt-5.6-luna` for narrow researcher assignments when cost or latency matters\n- Use `gpt-5.6-terra` with high reasoning for the report-writer when synthesis quality matters\n- Clear task delineation prevents redundant research\n\n## Common Patterns\n\n### Comparative Research\nWhen comparing technologies, approaches, or solutions:\n- Assign one researcher per option being compared\n- Assign one researcher for cross-cutting concerns (performance, cost, etc.)\n- Report-writer creates comparison tables\n\n### Technical Deep-Dives\nWhen researching technical topics:\n- Assign researchers to: fundamentals, implementation, case studies, limitations\n- Report-writer structures from basics to advanced\n\n### Market\u002FLandscape Research\nWhen surveying a domain or market:\n- Assign researchers to: major players, emerging players, trends, analysis firms\n- Report-writer categorizes and evaluates the landscape\n\n### Historical\u002FEvolution Research\nWhen investigating how something developed:\n- Assign researchers to different time periods or key events\n- Report-writer creates timeline and connects to present\n",{"name":5,"license":15,"description":7},"main","e63965e4644984470d4cc8b3014a8b001f0c2666","codex\u002Fconfig\u002Fskills\u002Fdeep-research","https:\u002F\u002Fgithub.com\u002Fbnferguson\u002Fdotfiles","https:\u002F\u002Fgithub.com\u002Fbnferguson","2026-11-11 03:04:59",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add bnferguson\u002Fdotfiles --skill deep-research",{"tool":56,"command":57},"bunx","bunx skills add bnferguson\u002Fdotfiles --skill deep-research",{"tool":59,"command":60},"pnpm","pnpm dlx skills add bnferguson\u002Fdotfiles --skill deep-research","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbnferguson\u002Fdotfiles\u002Fblob\u002Fmain\u002Fcodex\u002Fconfig\u002Fskills\u002Fdeep-research\u002FSKILL.md",true,[],[65,94,111,141,150,163],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"licenseFileUrl":70,"sourceHtmlUrl":71,"categories":72,"keywords":76,"publishedAt":39},"01M6BVA3RS3M016FANZ6792F9H","skill-creator","Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fbnferguson\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude\u002Fconfig\u002Fskills\u002Fskill-creator\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fbnferguson\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude\u002Fconfig\u002Fskills\u002Fskill-creator\u002FSKILL.md",[73],{"categoryNo":74,"categoryName":75,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[77,78,79,80,81,82,83,84,85,86,87,88,89,90,33,91,92,38,93],"creator","skill creator","specialized","workflows","create","update","capabilities","knowledge","tool","integrations","guide","new skill","existing skill","users","for","Existing","new",{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":108,"publishedAt":39},"01M6BV94WN2RPYM8N6PN8TBNT8","writing-shape","Writing, exploit: shape raw material into an article, paragraph by paragraph.","https:\u002F\u002Fgithub.com\u002Fbnferguson\u002Fdotfiles\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwriting-shape\u002FSKILL.md",[100,103],{"categoryNo":101,"categoryName":102,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":104,"categoryName":105,"taxonomyType":106,"taxonomyTypeDesc":107},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[109,110],"writing shape","writing",{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"licenseFileUrl":115,"sourceHtmlUrl":116,"categories":117,"keywords":124,"publishedAt":39},"01M6BV8QDFJ6PXBVK5NFBZT5M7","webapp-testing","Test local web applications using Playwright. Use when verifying frontend functionality, debugging UI behavior, capturing browser screenshots, or viewing browser logs.","https:\u002F\u002Fgithub.com\u002Fbnferguson\u002Fdotfiles\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fbnferguson\u002Fdotfiles\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[118,121],{"categoryNo":119,"categoryName":120,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":122,"categoryName":123,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[125,126,127,128,129,130,131,132,133,134,135,136,137,138,30,139,140,38],"webapp","webapp testing","testing","browser","frontend","screenshots","playwright","test","web","debugging","ui","logs","applications","behavior","local","test local",{"skillNo":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":147,"publishedAt":39},"01M6BV8MDXKXNVHKS3QF3YDFTF","wait-what","Stop. That last message did not land: re-pitch it.","https:\u002F\u002Fgithub.com\u002Fbnferguson\u002Fdotfiles\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwait-what\u002FSKILL.md",[],[148,149],"wait what","land",{"skillNo":151,"name":152,"nameZh":6,"description":153,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":154,"categories":155,"keywords":159,"publishedAt":39},"01M6BV756DJHT5BDA1HVRVHJJ7","prototype","Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.","https:\u002F\u002Fgithub.com\u002Fbnferguson\u002Fdotfiles\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fprototype\u002FSKILL.md",[156],{"categoryNo":157,"categoryName":158,"taxonomyType":106,"taxonomyTypeDesc":107},"01JBSEEDCAT000000000000032","设计师",[152,160,161,135,162],"design","explore","state",{"skillNo":164,"name":165,"nameZh":6,"description":166,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":167,"categories":168,"keywords":170,"publishedAt":39},"01M6BV6SBW166685KVBPWM2K4N","improve-codebase-architecture","Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.","https:\u002F\u002Fgithub.com\u002Fbnferguson\u002Fdotfiles\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fimprove-codebase-architecture\u002FSKILL.md",[169],{"categoryNo":122,"categoryName":123,"taxonomyType":21,"taxonomyTypeDesc":22},[171,172,173,174],"architecture","improve","improve codebase architecture","report"]