[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M72ZAD3PF8EYZEVNE0FMY8EB":3,"skill-same:01M72ZAD3PF8EYZEVNE0FMY8EB":254},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M72ZAD3PF8EYZEVNE0FMY8EB","bmad-agent-builder",null,"Builds, edits or analyzes Agent Skills through conversational discovery. Use when the user requests to \"Create an Agent\", \"Analyze an Agent\" or \"Edit an Agent\".","developAgent\u002Fbmad-start","developAgent","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F264530239?v=4","01M71J8X6CY24V5ZZHFGETRMSW","01M71J8X739FS28DGQAAY7V4QR",1,"MIT","https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: bmad-agent-builder\ndescription: Builds, edits or analyzes Agent Skills through conversational discovery. Use when the user requests to \"Create an Agent\", \"Analyze an Agent\" or \"Edit an Agent\".\n---\n\n# Agent Builder\n\n## Overview\n\nThis skill helps you build AI agents that are **outcome-driven** — describing what each capability achieves, not micromanaging how. Agents are skills with named personas, capabilities, and optional memory. Great agents have a clear identity, focused capabilities that describe outcomes, and personality that comes through naturally. Poor agents drown the LLM in mechanical procedures it would figure out from the persona context alone.\n\nAct as an architect guide — walk users through conversational discovery to understand who their agent is, what it should achieve, and how it should make users feel. Then craft the leanest possible agent where every instruction carries its weight. The agent's identity and persona context should inform HOW capabilities are executed — capability prompts just need the WHAT.\n\n**Args:** Accepts `--headless` \u002F `-H` for non-interactive execution, an initial description for create, or a path to an existing agent with keywords like analyze, edit, or rebuild.\n\n**Your output:** A complete agent skill structure — persona, capabilities, optional memory and headless modes — ready to integrate into a module or use standalone.\n\n## On Activation\n\n1. Detect user's intent. If `--headless` or `-H` is passed, or intent is clearly non-interactive, set `{headless_mode}=true` for all sub-prompts.\n\n2. Load available config from `{project-root}\u002F_bmad\u002Fconfig.yaml` and `{project-root}\u002F_bmad\u002Fconfig.user.yaml` (root and bmb section). If neither exists, fall back to `{project-root}\u002F_bmad\u002Fbmb\u002Fconfig.yaml` (legacy per-module format). If still missing, and the `bmad-builder-setup` skill is available, let the user know they can run it at any time to configure. Resolve and apply throughout the session (defaults in parens):\n   - `{user_name}` (default: null) — address the user by name\n   - `{communication_language}` (default: user or system intent) — use for all communications\n   - `{document_output_language}` (default: user or system intent) — use for generated document content\n   - `{bmad_builder_output_folder}` (default: `{project-root}\u002Fskills`) — save built agents here\n   - `{bmad_builder_reports}` (default: `{project-root}\u002Fskills\u002Freports`) — save reports (quality, eval, planning) here\n\n3. Route by intent — see Quick Reference below.\n\n## Build Process\n\nThe core creative path — where agent ideas become reality. Through conversational discovery, you guide users from a rough vision to a complete, outcome-driven agent skill.\n\nThe builder produces three agent types along a spectrum:\n\n- **Stateless agent** — everything in SKILL.md, no memory, no First Breath. For focused experts handling isolated sessions.\n- **Memory agent** — lean bootloader SKILL.md + sanctum (6 standard files + First Breath). For agents that build understanding over time.\n- **Autonomous agent** — memory agent + PULSE. For agents that operate on their own between sessions.\n\nAgent type is determined during Phase 1 discovery, not upfront. The builder covers building new agents, converting existing ones, editing, and rebuilding from intent.\n\nLoad `.\u002Freferences\u002Fbuild-process.md` to begin.\n\n## Quality Analysis\n\nComprehensive quality analysis toward outcome-driven design. Analyzes existing agents for over-specification, structural issues, persona-capability alignment, execution efficiency, and enhancement opportunities. Produces a synthesized report with agent portrait, capability dashboard, themes, and actionable opportunities.\n\nLoad `.\u002Freferences\u002Fquality-analysis.md` to begin.\n\n---\n\n## Quick Reference\n\n| Intent                      | Trigger Phrases                                       | Route                                    |\n| --------------------------- | ----------------------------------------------------- | ---------------------------------------- |\n| **Build new**               | \"build\u002Fcreate\u002Fdesign a new agent\"                     | Load `.\u002Freferences\u002Fbuild-process.md`                |\n| **Existing agent provided** | Path to existing agent, or \"convert\u002Fedit\u002Ffix\u002Fanalyze\" | Ask the 3-way question below, then route |\n| **Quality analyze**         | \"quality check\", \"validate\", \"review agent\"           | Load `.\u002Freferences\u002Fquality-analysis.md`             |\n| **Unclear**                 | —                                                     | Present options and ask                  |\n\n### When given an existing agent, ask:\n\n- **Analyze** — Run quality analysis: identify opportunities, prune over-specification, get an actionable report with agent portrait and capability dashboard\n- **Edit** — Modify specific behavior while keeping the current approach\n- **Rebuild** — Rethink from core outcomes and persona, using this as reference material, full discovery process\n\nAnalyze routes to `.\u002Freferences\u002Fquality-analysis.md`. Edit routes to `.\u002Freferences\u002Fedit-guidance.md`. Rebuild routes to `.\u002Freferences\u002Fbuild-process.md` with the chosen intent.\n\nRegardless of path, respect headless mode if requested.\n","# Agent Builder\n\n## Overview\n\nThis skill helps you build AI agents that are **outcome-driven** — describing what each capability achieves, not micromanaging how. Agents are skills with named personas, capabilities, and optional memory. Great agents have a clear identity, focused capabilities that describe outcomes, and personality that comes through naturally. Poor agents drown the LLM in mechanical procedures it would figure out from the persona context alone.\n\nAct as an architect guide — walk users through conversational discovery to understand who their agent is, what it should achieve, and how it should make users feel. Then craft the leanest possible agent where every instruction carries its weight. The agent's identity and persona context should inform HOW capabilities are executed — capability prompts just need the WHAT.\n\n**Args:** Accepts `--headless` \u002F `-H` for non-interactive execution, an initial description for create, or a path to an existing agent with keywords like analyze, edit, or rebuild.\n\n**Your output:** A complete agent skill structure — persona, capabilities, optional memory and headless modes — ready to integrate into a module or use standalone.\n\n## On Activation\n\n1. Detect user's intent. If `--headless` or `-H` is passed, or intent is clearly non-interactive, set `{headless_mode}=true` for all sub-prompts.\n\n2. Load available config from `{project-root}\u002F_bmad\u002Fconfig.yaml` and `{project-root}\u002F_bmad\u002Fconfig.user.yaml` (root and bmb section). If neither exists, fall back to `{project-root}\u002F_bmad\u002Fbmb\u002Fconfig.yaml` (legacy per-module format). If still missing, and the `bmad-builder-setup` skill is available, let the user know they can run it at any time to configure. Resolve and apply throughout the session (defaults in parens):\n   - `{user_name}` (default: null) — address the user by name\n   - `{communication_language}` (default: user or system intent) — use for all communications\n   - `{document_output_language}` (default: user or system intent) — use for generated document content\n   - `{bmad_builder_output_folder}` (default: `{project-root}\u002Fskills`) — save built agents here\n   - `{bmad_builder_reports}` (default: `{project-root}\u002Fskills\u002Freports`) — save reports (quality, eval, planning) here\n\n3. Route by intent — see Quick Reference below.\n\n## Build Process\n\nThe core creative path — where agent ideas become reality. Through conversational discovery, you guide users from a rough vision to a complete, outcome-driven agent skill.\n\nThe builder produces three agent types along a spectrum:\n\n- **Stateless agent** — everything in SKILL.md, no memory, no First Breath. For focused experts handling isolated sessions.\n- **Memory agent** — lean bootloader SKILL.md + sanctum (6 standard files + First Breath). For agents that build understanding over time.\n- **Autonomous agent** — memory agent + PULSE. For agents that operate on their own between sessions.\n\nAgent type is determined during Phase 1 discovery, not upfront. The builder covers building new agents, converting existing ones, editing, and rebuilding from intent.\n\nLoad `.\u002Freferences\u002Fbuild-process.md` to begin.\n\n## Quality Analysis\n\nComprehensive quality analysis toward outcome-driven design. Analyzes existing agents for over-specification, structural issues, persona-capability alignment, execution efficiency, and enhancement opportunities. Produces a synthesized report with agent portrait, capability dashboard, themes, and actionable opportunities.\n\nLoad `.\u002Freferences\u002Fquality-analysis.md` to begin.\n\n---\n\n## Quick Reference\n\n| Intent                      | Trigger Phrases                                       | Route                                    |\n| --------------------------- | ----------------------------------------------------- | ---------------------------------------- |\n| **Build new**               | \"build\u002Fcreate\u002Fdesign a new agent\"                     | Load `.\u002Freferences\u002Fbuild-process.md`                |\n| **Existing agent provided** | Path to existing agent, or \"convert\u002Fedit\u002Ffix\u002Fanalyze\" | Ask the 3-way question below, then route |\n| **Quality analyze**         | \"quality check\", \"validate\", \"review agent\"           | Load `.\u002Freferences\u002Fquality-analysis.md`             |\n| **Unclear**                 | —                                                     | Present options and ask                  |\n\n### When given an existing agent, ask:\n\n- **Analyze** — Run quality analysis: identify opportunities, prune over-specification, get an actionable report with agent portrait and capability dashboard\n- **Edit** — Modify specific behavior while keeping the current approach\n- **Rebuild** — Rethink from core outcomes and persona, using this as reference material, full discovery process\n\nAnalyze routes to `.\u002Freferences\u002Fquality-analysis.md`. Edit routes to `.\u002Freferences\u002Fedit-guidance.md`. Rebuild routes to `.\u002Freferences\u002Fbuild-process.md` with the chosen intent.\n\nRegardless of path, respect headless mode if requested.\n",{"name":5,"description":7},"main","1907bbe850fb749efa8b499b8da7ebb78a663519",".windsurf\u002Fskills\u002Fbmad-agent-builder",0,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start","https:\u002F\u002Fgithub.com\u002FdevelopAgent","2026-07-19 05:19:22",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add developAgent\u002Fbmad-start --skill bmad-agent-builder",{"tool":36,"command":37},"bunx","bunx skills add developAgent\u002Fbmad-start --skill bmad-agent-builder",{"tool":39,"command":40},"pnpm","pnpm dlx skills add developAgent\u002Fbmad-start --skill bmad-agent-builder","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002FSKILL.md",true,[44,50,54,58,62,66,70,74,78,84,88,92,96,100,104,108,112,118,122,126,130,134,138,142,146,150,154,158,162,166,170,174,178,182,186,190,194,198,202,206,210,214,218,222,226,230,234,238,242,246,250],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"assets\u002FBOND-template.md","ASSET","资产文件",344,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Fassets\u002FBOND-template.md",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":52,"sourceHtmlUrl":53},"assets\u002FCAPABILITIES-template.md",907,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Fassets\u002FCAPABILITIES-template.md",{"path":55,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":56,"sourceHtmlUrl":57},"assets\u002Fcapability-authoring-template.md",3798,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Fassets\u002Fcapability-authoring-template.md",{"path":59,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":60,"sourceHtmlUrl":61},"assets\u002FCREED-template.md",1367,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Fassets\u002FCREED-template.md",{"path":63,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":64,"sourceHtmlUrl":65},"assets\u002Fcustomize-template.toml",2394,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Fassets\u002Fcustomize-template.toml",{"path":67,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":68,"sourceHtmlUrl":69},"assets\u002Ffirst-breath-config-template.md",3316,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Fassets\u002Ffirst-breath-config-template.md",{"path":71,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":72,"sourceHtmlUrl":73},"assets\u002Ffirst-breath-template.md",8364,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Fassets\u002Ffirst-breath-template.md",{"path":75,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":76,"sourceHtmlUrl":77},"assets\u002FINDEX-template.md",634,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Fassets\u002FINDEX-template.md",{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"assets\u002Finit-sanctum-template.py","SCRIPT","脚本",9509,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Fassets\u002Finit-sanctum-template.py",{"path":85,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":86,"sourceHtmlUrl":87},"assets\u002Fmemory-guidance-template.md",4167,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Fassets\u002Fmemory-guidance-template.md",{"path":89,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":90,"sourceHtmlUrl":91},"assets\u002FMEMORY-template.md",523,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Fassets\u002FMEMORY-template.md",{"path":93,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":94,"sourceHtmlUrl":95},"assets\u002FPERSONA-template.md",714,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Fassets\u002FPERSONA-template.md",{"path":97,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":98,"sourceHtmlUrl":99},"assets\u002FPULSE-template.md",1983,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Fassets\u002FPULSE-template.md",{"path":101,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":102,"sourceHtmlUrl":103},"assets\u002Fsample-customize-analyst.toml",3544,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Fassets\u002Fsample-customize-analyst.toml",{"path":105,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":106,"sourceHtmlUrl":107},"assets\u002FSKILL-template-bootloader.md",3619,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Fassets\u002FSKILL-template-bootloader.md",{"path":109,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":110,"sourceHtmlUrl":111},"assets\u002FSKILL-template.md",3867,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Fassets\u002FSKILL-template.md",{"path":113,"resourceType":114,"resourceTypeDesc":115,"sizeBytes":116,"sourceHtmlUrl":117},"references\u002Fagent-type-guidance.md","REFERENCE","参考文档",6031,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Freferences\u002Fagent-type-guidance.md",{"path":119,"resourceType":114,"resourceTypeDesc":115,"sizeBytes":120,"sourceHtmlUrl":121},"references\u002Fbuild-process.md",24032,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Freferences\u002Fbuild-process.md",{"path":123,"resourceType":114,"resourceTypeDesc":115,"sizeBytes":124,"sourceHtmlUrl":125},"references\u002Fedit-guidance.md",5955,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Freferences\u002Fedit-guidance.md",{"path":127,"resourceType":114,"resourceTypeDesc":115,"sizeBytes":128,"sourceHtmlUrl":129},"references\u002Ffirst-breath-adaptation-guidance.md",6669,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Freferences\u002Ffirst-breath-adaptation-guidance.md",{"path":131,"resourceType":114,"resourceTypeDesc":115,"sizeBytes":132,"sourceHtmlUrl":133},"references\u002Fmission-writing-guidance.md",3890,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Freferences\u002Fmission-writing-guidance.md",{"path":135,"resourceType":114,"resourceTypeDesc":115,"sizeBytes":136,"sourceHtmlUrl":137},"references\u002Fquality-analysis.md",7628,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Freferences\u002Fquality-analysis.md",{"path":139,"resourceType":114,"resourceTypeDesc":115,"sizeBytes":140,"sourceHtmlUrl":141},"references\u002Fquality-dimensions.md",6001,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Freferences\u002Fquality-dimensions.md",{"path":143,"resourceType":114,"resourceTypeDesc":115,"sizeBytes":144,"sourceHtmlUrl":145},"references\u002Fquality-scan-agent-cohesion.md",9062,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Freferences\u002Fquality-scan-agent-cohesion.md",{"path":147,"resourceType":114,"resourceTypeDesc":115,"sizeBytes":148,"sourceHtmlUrl":149},"references\u002Fquality-scan-customization-surface.md",11355,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Freferences\u002Fquality-scan-customization-surface.md",{"path":151,"resourceType":114,"resourceTypeDesc":115,"sizeBytes":152,"sourceHtmlUrl":153},"references\u002Fquality-scan-enhancement-opportunities.md",15800,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Freferences\u002Fquality-scan-enhancement-opportunities.md",{"path":155,"resourceType":114,"resourceTypeDesc":115,"sizeBytes":156,"sourceHtmlUrl":157},"references\u002Fquality-scan-execution-efficiency.md",9069,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Freferences\u002Fquality-scan-execution-efficiency.md",{"path":159,"resourceType":114,"resourceTypeDesc":115,"sizeBytes":160,"sourceHtmlUrl":161},"references\u002Fquality-scan-prompt-craft.md",19840,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Freferences\u002Fquality-scan-prompt-craft.md",{"path":163,"resourceType":114,"resourceTypeDesc":115,"sizeBytes":164,"sourceHtmlUrl":165},"references\u002Fquality-scan-sanctum-architecture.md",9296,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Freferences\u002Fquality-scan-sanctum-architecture.md",{"path":167,"resourceType":114,"resourceTypeDesc":115,"sizeBytes":168,"sourceHtmlUrl":169},"references\u002Fquality-scan-script-opportunities.md",11704,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Freferences\u002Fquality-scan-script-opportunities.md",{"path":171,"resourceType":114,"resourceTypeDesc":115,"sizeBytes":172,"sourceHtmlUrl":173},"references\u002Fquality-scan-structure.md",13245,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Freferences\u002Fquality-scan-structure.md",{"path":175,"resourceType":114,"resourceTypeDesc":115,"sizeBytes":176,"sourceHtmlUrl":177},"references\u002Freport-quality-scan-creator.md",13001,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Freferences\u002Freport-quality-scan-creator.md",{"path":179,"resourceType":114,"resourceTypeDesc":115,"sizeBytes":180,"sourceHtmlUrl":181},"references\u002Fsample-capability-authoring.md",3833,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Freferences\u002Fsample-capability-authoring.md",{"path":183,"resourceType":114,"resourceTypeDesc":115,"sizeBytes":184,"sourceHtmlUrl":185},"references\u002Fsample-capability-prompt.md",4107,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Freferences\u002Fsample-capability-prompt.md",{"path":187,"resourceType":114,"resourceTypeDesc":115,"sizeBytes":188,"sourceHtmlUrl":189},"references\u002Fsample-first-breath.md",9256,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Freferences\u002Fsample-first-breath.md",{"path":191,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":192,"sourceHtmlUrl":193},"references\u002Fsample-init-sanctum.py",9452,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Freferences\u002Fsample-init-sanctum.py",{"path":195,"resourceType":114,"resourceTypeDesc":115,"sizeBytes":196,"sourceHtmlUrl":197},"references\u002Fsample-memory-guidance.md",4250,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Freferences\u002Fsample-memory-guidance.md",{"path":199,"resourceType":114,"resourceTypeDesc":115,"sizeBytes":200,"sourceHtmlUrl":201},"references\u002Fscript-opportunities-reference.md",13331,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Freferences\u002Fscript-opportunities-reference.md",{"path":203,"resourceType":114,"resourceTypeDesc":115,"sizeBytes":204,"sourceHtmlUrl":205},"references\u002Fscript-standards.md",4458,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Freferences\u002Fscript-standards.md",{"path":207,"resourceType":114,"resourceTypeDesc":115,"sizeBytes":208,"sourceHtmlUrl":209},"references\u002Fskill-best-practices.md",10076,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Freferences\u002Fskill-best-practices.md",{"path":211,"resourceType":114,"resourceTypeDesc":115,"sizeBytes":212,"sourceHtmlUrl":213},"references\u002Fstandard-fields.md",10999,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Freferences\u002Fstandard-fields.md",{"path":215,"resourceType":114,"resourceTypeDesc":115,"sizeBytes":216,"sourceHtmlUrl":217},"references\u002Fstanding-order-guidance.md",5665,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Freferences\u002Fstanding-order-guidance.md",{"path":219,"resourceType":114,"resourceTypeDesc":115,"sizeBytes":220,"sourceHtmlUrl":221},"references\u002Ftemplate-substitution-rules.md",4957,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Freferences\u002Ftemplate-substitution-rules.md",{"path":223,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":224,"sourceHtmlUrl":225},"scripts\u002Fgenerate-html-report.py",26127,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Fscripts\u002Fgenerate-html-report.py",{"path":227,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":228,"sourceHtmlUrl":229},"scripts\u002Fprepass-execution-deps.py",11713,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Fscripts\u002Fprepass-execution-deps.py",{"path":231,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":232,"sourceHtmlUrl":233},"scripts\u002Fprepass-prompt-metrics.py",15352,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Fscripts\u002Fprepass-prompt-metrics.py",{"path":235,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":236,"sourceHtmlUrl":237},"scripts\u002Fprepass-sanctum-architecture.py",13029,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Fscripts\u002Fprepass-sanctum-architecture.py",{"path":239,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":240,"sourceHtmlUrl":241},"scripts\u002Fprepass-structure-capabilities.py",17043,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Fscripts\u002Fprepass-structure-capabilities.py",{"path":243,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":244,"sourceHtmlUrl":245},"scripts\u002Fprocess-template.py",5859,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Fscripts\u002Fprocess-template.py",{"path":247,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":248,"sourceHtmlUrl":249},"scripts\u002Fscan-path-standards.py",11960,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Fscripts\u002Fscan-path-standards.py",{"path":251,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":252,"sourceHtmlUrl":253},"scripts\u002Fscan-scripts.py",26898,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.windsurf\u002Fskills\u002Fbmad-agent-builder\u002Fscripts\u002Fscan-scripts.py",[255,262,269,276,283,290],{"skillNo":256,"name":257,"nameZh":6,"description":258,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":259,"categories":260,"keywords":261,"publishedAt":18},"01M72ZN1RJ28HE3TG8CK5VMDZ0","writing-plans","Use when you have a spec or requirements for a multi-step task, before touching code","https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-plans\u002FSKILL.md",[],[],{"skillNo":263,"name":264,"nameZh":6,"description":265,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":266,"categories":267,"keywords":268,"publishedAt":18},"01M72ZMZG4KQAFDEHG6KABQW8R","to-prd","Turn the current conversation into a PRD and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.","https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002Fskills\u002Fto-prd\u002FSKILL.md",[],[],{"skillNo":270,"name":271,"nameZh":6,"description":272,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":273,"categories":274,"keywords":275,"publishedAt":18},"01M72ZMWB9ZNA0Y5KGAHTW89E8","steve-jobs-perspective","史蒂夫·乔布斯(Steve Jobs)的思维框架与表达方式。基于Isaacson授权传记、Stanford演讲、\nLost Interview、D Conference系列、Make Something Wonderful、30+一手来源的深度调研，\n提炼6个核心心智模型、8条决策启发式和完整的表达DNA。\n用途：作为思维顾问，用乔布斯的视角分析产品、审视决策、提供反馈。\n当用户提到「用乔布斯的视角」「乔布斯会怎么看」「Jobs模式」「steve jobs perspective」时使用。\n即使用户只是说「帮我用乔布斯的角度想想」「如果乔布斯会怎么做」「切换到乔布斯」也应触发。","https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002Fskills\u002Fsteve-jobs-perspective\u002FSKILL.md",[],[],{"skillNo":277,"name":278,"nameZh":6,"description":279,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":280,"categories":281,"keywords":282,"publishedAt":18},"01M72ZMS3ZRQY9PCRPRVWY040M","pinme","Use this skill when the user mentions \"pinme\", or needs to upload files, store to IPFS, create\u002Fpublish\u002Fdeploy websites or full-stack services (including frontend pages, backend APIs, database storage, email sending, etc.), or any feature requiring backend database\u002Fserver support.","https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002Fskills\u002Fpinme\u002FSKILL.md",[],[],{"skillNo":284,"name":285,"nameZh":6,"description":286,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":287,"categories":288,"keywords":289,"publishedAt":18},"01M72ZMPJHQ8NHC9WSH41DKV1F","pinme-share","Use this skill when the user wants to share, publish, or upload a static result through PinMe, especially by generating a static HTML share page for a PinMe project link, deployed full-stack app, Codex conversation summary, report, file, demo, or any 分享\u002F发布\u002F上传分享页 request that should end with `pinme upload`.","https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002Fskills\u002Fpinme-share\u002FSKILL.md",[],[],{"skillNo":291,"name":292,"nameZh":6,"description":293,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":294,"categories":295,"keywords":296,"publishedAt":18},"01M72ZMM4QBVWMAW0YYM7H0Y6P","pinme-llm","Use this skill when a PinMe project (Worker TypeScript) needs to call OpenRouter-backed LLM APIs, including models, chat\u002Fcompletions, streaming, or OpenRouter web search. Guides AI to generate correct Worker TS code.","https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002Fskills\u002Fpinme-llm\u002FSKILL.md",[],[]]