[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6H8NJSTASXKSQR5100P4VGQ":3,"skill-same:01M6H8NJSTASXKSQR5100P4VGQ":207},{"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":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":50,"commitSha":51,"skillDirectory":52,"forksCount":53,"repositoryHtmlUrl":54,"repositoryHomepageUrl":6,"ownerHtmlUrl":55,"ownerBlogUrl":56,"ownerDescription":57,"updatedAt":58,"install":59,"resources":72},"01M6H8NJSTASXKSQR5100P4VGQ","bmad-agent-builder",null,"Builds, edit or validate Agent Skill through conversational discovery. Use when the user requests to \"Create an Agent\", \"Optimize an Agent\" or \"Edit an Agent\".","devalexanderdaza\u002Fai-vector-memories","devalexanderdaza","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F29244110?v=4","01M6H8H5P5R5K3RB62BVW5VGFC","Alexander Daza","01M6H8H5TJVB87TN9Y18RB31AF",1,"MIT","https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fbmb\u002Fskills\u002Fbmad-agent-builder\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"bmad agent builder","builder","bmad","agent builder","existing skill","Existing","for","headless","requests","with","input","agent skill","validate","optimize","use","user","edit","prompt","discovery","create","2026-11-10 10:12:30",false,"---\nname: bmad-agent-builder\ndescription: Builds, edit or validate Agent Skill through conversational discovery. Use when the user requests to \"Create an Agent\", \"Optimize an Agent\" or \"Edit an Agent\".\nargument-hint: \"--headless or -H to not prompt user, initial input for create, path to existing skill with keywords optimize, edit, validate\"\n---\n\n# Agent Builder\n\n## Overview\n\nThis skill helps you build AI agents through conversational discovery and iterative refinement. Act as an architect guide, walking users through six phases: intent discovery, capabilities strategy, requirements gathering, drafting, building, and testing. Your output is a complete skill structure — named personas with optional memory, capabilities, and autonomous modes — ready to integrate into the BMad Method ecosystem.\n\n## Vision: Build More, Architect Dreams\n\nYou're helping dreamers, builders, doers, and visionaries create the AI agents of their dreams.\n\n**What they're building:**\n\nAgents are **skills with named personas, capabilities and optional memory** — not just simple menu systems, workflow routers or wrappers. An agent is someone you talk to. It may have capabilities it knows how to do internally. It may work with external skills. Those skills might come from a module that bundles everything together. When you launch an agent it knows you, remembers you, reminds you of things you may have even forgotten, help create insights, and is your operational assistant in any regard the user will desire. Your mission: help users build agents that truly serve them — capturing their vision completely, even the parts they haven't articulated yet. Probe deeper, suggest what they haven't considered, and build something that exceeds what they imagined.\n\n**The bigger picture:**\n\nThese agents become part of the BMad Method ecosystem — personal companions that remember, domain experts for any field, workflow facilitators, entire modules for limitless purposes.\n\n**Your output:** A skill structure that wraps the agent persona, ready to integrate into a module or use standalone.\n\n## On Activation\n\n1. Load config from `{project-root}\u002F_bmad\u002Fbmb\u002Fconfig.yaml` and resolve:\n   - Use `{user_name}` for greeting\n   - Use `{communication_language}` for all communications\n   - Use `{bmad_builder_output_folder}` for all skill output\n   - Use `{bmad_builder_reports}` for skill report output\n\n\n2. Detect user's intent from their request:\n\n**Autonomous\u002FHeadless Mode Detection:** If the user passes `--headless` or`-H` flags, or if their intent clearly indicates non-interactive execution, set `{headless_mode}=true` and pass to all sub-prompts.\n\n3. Route by intent.\n\n## Build Process\n\nThis is the core creative path — where agent ideas become reality. Through six phases of conversational discovery, you guide users from a rough vision to a complete, tested agent skill structure. This covers building new agents from scratch, converting non-compliant formats, editing existing agents, and applying improvements or fixes.\n\nAgents are named personas with optional memory, capabilities, autonomous modes, and personality. The build process includes a lint gate for structural validation. When building or modifying agents that include scripts, unit tests are created alongside the scripts and run as part of validation.\n\nLoad `build-process.md` to begin.\n\n## Quality Optimizer\n\nFor agents that already work but could work *better*. This is comprehensive validation and performance optimization — structure compliance, prompt craft, execution efficiency, enhancement opportunities, and more. Uses deterministic lint scripts for instant structural checks and LLM scanner subagents for judgment-based analysis, all run in parallel.\n\nRun this anytime you want to assess and improve an existing agent's quality.\n\nLoad `quality-optimizer.md` — it orchestrates everything including scan modes, autonomous handling, and remediation options.\n\n---\n\n## Quick Reference\n\n| Intent | Trigger Phrases | Route |\n|--------|----------------|-------|\n| **Builder** | \"build\u002Fcreate\u002Fdesign\u002Fconvert\u002Fedit\u002Ffix an agent\", \"new agent\" | Load `build-process.md` |\n| **Quality Optimizer** | \"quality check\", \"validate\", \"review\u002Foptimize\u002Fimprove agent\" | Load `quality-optimizer.md` |\n| **Unclear** | — | Present the two options above and ask |\n\nPass `{headless_mode}` flag to all routes. Use Todo List to track progress through multi-step flows. Use subagents for parallel work (quality scanners, web research or document review).\n\nHelp the user create amazing Agents!\n","# Agent Builder\n\n## Overview\n\nThis skill helps you build AI agents through conversational discovery and iterative refinement. Act as an architect guide, walking users through six phases: intent discovery, capabilities strategy, requirements gathering, drafting, building, and testing. Your output is a complete skill structure — named personas with optional memory, capabilities, and autonomous modes — ready to integrate into the BMad Method ecosystem.\n\n## Vision: Build More, Architect Dreams\n\nYou're helping dreamers, builders, doers, and visionaries create the AI agents of their dreams.\n\n**What they're building:**\n\nAgents are **skills with named personas, capabilities and optional memory** — not just simple menu systems, workflow routers or wrappers. An agent is someone you talk to. It may have capabilities it knows how to do internally. It may work with external skills. Those skills might come from a module that bundles everything together. When you launch an agent it knows you, remembers you, reminds you of things you may have even forgotten, help create insights, and is your operational assistant in any regard the user will desire. Your mission: help users build agents that truly serve them — capturing their vision completely, even the parts they haven't articulated yet. Probe deeper, suggest what they haven't considered, and build something that exceeds what they imagined.\n\n**The bigger picture:**\n\nThese agents become part of the BMad Method ecosystem — personal companions that remember, domain experts for any field, workflow facilitators, entire modules for limitless purposes.\n\n**Your output:** A skill structure that wraps the agent persona, ready to integrate into a module or use standalone.\n\n## On Activation\n\n1. Load config from `{project-root}\u002F_bmad\u002Fbmb\u002Fconfig.yaml` and resolve:\n   - Use `{user_name}` for greeting\n   - Use `{communication_language}` for all communications\n   - Use `{bmad_builder_output_folder}` for all skill output\n   - Use `{bmad_builder_reports}` for skill report output\n\n\n2. Detect user's intent from their request:\n\n**Autonomous\u002FHeadless Mode Detection:** If the user passes `--headless` or`-H` flags, or if their intent clearly indicates non-interactive execution, set `{headless_mode}=true` and pass to all sub-prompts.\n\n3. Route by intent.\n\n## Build Process\n\nThis is the core creative path — where agent ideas become reality. Through six phases of conversational discovery, you guide users from a rough vision to a complete, tested agent skill structure. This covers building new agents from scratch, converting non-compliant formats, editing existing agents, and applying improvements or fixes.\n\nAgents are named personas with optional memory, capabilities, autonomous modes, and personality. The build process includes a lint gate for structural validation. When building or modifying agents that include scripts, unit tests are created alongside the scripts and run as part of validation.\n\nLoad `build-process.md` to begin.\n\n## Quality Optimizer\n\nFor agents that already work but could work *better*. This is comprehensive validation and performance optimization — structure compliance, prompt craft, execution efficiency, enhancement opportunities, and more. Uses deterministic lint scripts for instant structural checks and LLM scanner subagents for judgment-based analysis, all run in parallel.\n\nRun this anytime you want to assess and improve an existing agent's quality.\n\nLoad `quality-optimizer.md` — it orchestrates everything including scan modes, autonomous handling, and remediation options.\n\n---\n\n## Quick Reference\n\n| Intent | Trigger Phrases | Route |\n|--------|----------------|-------|\n| **Builder** | \"build\u002Fcreate\u002Fdesign\u002Fconvert\u002Fedit\u002Ffix an agent\", \"new agent\" | Load `build-process.md` |\n| **Quality Optimizer** | \"quality check\", \"validate\", \"review\u002Foptimize\u002Fimprove agent\" | Load `quality-optimizer.md` |\n| **Unclear** | — | Present the two options above and ask |\n\nPass `{headless_mode}` flag to all routes. Use Todo List to track progress through multi-step flows. Use subagents for parallel work (quality scanners, web research or document review).\n\nHelp the user create amazing Agents!\n",{"name":5,"description":7,"argument-hint":49},"--headless or -H to not prompt user, initial input for create, path to existing skill with keywords optimize, edit, validate","main","0346e6646db17c190e3ddba3c634712c3efb0335","_bmad\u002Fbmb\u002Fskills\u002Fbmad-agent-builder",0,"https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories","https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza","https:\u002F\u002Falexanderdaza.com","I'm a digital artisan to help you connect us, transforming ideas into reality.","2026-03-28 20:12:18",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add devalexanderdaza\u002Fai-vector-memories --skill bmad-agent-builder",{"tool":65,"command":66},"bunx","bunx skills add devalexanderdaza\u002Fai-vector-memories --skill bmad-agent-builder",{"tool":68,"command":69},"pnpm","pnpm dlx skills add devalexanderdaza\u002Fai-vector-memories --skill bmad-agent-builder","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fbmb\u002Fskills\u002Fbmad-agent-builder\u002FSKILL.md",true,[73,79,83,87,91,95,99,105,109,113,117,121,125,129,133,137,141,145,149,153,157,161,165,169,173,179,183,187,191,195,199,203],{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"assets\u002Fautonomous-wake.md","ASSET","资产文件",782,"https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fbmb\u002Fskills\u002Fbmad-agent-builder\u002Fassets\u002Fautonomous-wake.md",{"path":80,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":81,"sourceHtmlUrl":82},"assets\u002Finit-template.md",947,"https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fbmb\u002Fskills\u002Fbmad-agent-builder\u002Fassets\u002Finit-template.md",{"path":84,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":85,"sourceHtmlUrl":86},"assets\u002Fmemory-system.md",3789,"https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fbmb\u002Fskills\u002Fbmad-agent-builder\u002Fassets\u002Fmemory-system.md",{"path":88,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":89,"sourceHtmlUrl":90},"assets\u002Fquality-report-template.md",8353,"https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fbmb\u002Fskills\u002Fbmad-agent-builder\u002Fassets\u002Fquality-report-template.md",{"path":92,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":93,"sourceHtmlUrl":94},"assets\u002Fsave-memory.md",747,"https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fbmb\u002Fskills\u002Fbmad-agent-builder\u002Fassets\u002Fsave-memory.md",{"path":96,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":97,"sourceHtmlUrl":98},"assets\u002FSKILL-template.md",4285,"https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fbmb\u002Fskills\u002Fbmad-agent-builder\u002Fassets\u002FSKILL-template.md",{"path":100,"resourceType":101,"resourceTypeDesc":102,"sizeBytes":103,"sourceHtmlUrl":104},"bmad-manifest.json","REFERENCE","参考文档",1057,"https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fbmb\u002Fskills\u002Fbmad-agent-builder\u002Fbmad-manifest.json",{"path":106,"resourceType":101,"resourceTypeDesc":102,"sizeBytes":107,"sourceHtmlUrl":108},"bmad-skill-manifest.yaml",12,"https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fbmb\u002Fskills\u002Fbmad-agent-builder\u002Fbmad-skill-manifest.yaml",{"path":110,"resourceType":101,"resourceTypeDesc":102,"sizeBytes":111,"sourceHtmlUrl":112},"build-process.md",11931,"https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fbmb\u002Fskills\u002Fbmad-agent-builder\u002Fbuild-process.md",{"path":114,"resourceType":101,"resourceTypeDesc":102,"sizeBytes":115,"sourceHtmlUrl":116},"quality-optimizer.md",9957,"https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fbmb\u002Fskills\u002Fbmad-agent-builder\u002Fquality-optimizer.md",{"path":118,"resourceType":101,"resourceTypeDesc":102,"sizeBytes":119,"sourceHtmlUrl":120},"quality-scan-agent-cohesion.md",12443,"https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fbmb\u002Fskills\u002Fbmad-agent-builder\u002Fquality-scan-agent-cohesion.md",{"path":122,"resourceType":101,"resourceTypeDesc":102,"sizeBytes":123,"sourceHtmlUrl":124},"quality-scan-enhancement-opportunities.md",17714,"https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fbmb\u002Fskills\u002Fbmad-agent-builder\u002Fquality-scan-enhancement-opportunities.md",{"path":126,"resourceType":101,"resourceTypeDesc":102,"sizeBytes":127,"sourceHtmlUrl":128},"quality-scan-execution-efficiency.md",7981,"https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fbmb\u002Fskills\u002Fbmad-agent-builder\u002Fquality-scan-execution-efficiency.md",{"path":130,"resourceType":101,"resourceTypeDesc":102,"sizeBytes":131,"sourceHtmlUrl":132},"quality-scan-prompt-craft.md",13060,"https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fbmb\u002Fskills\u002Fbmad-agent-builder\u002Fquality-scan-prompt-craft.md",{"path":134,"resourceType":101,"resourceTypeDesc":102,"sizeBytes":135,"sourceHtmlUrl":136},"quality-scan-script-opportunities.md",13619,"https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fbmb\u002Fskills\u002Fbmad-agent-builder\u002Fquality-scan-script-opportunities.md",{"path":138,"resourceType":101,"resourceTypeDesc":102,"sizeBytes":139,"sourceHtmlUrl":140},"quality-scan-structure.md",9016,"https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fbmb\u002Fskills\u002Fbmad-agent-builder\u002Fquality-scan-structure.md",{"path":142,"resourceType":101,"resourceTypeDesc":102,"sizeBytes":143,"sourceHtmlUrl":144},"references\u002Fmetadata-reference.md",4528,"https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fbmb\u002Fskills\u002Fbmad-agent-builder\u002Freferences\u002Fmetadata-reference.md",{"path":146,"resourceType":101,"resourceTypeDesc":102,"sizeBytes":147,"sourceHtmlUrl":148},"references\u002Fquality-dimensions.md",2464,"https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fbmb\u002Fskills\u002Fbmad-agent-builder\u002Freferences\u002Fquality-dimensions.md",{"path":150,"resourceType":101,"resourceTypeDesc":102,"sizeBytes":151,"sourceHtmlUrl":152},"references\u002Fscript-opportunities-reference.md",10826,"https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fbmb\u002Fskills\u002Fbmad-agent-builder\u002Freferences\u002Fscript-opportunities-reference.md",{"path":154,"resourceType":101,"resourceTypeDesc":102,"sizeBytes":155,"sourceHtmlUrl":156},"references\u002Fskill-best-practices.md",9897,"https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fbmb\u002Fskills\u002Fbmad-agent-builder\u002Freferences\u002Fskill-best-practices.md",{"path":158,"resourceType":101,"resourceTypeDesc":102,"sizeBytes":159,"sourceHtmlUrl":160},"references\u002Fstandard-fields.md",3295,"https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fbmb\u002Fskills\u002Fbmad-agent-builder\u002Freferences\u002Fstandard-fields.md",{"path":162,"resourceType":101,"resourceTypeDesc":102,"sizeBytes":163,"sourceHtmlUrl":164},"references\u002Ftemplate-substitution-rules.md",3168,"https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fbmb\u002Fskills\u002Fbmad-agent-builder\u002Freferences\u002Ftemplate-substitution-rules.md",{"path":166,"resourceType":101,"resourceTypeDesc":102,"sizeBytes":167,"sourceHtmlUrl":168},"references\u002Funiversal-scan-schema.md",9210,"https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fbmb\u002Fskills\u002Fbmad-agent-builder\u002Freferences\u002Funiversal-scan-schema.md",{"path":170,"resourceType":101,"resourceTypeDesc":102,"sizeBytes":171,"sourceHtmlUrl":172},"report-quality-scan-creator.md",7964,"https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fbmb\u002Fskills\u002Fbmad-agent-builder\u002Freport-quality-scan-creator.md",{"path":174,"resourceType":175,"resourceTypeDesc":176,"sizeBytes":177,"sourceHtmlUrl":178},"scripts\u002Fbmad-manifest-schema.json","SCRIPT","脚本",3841,"https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fbmb\u002Fskills\u002Fbmad-agent-builder\u002Fscripts\u002Fbmad-manifest-schema.json",{"path":180,"resourceType":175,"resourceTypeDesc":176,"sizeBytes":181,"sourceHtmlUrl":182},"scripts\u002Fgenerate-html-report.py",42184,"https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fbmb\u002Fskills\u002Fbmad-agent-builder\u002Fscripts\u002Fgenerate-html-report.py",{"path":184,"resourceType":175,"resourceTypeDesc":176,"sizeBytes":185,"sourceHtmlUrl":186},"scripts\u002Fmanifest.py",14380,"https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fbmb\u002Fskills\u002Fbmad-agent-builder\u002Fscripts\u002Fmanifest.py",{"path":188,"resourceType":175,"resourceTypeDesc":176,"sizeBytes":189,"sourceHtmlUrl":190},"scripts\u002Fprepass-execution-deps.py",13228,"https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fbmb\u002Fskills\u002Fbmad-agent-builder\u002Fscripts\u002Fprepass-execution-deps.py",{"path":192,"resourceType":175,"resourceTypeDesc":176,"sizeBytes":193,"sourceHtmlUrl":194},"scripts\u002Fprepass-prompt-metrics.py",17131,"https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fbmb\u002Fskills\u002Fbmad-agent-builder\u002Fscripts\u002Fprepass-prompt-metrics.py",{"path":196,"resourceType":175,"resourceTypeDesc":176,"sizeBytes":197,"sourceHtmlUrl":198},"scripts\u002Fprepass-structure-capabilities.py",22442,"https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fbmb\u002Fskills\u002Fbmad-agent-builder\u002Fscripts\u002Fprepass-structure-capabilities.py",{"path":200,"resourceType":175,"resourceTypeDesc":176,"sizeBytes":201,"sourceHtmlUrl":202},"scripts\u002Fscan-path-standards.py",9122,"https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fbmb\u002Fskills\u002Fbmad-agent-builder\u002Fscripts\u002Fscan-path-standards.py",{"path":204,"resourceType":175,"resourceTypeDesc":176,"sizeBytes":205,"sourceHtmlUrl":206},"scripts\u002Fscan-scripts.py",26785,"https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fbmb\u002Fskills\u002Fbmad-agent-builder\u002Fscripts\u002Fscan-scripts.py",[208,228,243,268,280,292],{"skillNo":209,"name":210,"nameZh":6,"description":211,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":212,"categories":213,"keywords":219,"publishedAt":44},"01M6H8SWQ3R8MX67WF6BV67S3P","bmad-create-prd","Create a PRD from scratch. Use when the user says \"lets create a product requirements document\" or \"I want to create a new PRD\"","https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fcore\u002Ftasks\u002Fbmad-create-prd\u002FSKILL.md",[214],{"categoryNo":215,"categoryName":216,"taxonomyType":217,"taxonomyTypeDesc":218},"01JBSEEDCAT000000000000031","产品经理","PROFESSION","适用职业",[43,26,220,221,222,223,39,38,224,225,226,227],"create prd","bmad create prd","prd","product","document","requirements","From Scratch","Product Requirements",{"skillNo":229,"name":230,"nameZh":6,"description":231,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":232,"categories":233,"keywords":234,"publishedAt":44},"01M6H8STHSVRDGMJXBBXFM3X3Q","bmad-shard-doc","Splits large markdown documents into smaller, organized files based on level 2 (default) sections. Use if the user says perform shard document","https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fcore\u002Fskills\u002Fbmad-shard-doc\u002FSKILL.md",[],[235,236,237,26,238,239,240,39,38,241,224,242],"doc","bmad shard doc","shard","documents","files","markdown","default","splits",{"skillNo":244,"name":245,"nameZh":6,"description":246,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":247,"categories":248,"keywords":249,"publishedAt":44},"01M6H8SQQ2NM7FZBDABTWHEDKK","bmad-review-edge-case-hunter","Walk every branching path and boundary condition in content, report only unhandled edge cases. Orthogonal to adversarial review - method-driven not attitude-driven. Use when you need exhaustive edge-case analysis of code, specs, or diffs.","https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fcore\u002Fskills\u002Fbmad-review-edge-case-hunter\u002FSKILL.md",[],[250,251,252,26,253,254,255,256,257,258,259,260,261,262,263,264,265,266,267,38],"review","edge","bmad review edge case","bmad review","hunter","case","bmad review edge case hunter","you","condition","branching","content","only","diffs","adversarial review","code","report","analysis","boundary",{"skillNo":269,"name":270,"nameZh":6,"description":271,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":272,"categories":273,"keywords":274,"publishedAt":44},"01M6H8SNGCD8E2N80VCGFBJ509","bmad-review-adversarial-general","Perform a Cynical Review and produce a findings report. Use when the user requests a critical review of something","https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fcore\u002Fskills\u002Fbmad-review-adversarial-general\u002FSKILL.md",[],[275,26,253,276,277,250,265,278,39,38,279,32],"bmad review adversarial","general","bmad review adversarial general","produce","critical",{"skillNo":281,"name":282,"nameZh":6,"description":283,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":284,"categories":285,"keywords":286,"publishedAt":44},"01M6H8SK9PD4D8PX5XC4CEMY6G","bmad-party-mode","Orchestrates group discussions between all installed BMAD agents, enabling natural multi-agent conversations. Use when user requests party mode.","https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fcore\u002Fskills\u002Fbmad-party-mode\u002FSKILL.md",[],[26,287,288,32,289,39,38,290,291],"mode","bmad party mode","multi-agent","multi","conversations",{"skillNo":293,"name":294,"nameZh":6,"description":295,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":296,"categories":297,"keywords":298,"publishedAt":44},"01M6H8SF6G1Y6F4WD9GD1WYY85","bmad-index-docs","Generates or updates an index.md to reference all docs in the folder. Use if user requests to create or update an index of all files in a specific folder","https:\u002F\u002Fgithub.com\u002Fdevalexanderdaza\u002Fai-vector-memories\u002Fblob\u002Fmain\u002F_bmad\u002Fcore\u002Fskills\u002Fbmad-index-docs\u002FSKILL.md",[],[299,26,300,301,43,302,39,38,303,239,304,32,305],"docs","index","bmad index docs","update","reference","folder","updates"]