[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6KH6SH05MCGEMDFWH0B6BC2":3,"skill-same:01M6KH6SH05MCGEMDFWH0B6BC2":64},{"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":22,"publishedAt":37,"linkOnly":38,"markdownContent":39,"markdownBody":40,"frontMatter":41,"refName":42,"commitSha":43,"skillDirectory":44,"forksCount":45,"repositoryHtmlUrl":46,"repositoryHomepageUrl":47,"ownerHtmlUrl":48,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":49,"install":50,"resources":63},"01M6KH6SH05MCGEMDFWH0B6BC2","oma-brainstorm",null,"Design-first ideation that explores user intent, constraints, and approaches before any planning or implementation. Use for brainstorming, ideation, exploring concepts, and evaluating approaches.","wooloolies\u002Fedcurate","wooloolies","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F249394924?v=4","01M6KH5E2GYFK48H4CM2H72J5Y","01M6KH5E69S3MAQGE2WKEPZTMR",4,"AGPL-3.0","https:\u002F\u002Fgithub.com\u002Fwooloolies\u002Fedcurate\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Foma-brainstorm\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36],"oma brainstorm","brainstorm","design","brainstorming","planning","first","constraints","user","use","ideation","implementation","intent","concepts","for","2026-11-10 10:12:30",false,"---\nname: oma-brainstorm\ndescription: Design-first ideation that explores user intent, constraints, and approaches before any planning or implementation. Use for brainstorming, ideation, exploring concepts, and evaluating approaches.\n---\n\n# Brainstorm - Design-First Ideation\n\n## When to use\n- Exploring a new feature idea before planning\n- Understanding user intent and constraints before committing to an approach\n- Comparing multiple design approaches with trade-offs\n- When the user says \"I have an idea\" or \"let's design something\"\n- Before invoking `\u002Fplan` for complex or ambiguous requests\n\n## When NOT to use\n- Requirements are already clear and well-defined -> use pm-agent directly\n- Implementing actual code -> delegate to specialized agents\n- Performing code reviews -> use QA Agent\n- Debugging existing issues -> use debug-agent\n\n## Core Rules\n1. **No implementation or planning before design approval** - brainstorm produces a design document, not code or task plans\n2. **One question at a time** - ask clarifying questions sequentially, not in batches\n3. **Always propose 2-3 approaches** - include a recommended option with trade-off analysis\n4. **Section-by-section design** - present design incrementally with user confirmation at each step\n5. **YAGNI** - do not over-engineer; design only what is needed for the stated goal\n6. **Save design, then transition** - persist the approved design document before handing off to `\u002Fplan`\n\n## How to Execute\nFollow the brainstorm workflow step by step:\n1. **Phase 1 - Context**: Explore the existing codebase and understand the project landscape\n2. **Phase 2 - Questions**: Ask clarifying questions one at a time to understand intent and constraints\n3. **Phase 3 - Approaches**: Propose 2-3 approaches with a recommended option and trade-off matrix\n4. **Phase 4 - Design**: Present the detailed design section by section, getting user approval at each step\n5. **Phase 5 - Documentation**: Save the approved design to `docs\u002Fplans\u002F` and project memory\n6. **Phase 6 - Transition**: Hand off to `\u002Fplan` for task decomposition\n\n## Common Pitfalls\n- **Jumping to solutions**: Asking \"how\" before fully understanding \"what\" and \"why\"\n- **Too many questions at once**: Overwhelming the user with a wall of questions\n- **Single approach bias**: Presenting only one option without alternatives\n- **Over-engineering**: Designing for hypothetical future requirements instead of stated needs\n- **Skipping confirmation**: Moving forward without explicit user approval on design decisions\n\n## Execution Protocol (CLI Mode)\n\nVendor-specific execution protocols are injected automatically by `oma agent:spawn`.\nSource files live under `..\u002F_shared\u002Fruntime\u002Fexecution-protocols\u002F{vendor}.md`.\n\n## References\n- Context loading: `..\u002F_shared\u002Fcore\u002Fcontext-loading.md`\n- Reasoning templates: `..\u002F_shared\u002Fcore\u002Freasoning-templates.md`\n- Clarification protocol: `..\u002F_shared\u002Fcore\u002Fclarification-protocol.md`\n- Quality principles: `..\u002F_shared\u002Fcore\u002Fquality-principles.md`\n- Skill-to-agent mapping: `..\u002F_shared\u002Fcore\u002Fskill-routing.md`\n","# Brainstorm - Design-First Ideation\n\n## When to use\n- Exploring a new feature idea before planning\n- Understanding user intent and constraints before committing to an approach\n- Comparing multiple design approaches with trade-offs\n- When the user says \"I have an idea\" or \"let's design something\"\n- Before invoking `\u002Fplan` for complex or ambiguous requests\n\n## When NOT to use\n- Requirements are already clear and well-defined -> use pm-agent directly\n- Implementing actual code -> delegate to specialized agents\n- Performing code reviews -> use QA Agent\n- Debugging existing issues -> use debug-agent\n\n## Core Rules\n1. **No implementation or planning before design approval** - brainstorm produces a design document, not code or task plans\n2. **One question at a time** - ask clarifying questions sequentially, not in batches\n3. **Always propose 2-3 approaches** - include a recommended option with trade-off analysis\n4. **Section-by-section design** - present design incrementally with user confirmation at each step\n5. **YAGNI** - do not over-engineer; design only what is needed for the stated goal\n6. **Save design, then transition** - persist the approved design document before handing off to `\u002Fplan`\n\n## How to Execute\nFollow the brainstorm workflow step by step:\n1. **Phase 1 - Context**: Explore the existing codebase and understand the project landscape\n2. **Phase 2 - Questions**: Ask clarifying questions one at a time to understand intent and constraints\n3. **Phase 3 - Approaches**: Propose 2-3 approaches with a recommended option and trade-off matrix\n4. **Phase 4 - Design**: Present the detailed design section by section, getting user approval at each step\n5. **Phase 5 - Documentation**: Save the approved design to `docs\u002Fplans\u002F` and project memory\n6. **Phase 6 - Transition**: Hand off to `\u002Fplan` for task decomposition\n\n## Common Pitfalls\n- **Jumping to solutions**: Asking \"how\" before fully understanding \"what\" and \"why\"\n- **Too many questions at once**: Overwhelming the user with a wall of questions\n- **Single approach bias**: Presenting only one option without alternatives\n- **Over-engineering**: Designing for hypothetical future requirements instead of stated needs\n- **Skipping confirmation**: Moving forward without explicit user approval on design decisions\n\n## Execution Protocol (CLI Mode)\n\nVendor-specific execution protocols are injected automatically by `oma agent:spawn`.\nSource files live under `..\u002F_shared\u002Fruntime\u002Fexecution-protocols\u002F{vendor}.md`.\n\n## References\n- Context loading: `..\u002F_shared\u002Fcore\u002Fcontext-loading.md`\n- Reasoning templates: `..\u002F_shared\u002Fcore\u002Freasoning-templates.md`\n- Clarification protocol: `..\u002F_shared\u002Fcore\u002Fclarification-protocol.md`\n- Quality principles: `..\u002F_shared\u002Fcore\u002Fquality-principles.md`\n- Skill-to-agent mapping: `..\u002F_shared\u002Fcore\u002Fskill-routing.md`\n",{"name":5,"description":7},"main","239752f2aaad461ba7abb70cd87445cc268ca5ff",".agents\u002Fskills\u002Foma-brainstorm",1,"https:\u002F\u002Fgithub.com\u002Fwooloolies\u002Fedcurate","https:\u002F\u002Fedcurate-2026.vercel.app","https:\u002F\u002Fgithub.com\u002Fwooloolies","2026-05-19 18:27:03",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add wooloolies\u002Fedcurate --skill oma-brainstorm",{"tool":56,"command":57},"bunx","bunx skills add wooloolies\u002Fedcurate --skill oma-brainstorm",{"tool":59,"command":60},"pnpm","pnpm dlx skills add wooloolies\u002Fedcurate --skill oma-brainstorm","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fwooloolies\u002Fedcurate\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Foma-brainstorm\u002FSKILL.md",true,[],[65,83,96,115,131,142],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":37},"01M6KHBR2FHN1VRRFV7FH8ENKS","work","Coordinate multiple agents for a complex multi-domain project using PM planning, parallel agent spawning, and QA review","https:\u002F\u002Fgithub.com\u002Fwooloolies\u002Fedcurate\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwork\u002FSKILL.md",[],[67,72,36,73,74,75,76,77,78,79,80,81,27,82],"qa review","true","multi","project","pm","domain","coordinate","multi-domain","parallel","qa","review",{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":37},"01M6KHBP5914PZ3RXE6T1B3PX1","ultrawork","Ultrawork - high-quality 5-phase development workflow with 11 review steps out of 17","https:\u002F\u002Fgithub.com\u002Fwooloolies\u002Fedcurate\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fultrawork\u002FSKILL.md",[],[85,82,90,91,92,73,93,94,95],"workflow","development","quality","development workflow","high","with",{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":105,"publishedAt":37},"01M6KHBK93J4MPCQEW08K9DAFC","tools","Manage MCP tools with natural language commands — list, enable, disable tools and tool groups","https:\u002F\u002Fgithub.com\u002Fwooloolies\u002Fedcurate\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftools\u002FSKILL.md",[102],{"categoryNo":103,"categoryName":104,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[106,95,73,107,108,109,110,111,112,113,114],"Tools","commands","natural language","language","manage","list","MCP","tool","mcp tools",{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":37},"01M6KHBF33ZBM85JAMKFH17WER","stack-set","Auto-detect project tech stack and generate stack-specific references for domain skills","https:\u002F\u002Fgithub.com\u002Fwooloolies\u002Fedcurate\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fstack-set\u002FSKILL.md",[],[122,123,124,125,126,127,77,75,128,129,73,36,130],"SET","stack","stack set","generate","auto","references","tech","detect","auto-detect",{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":137,"publishedAt":37},"01M6KHBD7SDS6HCK1A79DNK4AZ","setup","oh-my-agent project setup verification and configuration","https:\u002F\u002Fgithub.com\u002Fwooloolies\u002Fedcurate\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fsetup\u002FSKILL.md",[],[133,75,138,139,140,73,141],"verification","project setup","configuration","my",{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":148,"publishedAt":37},"01M6KHBAFKX9WWN5N3WE06MX97","scm","SCM workflow for Git operations (branching\u002Fmerge\u002Fconflict\u002Fworktree) plus Conventional Commit execution.","https:\u002F\u002Fgithub.com\u002Fwooloolies\u002Fedcurate\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fscm\u002FSKILL.md",[],[144,149,150,151,152,153,154,155,156,157,158,73,36,90],"commit","merge","git","worktree","conventional commit","execution","operations","conflict","git operations","branching"]