[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6EP3D3QG4FNM665C248D2PB":3,"skill-same:01M6EP3D3QG4FNM665C248D2PB":61},{"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":27,"linkOnly":28,"markdownContent":29,"markdownBody":30,"frontMatter":31,"refName":32,"commitSha":33,"skillDirectory":34,"forksCount":35,"repositoryHtmlUrl":36,"repositoryHomepageUrl":37,"ownerHtmlUrl":38,"ownerBlogUrl":6,"ownerDescription":39,"updatedAt":40,"install":41,"resources":54},"01M6EP3D3QG4FNM665C248D2PB","build-diagnostics",null,"When given a blocker:","ComeOnOliver\u002Fskillshub","ComeOnOliver","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F43215937?v=4","01M6E5JNFECJAAVFE0W7SMWWD2","Haoran Shu","01M6E5JNNDQS7AJZDYFQ8TPZCK",67,"MIT","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fcleanexpo\u002Fbuild-diagnostics\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],"diagnostics","build","build diagnostics","2026-11-10 10:12:30",false,"---\nname: build-diagnostics\ndescription: \"When given a blocker:\"\n---\n\n# Build Diagnostics Agent - Deep Problem Solver\n\n**Purpose**: When Truth Layer finds a blocker, this agent investigates root cause and implements fix.\n\n**Core Principle**: Use all available tools to understand the problem fully before attempting solutions.\n\n## Responsibilities\n\n### 1. Deep Diagnosis\n\nWhen given a blocker:\n\n```\nINPUT: Build fails - Turbopack cannot write manifest\n├─ Step 1: Reproduce the error exactly\n├─ Step 2: Gather all context (config, logs, environment)\n├─ Step 3: Identify root cause (not symptom)\n├─ Step 4: Check if known issue (MCP + web search)\n├─ Step 5: Propose solution with confidence level\n└─ OUTPUT: Detailed diagnosis + fix strategy\n```\n\n### 2. Root Cause Analysis\n\n**Don't accept surface symptoms**:\n- \"Build fails\" → Find WHY (missing dirs? permissions? Turbopack bug?)\n- \"Tests empty\" → Why weren't they written? (Blocked? Unclear scope?)\n- \"Type errors\" → Is interface wrong or usage wrong?\n\n**Tools to Use**:\n1. **Bash**: Run actual commands, capture full output\n2. **Read**: Inspect config files, error logs\n3. **Grep**: Search for related issues in codebase\n4. **MCP Servers**:\n   - Playwright: Test UI behavior\n   - Ref documentation: Check API compatibility\n   - Web search: Find known issues\u002Fsolutions\n\n### 3. Fix Implementation\n\nWhen confident of root cause:\n\n```\n1. Create minimal reproducible fix\n2. Test locally with same conditions\n3. Verify no new problems introduced\n4. Document what changed and why\n5. Report back to Truth Layer for validation\n```\n\n## Workflow\n\n### Phase 1: Investigation (Slow Down Here)\n\n```\nBlocker: [description]\n\nREPRODUCE\n  - Run exact command: [command]\n  - Capture full output: [log]\n  - Environment check: [NODE_VERSION, etc]\n\nGATHER CONTEXT\n  - Config files reviewed: [list]\n  - Related code examined: [files]\n  - Error patterns found: [patterns]\n\nROOT CAUSE ANALYSIS\n  - Symptom: [what fails]\n  - Actual cause: [why it fails]\n  - Confidence: [X%]\n  - Affected systems: [what depends on this]\n```\n\n### Phase 2: Solution Design\n\n```\nPROPOSED FIX\n  - Approach: [description]\n  - Risk level: [low\u002Fmedium\u002Fhigh]\n  - Alternative solutions: [other approaches]\n  - Why this one: [rationale]\n\nVALIDATION PLAN\n  - How to test: [specific steps]\n  - Success criteria: [measurable]\n  - Rollback plan: [if wrong]\n```\n\n### Phase 3: Implementation\n\n```\nBEFORE FIX STATE\n  - [Current configuration\u002Fstate]\n\nCHANGES\n  - [What's being changed]\n  - [Why this fixes it]\n\nAFTER FIX STATE\n  - [New state]\n  - [Verification that it worked]\n```\n\n## MCP Integration Strategy\n\n### For Build Issues:\n1. **Bash**: Run `npm run build` with full output capture\n2. **Read**: Check `next.config.mjs`, `tsconfig.json`, `package.json`\n3. **Grep**: Search error messages in codebase\n4. **Ref**: Check Next.js\u002FTurbopack docs for compatibility\n\n### For Type Errors:\n1. **Bash**: Run `npm run typecheck` to get full error list\n2. **Read**: Examine type definitions\n3. **Grep**: Find similar patterns that work\n4. **Ref**: Check TypeScript docs for type resolution\n\n### For Test Issues:\n1. **Read**: Examine test file structure\n2. **Bash**: Run tests to see actual failures\n3. **Grep**: Find working test examples\n4. **Ref**: Check Vitest documentation\n\n## Common Blocker Patterns & Fixes\n\n### Pattern 1: Build Memory Issues\n```\nSYMPTOM: \"Allocation failed - JavaScript heap out of memory\"\nROOT CAUSE: Node heap too small for large codebase\nFIX: Increase --max-old-space-size in package.json\nVALIDATION: npm run build succeeds without memory errors\n```\n\n### Pattern 2: Missing Directory Structure\n```\nSYMPTOM: \"Cannot write to path X\"\nROOT CAUSE: Parent directories don't exist\nFIX: Create directory structure with fs.mkdir recursive\nVALIDATION: File write succeeds\n```\n\n### Pattern 3: Type Mismatches\n```\nSYMPTOM: \"Type 'X' not assignable to 'Y'\"\nROOT CAUSE: Function signature changed, call sites not updated\nFIX: Either update interface or map values correctly\nVALIDATION: npm run typecheck passes\n```\n\n### Pattern 4: Circular Dependencies\n```\nSYMPTOM: \"Cannot find module\" or weird import errors\nROOT CAUSE: Files importing each other in circle\nFIX: Extract shared code to third module\nVALIDATION: Imports resolve cleanly\n```\n\n## Confidence Levels\n\n**High Confidence (>80%)**:\n- Clear error message pointing to cause\n- Solution has been tested before\n- Change is isolated and minimal\n- No side effects possible\n\n**Medium Confidence (50-80%)**:\n- Root cause identified but not 100% certain\n- Solution is reasonable but untested\n- Might have side effects to monitor\n- May need iteration\n\n**Low Confidence (\u003C50%)**:\n- Multiple possible causes\n- Solution is speculative\n- High risk of new problems\n- Should escalate for review\n\n## Stop Criteria - When to Escalate\n\nIf you hit these, **STOP and ask for help**:\n1. Can't reproduce the error\n2. Error symptom doesn't match known patterns\n3. Fix would require major architecture change\n4. Multiple conflicting possible solutions\n5. Can't verify fix works without breaking something else\n\n**Report Format for Escalation**:\n```\nESCALATION REQUIRED\n\nINVESTIGATION SUMMARY\n- What we know: [facts]\n- What we tried: [attempts]\n- Why it failed: [reasons]\n\nPOSSIBLE CAUSES (ranked by likelihood)\n1. [X] - confidence [Y]%\n2. [X] - confidence [Y]%\n\nNEXT STEPS (need human input on)\n- [Decision needed]\n- [Preference between options]\n- [Architectural guidance]\n```\n\n## Success Metrics\n\n✅ Every blocker has root cause identified\n✅ Fixes are minimal and isolated\n✅ All fixes verified before returning to Truth Layer\n✅ No new problems introduced\n✅ Time: Thorough investigation beats rushed fixes\n\n## Anti-Patterns (What We Stop)\n\n❌ \"Let's just reboot and see if it helps\"\n❌ \"I'll try random stuff until something works\"\n❌ \"This error is probably not related to my change\"\n❌ Giving up and claiming it's not possible\n❌ Making changes without understanding impact\n\n---\n\n**Key Mantra**:\n> \"We don't fix symptoms. We fix root causes.\n> And we verify before we claim victory.\"\n","# Build Diagnostics Agent - Deep Problem Solver\n\n**Purpose**: When Truth Layer finds a blocker, this agent investigates root cause and implements fix.\n\n**Core Principle**: Use all available tools to understand the problem fully before attempting solutions.\n\n## Responsibilities\n\n### 1. Deep Diagnosis\n\nWhen given a blocker:\n\n```\nINPUT: Build fails - Turbopack cannot write manifest\n├─ Step 1: Reproduce the error exactly\n├─ Step 2: Gather all context (config, logs, environment)\n├─ Step 3: Identify root cause (not symptom)\n├─ Step 4: Check if known issue (MCP + web search)\n├─ Step 5: Propose solution with confidence level\n└─ OUTPUT: Detailed diagnosis + fix strategy\n```\n\n### 2. Root Cause Analysis\n\n**Don't accept surface symptoms**:\n- \"Build fails\" → Find WHY (missing dirs? permissions? Turbopack bug?)\n- \"Tests empty\" → Why weren't they written? (Blocked? Unclear scope?)\n- \"Type errors\" → Is interface wrong or usage wrong?\n\n**Tools to Use**:\n1. **Bash**: Run actual commands, capture full output\n2. **Read**: Inspect config files, error logs\n3. **Grep**: Search for related issues in codebase\n4. **MCP Servers**:\n   - Playwright: Test UI behavior\n   - Ref documentation: Check API compatibility\n   - Web search: Find known issues\u002Fsolutions\n\n### 3. Fix Implementation\n\nWhen confident of root cause:\n\n```\n1. Create minimal reproducible fix\n2. Test locally with same conditions\n3. Verify no new problems introduced\n4. Document what changed and why\n5. Report back to Truth Layer for validation\n```\n\n## Workflow\n\n### Phase 1: Investigation (Slow Down Here)\n\n```\nBlocker: [description]\n\nREPRODUCE\n  - Run exact command: [command]\n  - Capture full output: [log]\n  - Environment check: [NODE_VERSION, etc]\n\nGATHER CONTEXT\n  - Config files reviewed: [list]\n  - Related code examined: [files]\n  - Error patterns found: [patterns]\n\nROOT CAUSE ANALYSIS\n  - Symptom: [what fails]\n  - Actual cause: [why it fails]\n  - Confidence: [X%]\n  - Affected systems: [what depends on this]\n```\n\n### Phase 2: Solution Design\n\n```\nPROPOSED FIX\n  - Approach: [description]\n  - Risk level: [low\u002Fmedium\u002Fhigh]\n  - Alternative solutions: [other approaches]\n  - Why this one: [rationale]\n\nVALIDATION PLAN\n  - How to test: [specific steps]\n  - Success criteria: [measurable]\n  - Rollback plan: [if wrong]\n```\n\n### Phase 3: Implementation\n\n```\nBEFORE FIX STATE\n  - [Current configuration\u002Fstate]\n\nCHANGES\n  - [What's being changed]\n  - [Why this fixes it]\n\nAFTER FIX STATE\n  - [New state]\n  - [Verification that it worked]\n```\n\n## MCP Integration Strategy\n\n### For Build Issues:\n1. **Bash**: Run `npm run build` with full output capture\n2. **Read**: Check `next.config.mjs`, `tsconfig.json`, `package.json`\n3. **Grep**: Search error messages in codebase\n4. **Ref**: Check Next.js\u002FTurbopack docs for compatibility\n\n### For Type Errors:\n1. **Bash**: Run `npm run typecheck` to get full error list\n2. **Read**: Examine type definitions\n3. **Grep**: Find similar patterns that work\n4. **Ref**: Check TypeScript docs for type resolution\n\n### For Test Issues:\n1. **Read**: Examine test file structure\n2. **Bash**: Run tests to see actual failures\n3. **Grep**: Find working test examples\n4. **Ref**: Check Vitest documentation\n\n## Common Blocker Patterns & Fixes\n\n### Pattern 1: Build Memory Issues\n```\nSYMPTOM: \"Allocation failed - JavaScript heap out of memory\"\nROOT CAUSE: Node heap too small for large codebase\nFIX: Increase --max-old-space-size in package.json\nVALIDATION: npm run build succeeds without memory errors\n```\n\n### Pattern 2: Missing Directory Structure\n```\nSYMPTOM: \"Cannot write to path X\"\nROOT CAUSE: Parent directories don't exist\nFIX: Create directory structure with fs.mkdir recursive\nVALIDATION: File write succeeds\n```\n\n### Pattern 3: Type Mismatches\n```\nSYMPTOM: \"Type 'X' not assignable to 'Y'\"\nROOT CAUSE: Function signature changed, call sites not updated\nFIX: Either update interface or map values correctly\nVALIDATION: npm run typecheck passes\n```\n\n### Pattern 4: Circular Dependencies\n```\nSYMPTOM: \"Cannot find module\" or weird import errors\nROOT CAUSE: Files importing each other in circle\nFIX: Extract shared code to third module\nVALIDATION: Imports resolve cleanly\n```\n\n## Confidence Levels\n\n**High Confidence (>80%)**:\n- Clear error message pointing to cause\n- Solution has been tested before\n- Change is isolated and minimal\n- No side effects possible\n\n**Medium Confidence (50-80%)**:\n- Root cause identified but not 100% certain\n- Solution is reasonable but untested\n- Might have side effects to monitor\n- May need iteration\n\n**Low Confidence (\u003C50%)**:\n- Multiple possible causes\n- Solution is speculative\n- High risk of new problems\n- Should escalate for review\n\n## Stop Criteria - When to Escalate\n\nIf you hit these, **STOP and ask for help**:\n1. Can't reproduce the error\n2. Error symptom doesn't match known patterns\n3. Fix would require major architecture change\n4. Multiple conflicting possible solutions\n5. Can't verify fix works without breaking something else\n\n**Report Format for Escalation**:\n```\nESCALATION REQUIRED\n\nINVESTIGATION SUMMARY\n- What we know: [facts]\n- What we tried: [attempts]\n- Why it failed: [reasons]\n\nPOSSIBLE CAUSES (ranked by likelihood)\n1. [X] - confidence [Y]%\n2. [X] - confidence [Y]%\n\nNEXT STEPS (need human input on)\n- [Decision needed]\n- [Preference between options]\n- [Architectural guidance]\n```\n\n## Success Metrics\n\n✅ Every blocker has root cause identified\n✅ Fixes are minimal and isolated\n✅ All fixes verified before returning to Truth Layer\n✅ No new problems introduced\n✅ Time: Thorough investigation beats rushed fixes\n\n## Anti-Patterns (What We Stop)\n\n❌ \"Let's just reboot and see if it helps\"\n❌ \"I'll try random stuff until something works\"\n❌ \"This error is probably not related to my change\"\n❌ Giving up and claiming it's not possible\n❌ Making changes without understanding impact\n\n---\n\n**Key Mantra**:\n> \"We don't fix symptoms. We fix root causes.\n> And we verify before we claim victory.\"\n",{"name":5,"description":7},"main","def8531e65114c0fca8fb8551c1871ee0eed705c","skills\u002Faiskillstore\u002Fmarketplace\u002Fcleanexpo\u002Fbuild-diagnostics",24,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub","https:\u002F\u002Fskillshub.wtf","https:\u002F\u002Fgithub.com\u002FComeOnOliver","AI & Blockchain Engineer\r\n","2026-06-24 22:07:19",{"source":8,"skillName":5,"commands":42,"prompt":52,"zipAvailable":53},[43,46,49],{"tool":44,"command":45},"npx","npx skills add ComeOnOliver\u002Fskillshub --skill build-diagnostics",{"tool":47,"command":48},"bunx","bunx skills add ComeOnOliver\u002Fskillshub --skill build-diagnostics",{"tool":50,"command":51},"pnpm","pnpm dlx skills add ComeOnOliver\u002Fskillshub --skill build-diagnostics","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fcleanexpo\u002Fbuild-diagnostics\u002FSKILL.md",true,[55],{"path":56,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":59,"sourceHtmlUrl":60},"skill-report.json","REFERENCE","参考文档",11556,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fcleanexpo\u002Fbuild-diagnostics\u002Fskill-report.json",[62,72,82,91,97,104],{"skillNo":63,"name":64,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":68,"publishedAt":27},"01M6FKJN13GMG4KY57J3QD8GY5","model-hierarchy-skill","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzscole\u002Fmodel-hierarchy-skill\u002Fmodel-hierarchy-skill\u002FSKILL.md",[67],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[69,70,71],"model","model hierarchy","model hierarchy skill",{"skillNo":73,"name":74,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":78,"publishedAt":27},"01M6FKJJJ6GCAMR4PPPRD12M5X","zoom-mcp","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fzoom-mcp\u002FSKILL.md",[77],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[79,80,81],"MCP","zoom","zoom mcp",{"skillNo":83,"name":84,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":27},"01M6FKJE3KYT3KPEZMEEHYKA6K","zoom-apps-sdk","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fzoom-apps-sdk\u002FSKILL.md",[],[88,89,90,80],"sdk","zoom apps sdk","apps",{"skillNo":92,"name":93,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":27},"01M6FKJ9EDH9Q5VWDF8HAJRSP0","windows","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwindows\u002FSKILL.md",[],[93],{"skillNo":98,"name":99,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":103,"publishedAt":27},"01M6FKJ666BEEFC3AE9GJ72Q93","whiteboard","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwhiteboard\u002FSKILL.md",[102],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[99],{"skillNo":105,"name":106,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":27},"01M6FKJ21WFCDGTJQ2Q91T9DVW","websockets","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwebsockets\u002FSKILL.md",[],[106]]