[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CQVV6T4J6AT27E5AFDC91X":3,"skill-same:01M6CQVV6T4J6AT27E5AFDC91X":56},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":25,"linkOnly":26,"markdownContent":27,"markdownBody":27,"frontMatter":28,"refName":29,"commitSha":30,"skillDirectory":31,"forksCount":13,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":34,"ownerDescription":6,"updatedAt":35,"install":36,"resources":49},"01M6CQVV6T4J6AT27E5AFDC91X","skill-acquisition",null,"dundas\u002Fagentbootup-public","dundas","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F627426?v=4","01M6CQVP2KHXEP7JH9WKKF59S7","David K. Dundas","01M6CQVP76D48NCMMXYDK9CBA8",0,"MIT","https:\u002F\u002Fgithub.com\u002Fdundas\u002Fagentbootup-public\u002Fblob\u002Fmain\u002Ftemplates\u002F.ai\u002Fskills\u002Fskill-acquisition\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24],"acquisition","skill acquisition","2026-11-10 10:12:30",false,"# Skill Acquisition\n\n**Purpose**: Systematically learn new capabilities, test them thoroughly, and save them as permanent skills.\n\n## When to Use\n\nTrigger this skill when:\n- Encountering a novel task or integration\n- Building a reusable workflow for the first time\n- Creating a new capability that should be permanently available\n- User says \"learn this\" or \"create a skill for this\"\n\n## Workflow\n\n### Phase 0: Check Existing Skills (MANDATORY)\n\n**CRITICAL**: Always check existing skills before building new ones!\n\n1. **List existing skills**:\n   ```bash\n   ls .ai\u002Fskills\u002F\n   ls .claude\u002Fskills\u002F  # If using Claude Code\n   ls .gemini\u002Fskills\u002F  # If using Gemini CLI\n   ```\n\n2. **Review skill documentation**:\n   - Read SKILL.md for each potentially relevant skill\n   - Check what capabilities already exist\n   - Look for similar patterns or workflows\n\n3. **Check memory**:\n   - Review `memory\u002FMEMORY.md` Skills Acquired section\n   - Verify skill isn't already documented\n\n4. **Consider skill composition**:\n   - Can existing skills be combined to solve this?\n   - Is extending an existing skill better than creating new?\n\n5. **Decision point**:\n   - ✅ **Proceed to Phase 1** if no existing skill covers this capability\n   - ❌ **Use existing skill** if functionality already exists\n   - ❌ **Compose skills** if combination solves the problem\n\n**Common mistake**: Building a skill that duplicates existing functionality. Always search first!\n\n### Phase 1: Discovery\n1. Identify the new capability needed\n2. **Confirm no existing skills cover it** (Phase 0 complete ✓)\n3. Research relevant documentation\u002FAPIs\n4. Document key requirements and constraints\n\n### Phase 2: Implementation\n1. Build working proof-of-concept\n2. Test with realistic scenarios\n3. Handle edge cases and errors\n4. Refine based on test results\n\n### Phase 3: Documentation\n1. Create skill directory: `.claude\u002Fskills\u002Fskill-name\u002F`\n2. Write SKILL.md with:\n   - Purpose and use cases\n   - Step-by-step workflow\n   - Examples\n   - Common pitfalls\n3. Create reference.md with:\n   - API documentation\n   - Configuration options\n   - Technical details\n4. Add examples\u002F directory if needed\n\n### Phase 4: Integration\n1. Test skill in real scenario\n2. Update `memory\u002FMEMORY.md` with new capability\n3. Add to skills list in MEMORY.md\n4. Announce skill availability\n5. Log to daily notes\n\n## Template Structure\n\n```\n.claude\u002Fskills\u002Fskill-name\u002F\n├── SKILL.md         # User-facing documentation\n├── reference.md     # Technical reference\n└── examples\u002F        # Example files (optional)\n    └── example-1.md\n```\n\n## SKILL.md Template\n\n```markdown\n# Skill Name\n\n**Purpose**: [One-line description]\n\n## When to Use\n\nTrigger this skill when:\n- [Trigger condition 1]\n- [Trigger condition 2]\n- User says \"[trigger phrase]\"\n\n## Workflow\n\n### Phase 1: [Phase Name]\n1. [Step 1]\n2. [Step 2]\n\n### Phase 2: [Phase Name]\n1. [Step 1]\n2. [Step 2]\n\n## Examples\n\n### Example 1: [Scenario]\n\\`\\`\\`\n[Example code or commands]\n\\`\\`\\`\n\n## Common Pitfalls\n\n- **Issue**: [Problem description]\n  - **Solution**: [How to fix]\n\n## Related Skills\n\n- [Related skill 1]\n- [Related skill 2]\n```\n\n## reference.md Template\n\n```markdown\n# Skill Name - Technical Reference\n\n## API Documentation\n\n### Function\u002FEndpoint 1\n- **Purpose**: [Description]\n- **Parameters**: [Parameter details]\n- **Returns**: [Return value]\n- **Example**: [Code example]\n\n## Configuration\n\n### Environment Variables\n- `VAR_NAME` - [Description]\n\n### Config File\n- `config.key` - [Description]\n\n## Implementation Details\n\n### Key Functions\n- `functionName()` - [What it does]\n\n### Error Handling\n- [Error type] - [How it's handled]\n\n## Testing\n\n### Test Cases\n1. [Test scenario 1]\n2. [Test scenario 2]\n\n### Validation\n\\`\\`\\`bash\n# Commands to validate skill works\n\\`\\`\\`\n```\n\n## Decision Framework\n\n### When to Create a New Skill\n\n**FIRST: Check existing skills** (see Phase 0 above)\n\n**Create a skill if ALL of these are true**:\n- ✅ Task is repeatable and reusable\n- ✅ Involves specific API\u002Ftool knowledge\n- ✅ Has clear workflow steps\n- ✅ Benefits from documentation\n- ✅ **No existing skill provides this capability** (MANDATORY CHECK)\n- ✅ **Cannot be achieved by composing existing skills** (MANDATORY CHECK)\n\n**Don't create a skill if ANY of these are true**:\n- ❌ One-time task with no reuse potential\n- ❌ Too simple (basic file operations)\n- ❌ **Already covered by existing skill** (ALWAYS CHECK FIRST!)\n- ❌ **Can be solved by combining existing skills**\n- ❌ Still experimental\u002Fnot validated\n- ❌ Duplicates existing functionality\n\n### Skill Naming Conventions\n\n- Use lowercase with hyphens: `skill-name`\n- Be specific: `github-pr-review` not just `github`\n- Action-oriented: `deploy-to-cloudflare` not `cloudflare-deployment`\n\n## Integration with Memory\n\nAfter creating a skill:\n\n1. **Update MEMORY.md**:\n```markdown\n## Skills Acquired\n\n**[Category]**: skill-name, ...\n\n### skill-name\n- **Purpose**: [One-line description]\n- **Created**: YYYY-MM-DD\n- **Usage**: [When to use]\n```\n\n2. **Update daily log**:\n```markdown\n## Skills Created\n\n### skill-name\n**Purpose**: [Description]\n\n**Decision**: Created because [reasoning]\n\n**Testing**: [Test results]\n\n**Status**: Production-ready ✅\n```\n\n## Quality Checklist\n\nBefore marking skill complete:\n\n- [ ] Implementation tested with realistic data\n- [ ] SKILL.md includes clear trigger conditions\n- [ ] reference.md documents all APIs\u002Fconfig\n- [ ] Examples demonstrate key use cases\n- [ ] Error handling covers edge cases\n- [ ] MEMORY.md updated with new capability\n- [ ] Daily log documents creation decision\n- [ ] Skill works without manual intervention\n\n## Examples\n\n### Example: Creating API Integration Skill\n\n```\n0. Check Existing Skills Phase:\n   - ls .ai\u002Fskills\u002F → Found: mech-storage, mech-llms, mech-reader\n   - Review: None cover this specific API\n   - Decision: No existing skill covers this, proceed to Phase 1 ✓\n\n1. Discovery Phase:\n   - Need: Integrate with new external API\n   - Research: Read API docs, test endpoints\n   - Requirements: Auth, rate limiting, error handling\n\n2. Implementation Phase:\n   - Build: HTTP client with auth headers\n   - Test: Real API calls, error scenarios\n   - Refine: Add retry logic, better errors\n\n3. Documentation Phase:\n   - Create: .claude\u002Fskills\u002Fapi-name-integration\u002F\n   - Write: SKILL.md with workflow steps\n   - Document: reference.md with endpoints\n\n4. Integration Phase:\n   - Test: Use in real scenario\n   - Update: MEMORY.md with new capability\n   - Log: Daily notes with decision rationale\n```\n\n## Common Pitfalls\n\n- **Issue**: Creating duplicate skills without checking existing ones\n  - **Solution**: ALWAYS run Phase 0 - check existing skills first!\n  - **Impact**: Wastes time, creates confusion, maintenance burden\n\n- **Issue**: Creating skills for one-off tasks\n  - **Solution**: Only create skills for reusable capabilities\n\n- **Issue**: Not checking if skills can be composed\n  - **Solution**: Consider combining existing skills before building new\n\n- **Issue**: Insufficient testing before saving\n  - **Solution**: Test with realistic data, edge cases\n\n- **Issue**: Poor documentation\n  - **Solution**: Include examples, common errors, clear triggers\n\n- **Issue**: Forgetting to update MEMORY.md\n  - **Solution**: Make memory update part of workflow\n\n## Related Skills\n\n- `memory-manager` - Manages persistent memory system\n- `autonomous-improver` - Uses skills for continuous improvement\n- `dev-workflow-orchestrator` - Orchestrates complex development tasks\n",{},"main","47b89745588c3057f0ccd0517a2eb8967df27054","templates\u002F.ai\u002Fskills\u002Fskill-acquisition","https:\u002F\u002Fgithub.com\u002Fdundas\u002Fagentbootup-public","https:\u002F\u002Fgithub.com\u002Fdundas","derivative.io","2026-09-02 20:12:15",{"source":7,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add dundas\u002Fagentbootup-public --skill skill-acquisition",{"tool":42,"command":43},"bunx","bunx skills add dundas\u002Fagentbootup-public --skill skill-acquisition",{"tool":45,"command":46},"pnpm","pnpm dlx skills add dundas\u002Fagentbootup-public --skill skill-acquisition","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdundas\u002Fagentbootup-public\u002Fblob\u002Fmain\u002Ftemplates\u002F.ai\u002Fskills\u002Fskill-acquisition\u002FSKILL.md",true,[50],{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"reference.md","REFERENCE","参考文档",7086,"https:\u002F\u002Fgithub.com\u002Fdundas\u002Fagentbootup-public\u002Fblob\u002Fmain\u002Ftemplates\u002F.ai\u002Fskills\u002Fskill-acquisition\u002Freference.md",[57,67,87,107,116,138],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":64,"publishedAt":25},"01M6CQZ7DFJB965BJJ5ZZ54CXY","fixture-skill","Secret-free recovery fixture skill.","https:\u002F\u002Fgithub.com\u002Fdundas\u002Fagentbootup-public\u002Fblob\u002Fmain\u002Ftests\u002Fruntime-adapters\u002Ffixtures\u002Fhermes\u002F0.18.2-darwin-arm64-real\u002Froot\u002Fskills\u002Ffixture-skill\u002FSKILL.md",[63],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[65,66],"fixture skill","recovery",{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":78,"publishedAt":25},"01M6CQZ4NN0KVH1Z4E1Y1GJ3X9","user-story-generator","Generate standalone user stories for features without creating a full PRD. Perfect for backlog grooming and story refinement.","https:\u002F\u002Fgithub.com\u002Fdundas\u002Fagentbootup-public\u002Fblob\u002Fmain\u002Ftemplates\u002F.claude\u002Fskills\u002Fuser-story-generator\u002FSKILL.md",[73],{"categoryNo":74,"categoryName":75,"taxonomyType":76,"taxonomyTypeDesc":77},"01JBSEEDCAT000000000000031","产品经理","PROFESSION","适用职业",[79,80,81,82,83,84,85,86],"user story generator","Story","user story","user","prd","documentation","generate","backlog",{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":99,"publishedAt":25},"01M6CQZ16VC27HMWM31CCKK6BC","user-journey-mapper","Map user flows and journeys through your application for UX design and workflow visualization, independent of testing.","https:\u002F\u002Fgithub.com\u002Fdundas\u002Fagentbootup-public\u002Fblob\u002Fmain\u002Ftemplates\u002F.claude\u002Fskills\u002Fuser-journey-mapper\u002FSKILL.md",[93,96],{"categoryNo":94,"categoryName":95,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":97,"categoryName":98,"taxonomyType":76,"taxonomyTypeDesc":77},"01JBSEEDCAT000000000000032","设计师",[100,101,82,84,102,103,104,105,106],"user journey mapper","journey","ux","visualization","workflow","design","testing",{"skillNo":108,"name":109,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":25},"01M6CQYXSQQJ4Z5CRAX2SSMHW1","transcript-query","https:\u002F\u002Fgithub.com\u002Fdundas\u002Fagentbootup-public\u002Fblob\u002Fmain\u002Ftemplates\u002F.claude\u002Fskills\u002Ftranscript-query\u002FSKILL.md",[],[113,114,115],"transcript","transcript query","query",{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":126,"publishedAt":25},"01M6CQYT7A1G4CPQTZKXR5TCK9","test-plan-generator","Generate comprehensive E2E test plans from PRDs, task lists, or descriptions with environment-aware prerequisites and issue tracking.","https:\u002F\u002Fgithub.com\u002Fdundas\u002Fagentbootup-public\u002Fblob\u002Fmain\u002Ftemplates\u002F.claude\u002Fskills\u002Ftest-plan-generator\u002FSKILL.md",[122,123],{"categoryNo":94,"categoryName":95,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":124,"categoryName":125,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000010","后端与接口",[127,128,129,130,131,132,133,134,135,136,85,137],"plan","test plan generator","test plan","test","task","issue","e2e test","environment","tracking","quality","e2e",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":145,"publishedAt":25},"01M6CQYQAWFSPTYE2VTJJVW72G","tasklist-generator","Generate high-level tasks and gated sub-tasks from a PRD, with agent assignments, commit\u002FPR strategy, and relevant files.","https:\u002F\u002Fgithub.com\u002Fdundas\u002Fagentbootup-public\u002Fblob\u002Fmain\u002Ftemplates\u002F.claude\u002Fskills\u002Ftasklist-generator\u002FSKILL.md",[144],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[146,147,148,149,83,85,150,151,152,104],"tasklist generator","gated","files","strategy","tasks","pr","commit"]