[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6ESFC10PS3BE22YB2SCDBYR":3,"skill-same:01M6ESFC10PS3BE22YB2SCDBYR":84},{"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":28,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":54,"ownerHtmlUrl":55,"ownerBlogUrl":6,"ownerDescription":56,"updatedAt":57,"install":58,"resources":71},"01M6ESFC10PS3BE22YB2SCDBYR","subagent-development",null,"Execute plans using fresh subagent per task with code review between tasks. Use for high-quality iterative implementation.","ComeOnOliver\u002Fskillshub","ComeOnOliver","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F43215937?v=4","01M6E5JNFECJAAVFE0W7SMWWD2","Haoran Shu","01M6E5JNNDQS7AJZDYFQ8TPZCK",66,"MIT","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fdmjgilbert\u002Fsubagent-development\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"development","subagent","subagent development","code review","review","tasks","code","quality","execute","use","implementation","task","plans","fresh","with","2026-11-10 10:12:30",false,"---\nname: subagent-development\ndescription: Execute plans using fresh subagent per task with code review between tasks. Use for high-quality iterative implementation.\n---\n\n# Subagent-Driven Development\n\nFresh subagent per task + review between tasks = high quality, fast iteration.\n\n## When to Use\n\n- Executing implementation plans in current session\n- Tasks are largely independent\n- Want continuous progress with quality gates\n- Need isolation between task contexts\n\n## When NOT to Use\n\n- Plan needs initial review\u002Frevision\n- Tasks have tight sequential dependencies\n- Simple changes that don't need isolation\n\n## The Process\n\n### 1. Load Plan & Create Tasks\n\n```\n1. Read the plan document\n2. Create TodoWrite with all tasks\n3. Verify plan is sound before starting\n```\n\n### 2. For Each Task\n\n**Dispatch Implementation Subagent:**\n\n```\nTask([appropriate-agent], prompt=\"\nImplement Task N from the plan:\n\n**Task:** [Task description]\n\n**Requirements:**\n- Follow TDD (write failing test first)\n- Implement minimal code to pass\n- Verify all tests pass\n- Commit with descriptive message\n\n**Output:**\n- What was implemented\n- Test results\n- Any issues encountered\n\")\n```\n\n### 3. Code Review Checkpoint\n\nAfter EACH task, dispatch reviewer:\n\n```\nTask(code-reviewer, prompt=\"\nReview implementation of Task N:\n\n**What was implemented:** [From subagent output]\n**Commits:** [Range]\n**Requirements:** [From plan]\n\nEvaluate:\n- Implementation vs requirements match\n- Code quality and patterns\n- Test coverage\n- Critical\u002FImportant\u002FMinor issues\n\")\n```\n\n### 4. Address Feedback\n\n| Severity | Action                      |\n| -------- | --------------------------- |\n| Critical | Fix immediately, re-review  |\n| High     | Fix before next task        |\n| Medium   | Fix if quick, else document |\n| Low      | Document for later          |\n\n### 5. Mark & Continue\n\n1. Update TodoWrite to mark task complete\n2. Proceed to next task\n3. Repeat cycle\n\n### 6. Final Review\n\nAfter all tasks complete:\n\n```\nTask(code-reviewer, prompt=\"\nFinal review of complete implementation:\n\n**Plan:** [Reference]\n**All commits:** [Full range]\n\nVerify:\n- Complete plan compliance\n- Architectural soundness\n- No regressions\n- Ready for merge\n\")\n```\n\n### 7. Finish\n\nTransition to merge\u002FPR workflow.\n\n## Critical Rules\n\n### Never:\n\n- Skip code reviews between tasks\n- Proceed with unresolved Critical issues\n- Run multiple implementation subagents in parallel\n- Implement without plan task reference\n\n### Always:\n\n- Fresh subagent for each task (clean context)\n- Review after each task (quality gate)\n- Fix Critical\u002FHigh before continuing\n- Document deferred issues\n\n## Quality Gate Template\n\n```markdown\n## Task N Review\n\n**Status:** [Pass\u002FFail]\n\n### Critical Issues\n\n[None \u002F List]\n\n### High Priority\n\n[None \u002F List]\n\n### Medium Priority\n\n[None \u002F List]\n\n### Minor\u002FSuggestions\n\n[None \u002F List]\n\n### Verdict\n\n- [ ] Proceed to next task\n- [ ] Fix issues first\n- [ ] Needs discussion\n```\n\n## Benefits\n\n- Clean context for each task (no accumulated confusion)\n- Built-in quality gates catch issues early\n- Reviewable progress at each step\n- Easy to pause\u002Fresume at task boundaries\n","# Subagent-Driven Development\n\nFresh subagent per task + review between tasks = high quality, fast iteration.\n\n## When to Use\n\n- Executing implementation plans in current session\n- Tasks are largely independent\n- Want continuous progress with quality gates\n- Need isolation between task contexts\n\n## When NOT to Use\n\n- Plan needs initial review\u002Frevision\n- Tasks have tight sequential dependencies\n- Simple changes that don't need isolation\n\n## The Process\n\n### 1. Load Plan & Create Tasks\n\n```\n1. Read the plan document\n2. Create TodoWrite with all tasks\n3. Verify plan is sound before starting\n```\n\n### 2. For Each Task\n\n**Dispatch Implementation Subagent:**\n\n```\nTask([appropriate-agent], prompt=\"\nImplement Task N from the plan:\n\n**Task:** [Task description]\n\n**Requirements:**\n- Follow TDD (write failing test first)\n- Implement minimal code to pass\n- Verify all tests pass\n- Commit with descriptive message\n\n**Output:**\n- What was implemented\n- Test results\n- Any issues encountered\n\")\n```\n\n### 3. Code Review Checkpoint\n\nAfter EACH task, dispatch reviewer:\n\n```\nTask(code-reviewer, prompt=\"\nReview implementation of Task N:\n\n**What was implemented:** [From subagent output]\n**Commits:** [Range]\n**Requirements:** [From plan]\n\nEvaluate:\n- Implementation vs requirements match\n- Code quality and patterns\n- Test coverage\n- Critical\u002FImportant\u002FMinor issues\n\")\n```\n\n### 4. Address Feedback\n\n| Severity | Action                      |\n| -------- | --------------------------- |\n| Critical | Fix immediately, re-review  |\n| High     | Fix before next task        |\n| Medium   | Fix if quick, else document |\n| Low      | Document for later          |\n\n### 5. Mark & Continue\n\n1. Update TodoWrite to mark task complete\n2. Proceed to next task\n3. Repeat cycle\n\n### 6. Final Review\n\nAfter all tasks complete:\n\n```\nTask(code-reviewer, prompt=\"\nFinal review of complete implementation:\n\n**Plan:** [Reference]\n**All commits:** [Full range]\n\nVerify:\n- Complete plan compliance\n- Architectural soundness\n- No regressions\n- Ready for merge\n\")\n```\n\n### 7. Finish\n\nTransition to merge\u002FPR workflow.\n\n## Critical Rules\n\n### Never:\n\n- Skip code reviews between tasks\n- Proceed with unresolved Critical issues\n- Run multiple implementation subagents in parallel\n- Implement without plan task reference\n\n### Always:\n\n- Fresh subagent for each task (clean context)\n- Review after each task (quality gate)\n- Fix Critical\u002FHigh before continuing\n- Document deferred issues\n\n## Quality Gate Template\n\n```markdown\n## Task N Review\n\n**Status:** [Pass\u002FFail]\n\n### Critical Issues\n\n[None \u002F List]\n\n### High Priority\n\n[None \u002F List]\n\n### Medium Priority\n\n[None \u002F List]\n\n### Minor\u002FSuggestions\n\n[None \u002F List]\n\n### Verdict\n\n- [ ] Proceed to next task\n- [ ] Fix issues first\n- [ ] Needs discussion\n```\n\n## Benefits\n\n- Clean context for each task (no accumulated confusion)\n- Built-in quality gates catch issues early\n- Reviewable progress at each step\n- Easy to pause\u002Fresume at task boundaries\n",{"name":5,"description":7},"main","def8531e65114c0fca8fb8551c1871ee0eed705c","skills\u002Faiskillstore\u002Fmarketplace\u002Fdmjgilbert\u002Fsubagent-development",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":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add ComeOnOliver\u002Fskillshub --skill subagent-development",{"tool":64,"command":65},"bunx","bunx skills add ComeOnOliver\u002Fskillshub --skill subagent-development",{"tool":67,"command":68},"pnpm","pnpm dlx skills add ComeOnOliver\u002Fskillshub --skill subagent-development","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fdmjgilbert\u002Fsubagent-development\u002FSKILL.md",true,[72,78],{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"customize.toml","OTHER","其他",1621,"https:\u002F\u002Fgithub.com\u002Fdeveloperworks\u002Frust-supervisor\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fgds-retrospective\u002Fcustomize.toml",{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"skill-report.json","REFERENCE","参考文档",9295,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fdmjgilbert\u002Fsubagent-development\u002Fskill-report.json",[85,97,107,116,122,129],{"skillNo":86,"name":87,"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":88,"categories":89,"keywords":93,"publishedAt":44},"01M6FKJN13GMG4KY57J3QD8GY5","model-hierarchy-skill","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzscole\u002Fmodel-hierarchy-skill\u002Fmodel-hierarchy-skill\u002FSKILL.md",[90],{"categoryNo":91,"categoryName":92,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[94,95,96],"model","model hierarchy","model hierarchy skill",{"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":44},"01M6FKJJJ6GCAMR4PPPRD12M5X","zoom-mcp","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fzoom-mcp\u002FSKILL.md",[102],{"categoryNo":91,"categoryName":92,"taxonomyType":21,"taxonomyTypeDesc":22},[104,105,106],"MCP","zoom","zoom mcp",{"skillNo":108,"name":109,"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":110,"categories":111,"keywords":112,"publishedAt":44},"01M6FKJE3KYT3KPEZMEEHYKA6K","zoom-apps-sdk","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fzoom-apps-sdk\u002FSKILL.md",[],[113,114,115,105],"sdk","zoom apps sdk","apps",{"skillNo":117,"name":118,"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":119,"categories":120,"keywords":121,"publishedAt":44},"01M6FKJ9EDH9Q5VWDF8HAJRSP0","windows","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwindows\u002FSKILL.md",[],[118],{"skillNo":123,"name":124,"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":125,"categories":126,"keywords":128,"publishedAt":44},"01M6FKJ666BEEFC3AE9GJ72Q93","whiteboard","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwhiteboard\u002FSKILL.md",[127],{"categoryNo":91,"categoryName":92,"taxonomyType":21,"taxonomyTypeDesc":22},[124],{"skillNo":130,"name":131,"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":132,"categories":133,"keywords":134,"publishedAt":44},"01M6FKJ21WFCDGTJQ2Q91T9DVW","websockets","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwebsockets\u002FSKILL.md",[],[131]]