[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CQYMPPAMFGCVABR7T5FRXX":3,"skill-same:01M6CQYMPPAMFGCVABR7T5FRXX":66},{"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":18,"publishedAt":30,"linkOnly":31,"markdownContent":32,"markdownBody":33,"frontMatter":34,"refName":35,"commitSha":36,"skillDirectory":37,"forksCount":14,"repositoryHtmlUrl":38,"repositoryHomepageUrl":6,"ownerHtmlUrl":39,"ownerBlogUrl":40,"ownerDescription":6,"updatedAt":41,"install":42,"resources":55},"01M6CQYMPPAMFGCVABR7T5FRXX","task-processor",null,"Process a task list one sub-task at a time with pause\u002Fconfirm gates, test\u002Fcommit protocol, and file tracking.","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.claude\u002Fskills\u002Ftask-processor\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29],"processor","task","task processor","workflow","test","commit","protocol","file","list","tracking","process","2026-11-10 10:12:30",false,"---\nname: task-processor\ndescription: Process a task list one sub-task at a time with pause\u002Fconfirm gates, test\u002Fcommit protocol, and file tracking.\ncategory: workflow\n---\n\n# Task Processor\n\n## Task Implementation\n- One sub-task at a time. Do not start the next sub-task until user says \"yes\" or \"y\".\n- Completion protocol:\n  1. When finishing a sub-task, mark it `[x]`.\n  2. If all sub-tasks under a parent are `[x]`, then:\n     - Run full test suite.\n     - If tests pass: stage changes (`git add .`).\n     - Clean up temporary files\u002Fcode.\n     - Commit using conventional commit style with multi-`-m` messages describing changes and referencing task\u002FPRD.\n        ```\n        git commit -m \"feat: add payment validation logic\" -m \"- Validates card type and expiry\" -m \"- Adds unit tests for edge cases\" -m \"Related to T123 in PRD\"\n        ```\n  3. After commit, mark the parent task `[x]`.\n- Stop after each sub-task and wait for user go-ahead.\n\n## Task List Maintenance\n1. Update the task list as you work: mark `[x]`, add tasks if needed.\n2. Maintain the \"Relevant Files\" section with one-line purpose per file.\n\n## Production Completion Criteria\n\nA sub-task is **NOT complete** until:\n\n1. **Implementation works**: The code functions correctly\n2. **Tests pass**: All related tests pass\n3. **End-to-end works**: The change works in the full user flow\n4. **No blocking issues**: Any discovered issues are fixed\n\n### Critical Rule: Fix Issues In-Place\n\nWhen you encounter an issue while implementing or testing:\n\n- **DO NOT** mark the sub-task complete with caveats\n- **DO NOT** say \"this works, but there's an unrelated issue\"\n- **DO NOT** defer issues to future tasks\n- **DO** fix the issue as part of the current work\n- **DO** re-test after each fix\n- **DO** only mark complete when it works end-to-end\n\nBefore requesting user approval to proceed:\n1. Verify the sub-task works in isolation\n2. Verify it works in the broader context\n3. If you found and fixed additional issues, mention them\n4. Confirm the feature is production-ready\n\n## AI Instructions\n1. Regularly update the task list after finishing significant work.\n2. Follow completion protocol strictly.\n3. Add newly discovered tasks.\n4. Keep \"Relevant Files\" accurate and up to date.\n5. Before starting, check which sub-task is next.\n6. After implementing a sub-task, update the file and pause for approval.\n7. **Validate end-to-end** before marking any sub-task complete.\n8. **Fix all blocking issues** in-place, never defer them.\n\n## References\n- See `reference.md`.\n- See `.claude\u002Fagents\u002Fproduction-validator.md` for validation guidance.\n","# Task Processor\n\n## Task Implementation\n- One sub-task at a time. Do not start the next sub-task until user says \"yes\" or \"y\".\n- Completion protocol:\n  1. When finishing a sub-task, mark it `[x]`.\n  2. If all sub-tasks under a parent are `[x]`, then:\n     - Run full test suite.\n     - If tests pass: stage changes (`git add .`).\n     - Clean up temporary files\u002Fcode.\n     - Commit using conventional commit style with multi-`-m` messages describing changes and referencing task\u002FPRD.\n        ```\n        git commit -m \"feat: add payment validation logic\" -m \"- Validates card type and expiry\" -m \"- Adds unit tests for edge cases\" -m \"Related to T123 in PRD\"\n        ```\n  3. After commit, mark the parent task `[x]`.\n- Stop after each sub-task and wait for user go-ahead.\n\n## Task List Maintenance\n1. Update the task list as you work: mark `[x]`, add tasks if needed.\n2. Maintain the \"Relevant Files\" section with one-line purpose per file.\n\n## Production Completion Criteria\n\nA sub-task is **NOT complete** until:\n\n1. **Implementation works**: The code functions correctly\n2. **Tests pass**: All related tests pass\n3. **End-to-end works**: The change works in the full user flow\n4. **No blocking issues**: Any discovered issues are fixed\n\n### Critical Rule: Fix Issues In-Place\n\nWhen you encounter an issue while implementing or testing:\n\n- **DO NOT** mark the sub-task complete with caveats\n- **DO NOT** say \"this works, but there's an unrelated issue\"\n- **DO NOT** defer issues to future tasks\n- **DO** fix the issue as part of the current work\n- **DO** re-test after each fix\n- **DO** only mark complete when it works end-to-end\n\nBefore requesting user approval to proceed:\n1. Verify the sub-task works in isolation\n2. Verify it works in the broader context\n3. If you found and fixed additional issues, mention them\n4. Confirm the feature is production-ready\n\n## AI Instructions\n1. Regularly update the task list after finishing significant work.\n2. Follow completion protocol strictly.\n3. Add newly discovered tasks.\n4. Keep \"Relevant Files\" accurate and up to date.\n5. Before starting, check which sub-task is next.\n6. After implementing a sub-task, update the file and pause for approval.\n7. **Validate end-to-end** before marking any sub-task complete.\n8. **Fix all blocking issues** in-place, never defer them.\n\n## References\n- See `reference.md`.\n- See `.claude\u002Fagents\u002Fproduction-validator.md` for validation guidance.\n",{"name":5,"category":22,"description":7},"main","47b89745588c3057f0ccd0517a2eb8967df27054","templates\u002F.claude\u002Fskills\u002Ftask-processor","https:\u002F\u002Fgithub.com\u002Fdundas\u002Fagentbootup-public","https:\u002F\u002Fgithub.com\u002Fdundas","derivative.io","2026-09-02 20:12:15",{"source":8,"skillName":5,"commands":43,"prompt":53,"zipAvailable":54},[44,47,50],{"tool":45,"command":46},"npx","npx skills add dundas\u002Fagentbootup-public --skill task-processor",{"tool":48,"command":49},"bunx","bunx skills add dundas\u002Fagentbootup-public --skill task-processor",{"tool":51,"command":52},"pnpm","pnpm dlx skills add dundas\u002Fagentbootup-public --skill task-processor","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdundas\u002Fagentbootup-public\u002Fblob\u002Fmain\u002Ftemplates\u002F.claude\u002Fskills\u002Ftask-processor\u002FSKILL.md",true,[56,62],{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"reference.md","REFERENCE","参考文档",257,"https:\u002F\u002Fgithub.com\u002Fdundas\u002Fagentbootup-public\u002Fblob\u002Fmain\u002Ftemplates\u002F.claude\u002Fskills\u002Ftask-processor\u002Freference.md",{"path":63,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":64,"sourceHtmlUrl":65},"skill-bundle-manifest.json",1003,"https:\u002F\u002Fgithub.com\u002Fdundas\u002Fagentbootup-public\u002Fblob\u002Fmain\u002Ftemplates\u002F.claude\u002Fskills\u002Ftask-processor\u002Fskill-bundle-manifest.json",[67,81,101,120,129,148],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":78,"publishedAt":30},"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",[73],{"categoryNo":74,"categoryName":75,"taxonomyType":76,"taxonomyTypeDesc":77},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[79,80],"fixture skill","recovery",{"skillNo":82,"name":83,"nameZh":6,"description":84,"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":92,"publishedAt":30},"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",[87],{"categoryNo":88,"categoryName":89,"taxonomyType":90,"taxonomyTypeDesc":91},"01JBSEEDCAT000000000000031","产品经理","PROFESSION","适用职业",[93,94,95,96,97,98,99,100],"user story generator","Story","user story","user","prd","documentation","generate","backlog",{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":113,"publishedAt":30},"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",[107,110],{"categoryNo":108,"categoryName":109,"taxonomyType":76,"taxonomyTypeDesc":77},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":111,"categoryName":112,"taxonomyType":90,"taxonomyTypeDesc":91},"01JBSEEDCAT000000000000032","设计师",[114,115,96,98,116,117,22,118,119],"user journey mapper","journey","ux","visualization","design","testing",{"skillNo":121,"name":122,"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":123,"categories":124,"keywords":125,"publishedAt":30},"01M6CQYXSQQJ4Z5CRAX2SSMHW1","transcript-query","https:\u002F\u002Fgithub.com\u002Fdundas\u002Fagentbootup-public\u002Fblob\u002Fmain\u002Ftemplates\u002F.claude\u002Fskills\u002Ftranscript-query\u002FSKILL.md",[],[126,127,128],"transcript","transcript query","query",{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":139,"publishedAt":30},"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",[135,136],{"categoryNo":108,"categoryName":109,"taxonomyType":76,"taxonomyTypeDesc":77},{"categoryNo":137,"categoryName":138,"taxonomyType":76,"taxonomyTypeDesc":77},"01JBSEEDCAT000000000000010","后端与接口",[140,141,142,23,20,143,144,145,28,146,99,147],"plan","test plan generator","test plan","issue","e2e test","environment","quality","e2e",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":155,"publishedAt":30},"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",[154],{"categoryNo":74,"categoryName":75,"taxonomyType":76,"taxonomyTypeDesc":77},[156,157,158,159,97,99,160,161,24,22],"tasklist generator","gated","files","strategy","tasks","pr"]