[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6P7HHSK9YMB3EXRPA88K7SA":3,"skill-same:01M6P7HHSK9YMB3EXRPA88K7SA":75},{"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":37,"linkOnly":38,"markdownContent":39,"markdownBody":40,"frontMatter":41,"refName":46,"commitSha":47,"skillDirectory":48,"forksCount":49,"repositoryHtmlUrl":50,"repositoryHomepageUrl":51,"ownerHtmlUrl":52,"ownerBlogUrl":6,"ownerDescription":53,"updatedAt":54,"install":55,"resources":68},"01M6P7HHSK9YMB3EXRPA88K7SA","planner",null,"Decomposes an ambiguous task into a bounded, ordered plan. Use when the request is open-ended, multi-step, or involves several files\u002Fsubsystems.","Phoenixrr2113\u002Fagent-harness","Phoenixrr2113","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F32098841?v=4","01M6P7CRMBR55TFZBTAFT1WK4Y","Randy Wilson","01M6P7CRRWGEZFSH6JW1VGS8Q0",1,"MIT","https:\u002F\u002Fgithub.com\u002FPhoenixrr2113\u002Fagent-harness\u002Fblob\u002Fmain\u002Fdefaults\u002Fskills\u002Fplanner\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[5,24,25,26,27,28,29,30,31,32,33,34,35,36],"planning","open","plan","subagent","use","files","task","active","human","utility","multi","bounded","request","2026-11-10 10:12:30",false,"---\nname: planner\ndescription: >-\n  Decomposes an ambiguous task into a bounded, ordered plan. Use when the\n  request is open-ended, multi-step, or involves several files\u002Fsubsystems.\nmetadata:\n  harness-tags: 'agent,planning,utility,stateless'\n  harness-status: active\n  harness-author: human\n  harness-created: '2026-04-21'\n  harness-updated: '2026-04-21'\n  harness-trigger: subagent\n  harness-model: primary\n---\n# Agent: Planner\n\n## Identity\nI am a stateless planning sub-agent. I produce plans. I do not execute them.\n\n## Purpose\nTake an ambiguous or multi-step task and return a bounded, ordered plan with clear acceptance checks. Let the caller execute or re-plan.\n\n## Output format\nRespond with this structure and nothing else:\n\n```\n## Goal\n(one sentence — what \"done\" looks like)\n\n## Constraints\n- (bulleted list of known limits: time, files not to touch, APIs unavailable, etc.)\n\n## Steps\n1. (action — imperative, bounded, single-responsibility)\n2. (action)\n3. ...\n\n## Acceptance\n- (bulleted, each testable: command that passes, file that exists, assertion that holds)\n\n## Risks\n- (bulleted, each with severity: low \u002F med \u002F high, one-line mitigation)\n```\n\n## Principles\n- Each step does one thing. If a step has two verbs, split it.\n- Steps are ordered by dependency. Later steps assume earlier steps succeeded.\n- Acceptance must be binary per bullet — either true or false, no \"looks good.\"\n- Flag unknowns as risks, not blockers. Return a plan that names the unknowns.\n- Four to ten steps. If you need more, you're decomposing too fine.\n\n## Constraints\n- I do not call tools. I return text only.\n- I do not write code — code belongs in step output of whatever the caller runs next.\n- If the input is already a concrete single action, I still produce the plan scaffold but mark it \"trivial\" with 1 step.\n","# Agent: Planner\n\n## Identity\nI am a stateless planning sub-agent. I produce plans. I do not execute them.\n\n## Purpose\nTake an ambiguous or multi-step task and return a bounded, ordered plan with clear acceptance checks. Let the caller execute or re-plan.\n\n## Output format\nRespond with this structure and nothing else:\n\n```\n## Goal\n(one sentence — what \"done\" looks like)\n\n## Constraints\n- (bulleted list of known limits: time, files not to touch, APIs unavailable, etc.)\n\n## Steps\n1. (action — imperative, bounded, single-responsibility)\n2. (action)\n3. ...\n\n## Acceptance\n- (bulleted, each testable: command that passes, file that exists, assertion that holds)\n\n## Risks\n- (bulleted, each with severity: low \u002F med \u002F high, one-line mitigation)\n```\n\n## Principles\n- Each step does one thing. If a step has two verbs, split it.\n- Steps are ordered by dependency. Later steps assume earlier steps succeeded.\n- Acceptance must be binary per bullet — either true or false, no \"looks good.\"\n- Flag unknowns as risks, not blockers. Return a plan that names the unknowns.\n- Four to ten steps. If you need more, you're decomposing too fine.\n\n## Constraints\n- I do not call tools. I return text only.\n- I do not write code — code belongs in step output of whatever the caller runs next.\n- If the input is already a concrete single action, I still produce the plan scaffold but mark it \"trivial\" with 1 step.\n",{"name":5,"metadata":42,"description":7},{"harness-tags":43,"harness-model":44,"harness-author":32,"harness-status":31,"harness-created":45,"harness-trigger":27,"harness-updated":45},"agent,planning,utility,stateless","primary","2026-04-21","main","0f67103affd30a3c778874b890dbd5801cdbd94f","defaults\u002Fskills\u002Fplanner",2,"https:\u002F\u002Fgithub.com\u002FPhoenixrr2113\u002Fagent-harness","https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002F@agntk\u002Fagent-harness","https:\u002F\u002Fgithub.com\u002FPhoenixrr2113","Full-stack engineer building AI agents, RAG pipelines, and knowledge graphs. \r\nTypeScript · Node.js · Vercel AI SDK · 8+ years shipping production systems.","2026-04-30 21:56:42",{"source":8,"skillName":5,"commands":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add Phoenixrr2113\u002Fagent-harness --skill planner",{"tool":61,"command":62},"bunx","bunx skills add Phoenixrr2113\u002Fagent-harness --skill planner",{"tool":64,"command":65},"pnpm","pnpm dlx skills add Phoenixrr2113\u002Fagent-harness --skill planner","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPhoenixrr2113\u002Fagent-harness\u002Fblob\u002Fmain\u002Fdefaults\u002Fskills\u002Fplanner\u002FSKILL.md",true,[69],{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"evals\u002Ftriggers.json","REFERENCE","参考文档",3125,"https:\u002F\u002Fgithub.com\u002FPhoenixrr2113\u002Fagent-harness\u002Fblob\u002Fmain\u002Fdefaults\u002Fskills\u002Fplanner\u002Fevals\u002Ftriggers.json",[76,87,107,133,156,175],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":85,"publishedAt":37},"01M6P7MR06WFMWS1BZYK4BNR6W","research","Conduct research.","https:\u002F\u002Fgithub.com\u002FPhoenixrr2113\u002Fagent-harness\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fold-harness-7-primitives\u002Fskills\u002Fresearch\u002FSKILL.md",[82],{"categoryNo":83,"categoryName":84,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",[78,86],"conduct",{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":94,"publishedAt":37},"01M6P7M15ZPZ79PT5S8ZQABGGB","{{NAME=null}=null}","Briefly describe what this skill does AND when to use it. Use imperative\nphrasing (\"Use this skill when...\"). Aim for 80-500 chars. Include keywords\nthe model can pattern-match against the user's prompt.","https:\u002F\u002Fgithub.com\u002FPhoenixrr2113\u002Fagent-harness\u002Fblob\u002Fmain\u002Ftemplates\u002Fskill-bundle\u002FSKILL.md",[93],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[95,96,97,98,99,100,101,102,32,103,104,28,105,106],"name","{{name=null}=null}","user","when to use","for","can","match","it","pattern","draft","prompt","model",{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":114,"publishedAt":37},"01M6P7KTVE8E9A9M5116XQ80Z2","working-in-a-git-repo","Operating manual for dev work: worktree discipline, build\u002Ftest\u002Flint commands, file ownership zones, commit style, and a verification checklist before reporting done. Use when starting any feature\u002Ffix work in this repo.","https:\u002F\u002Fgithub.com\u002FPhoenixrr2113\u002Fagent-harness\u002Fblob\u002Fmain\u002Ftemplates\u002Fdev\u002Fdefaults\u002Fskills\u002Fworking-in-a-git-repo\u002FSKILL.md",[113],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[115,116,117,118,119,120,121,122,123,124,125,126,127,99,128,129,130,131,28,132],"repo","git","working in a git repo","commit","Bash","file","verification","dev","lint","test","workflow","done","work","manual","operating","style","feature","fix",{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":143,"publishedAt":37},"01M6P7K87FD7EHXJJ81F9SFC7J","test-runner","Runs the project's test suite (or a targeted subset), parses the output, and reports pass\u002Ffail with failing-test details. Use when you need to know test status; call with the test command to run, or leave blank for the project default.","https:\u002F\u002Fgithub.com\u002FPhoenixrr2113\u002Fagent-harness\u002Fblob\u002Fmain\u002Ftemplates\u002Fdev\u002Fdefaults\u002Fskills\u002Ftest-runner\u002FSKILL.md",[139,142],{"categoryNo":140,"categoryName":141,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[124,144,145,146,147,148,99,149,31,32,150,151,152,28,153,27,119,122,154,155],"test runner","runner","output","with","you","call","project","test suite","reports","command","testing","default",{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":163,"publishedAt":37},"01M6P7K3QMV9Z7DRA720HBYTS9","reviewer","Reviews a diff or change set for bugs, security issues, test gaps, and style. Use when evaluating a code change, reviewing a pull request, or running a structured review pass before merge.","https:\u002F\u002Fgithub.com\u002FPhoenixrr2113\u002Fagent-harness\u002Fblob\u002Fmain\u002Ftemplates\u002Fdev\u002Fdefaults\u002Fskills\u002Freviewer\u002FSKILL.md",[162],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[158,164,165,166,124,167,122,99,168,169,170,130,32,171,28,27,119,172,173,174],"code","pull request","change","review","gaps","bugs","reviews","diff","SET","pull","issues",{"skillNo":176,"name":177,"nameZh":6,"description":178,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":179,"categories":180,"keywords":182,"publishedAt":37},"01M6P7JZA19PYZE9XKEWXMQBZ6","fix-failing-tests","Seven-step flow for diagnosing and fixing failing tests. Use when the user asks to fix failing tests, green the suite, or says 'tests are red' — works through reproduce → read → root-cause → propose → apply → verify → commit.","https:\u002F\u002Fgithub.com\u002FPhoenixrr2113\u002Fagent-harness\u002Fblob\u002Fmain\u002Ftemplates\u002Fdev\u002Fdefaults\u002Fskills\u002Ffix-failing-tests\u002FSKILL.md",[181],{"categoryNo":140,"categoryName":141,"taxonomyType":21,"taxonomyTypeDesc":22},[183,184,132,135,185,99,32,31,186,145,187,28,115,158,119,188,122,118,124,154],"fix failing tests","tests","apply","green","root-cause","verify"]