[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6P7J5QVMXPJH1WTV33SC2VJ":3,"skill-same:01M6P7J5QVMXPJH1WTV33SC2VJ":104},{"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":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":53,"commitSha":54,"skillDirectory":55,"forksCount":56,"repositoryHtmlUrl":57,"repositoryHomepageUrl":58,"ownerHtmlUrl":59,"ownerBlogUrl":6,"ownerDescription":60,"updatedAt":61,"install":62,"resources":75},"01M6P7J5QVMXPJH1WTV33SC2VJ","ship-feature",null,"Ship a feature end-to-end: understand the ask, research the codebase, plan,\nbuild test-first with small commits, verify via scripts, and deliver. Use this\nskill when starting any non-trivial feature, bug fix, or refactor that needs\nthe full understand → plan → build → verify → deliver cycle.","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\u002Fship-feature\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"ship feature","ship","feature","build test","test-first","ship a feature","scripts","end","human","active","cycle","create","bug","fix","edit","read","ask","plan","search","shipping","2026-11-10 10:12:30",false,"---\nname: ship-feature\ndescription: |\n  Ship a feature end-to-end: understand the ask, research the codebase, plan,\n  build test-first with small commits, verify via scripts, and deliver. Use this\n  skill when starting any non-trivial feature, bug fix, or refactor that needs\n  the full understand → plan → build → verify → deliver cycle.\nlicense: MIT\nmetadata:\n  harness-tags: 'methodology,development,shipping'\n  harness-status: active\n  harness-author: human\n  harness-related: 'read-before-edit,search-before-create'\n---\n\n# ship-feature\n\n## When to use\n\nUse this skill when the user asks to implement a feature, fix a bug, or perform\na refactor that requires more than a trivial one-liner. It covers the full\nlifecycle from understanding the ask through verified delivery.\n\n## Available scripts\n\n- `scripts\u002Fverify-tests.sh` — Run the project's test suite and return pass\u002Ffail counts as JSON. Call this after each significant change to confirm nothing regressed.\n- `scripts\u002Fverify-build.sh` — Run the project's build and return success\u002Ffailure as JSON. Call this before opening a PR.\n- `scripts\u002Fpre-pr-checklist.sh` — Run typecheck + lint + tests + build all-or-nothing. Call this once when the feature is complete and all commits are staged.\n\n## Workflow\n\n1. **Understand** — Read the full ask. Ask clarifying questions if ambiguous.\n2. **Research** — Search the codebase for existing patterns, types, and utilities that the change will touch. Read every related file completely — never speculate.\n3. **Plan** — Outline the approach. Identify risks. Share the plan with the user if the change is non-trivial.\n4. **Build** — One file at a time. Write or update tests alongside each change. Read before edit; reuse before create.\n5. **Verify** — Run `scripts\u002Fverify-tests.sh` after each significant change. Address failures before moving to the next file.\n6. **Pre-PR check** — Run `scripts\u002Fpre-pr-checklist.sh` once all commits are ready. Fix every error before opening the PR.\n7. **Deliver** — Push with a clear commit message. Summarize what changed and why.\n\n## Gotchas\n\n- **Scope creep**: if the work reveals adjacent issues, flag them to the user rather than expanding the change silently.\n- **Missing dependencies**: propose adding any missing library with a rationale before installing it.\n- **Pre-PR checklist is blocking**: if `scripts\u002Fpre-pr-checklist.sh` returns `status: error`, fix the reported step before proceeding.\n- **No test runner detected**: if `scripts\u002Fverify-tests.sh` returns `status: blocked` with `code: NO_TEST_COMMAND`, inform the user and agree on a manual verification step.\n\n## Failure modes\n\nIf `scripts\u002Fpre-pr-checklist.sh` returns `status: error`, read `error.code`:\n\n- `TYPECHECK_FAILED` — TypeScript errors present. Fix them before continuing.\n- `LINT_FAILED` — Lint violations present. Fix or suppress with justification.\n- `TESTS_FAILED` — Test suite is red. Fix failing tests before opening the PR.\n- `BUILD_FAILED` — Build command failed. Fix compilation\u002Fbundling errors.\n- `NO_TEST_COMMAND` — Project has no detectable test script. Discuss with user.\n- `NO_BUILD_COMMAND` — Project has no detectable build script. Typecheck and lint are still enforced.\n","# ship-feature\n\n## When to use\n\nUse this skill when the user asks to implement a feature, fix a bug, or perform\na refactor that requires more than a trivial one-liner. It covers the full\nlifecycle from understanding the ask through verified delivery.\n\n## Available scripts\n\n- `scripts\u002Fverify-tests.sh` — Run the project's test suite and return pass\u002Ffail counts as JSON. Call this after each significant change to confirm nothing regressed.\n- `scripts\u002Fverify-build.sh` — Run the project's build and return success\u002Ffailure as JSON. Call this before opening a PR.\n- `scripts\u002Fpre-pr-checklist.sh` — Run typecheck + lint + tests + build all-or-nothing. Call this once when the feature is complete and all commits are staged.\n\n## Workflow\n\n1. **Understand** — Read the full ask. Ask clarifying questions if ambiguous.\n2. **Research** — Search the codebase for existing patterns, types, and utilities that the change will touch. Read every related file completely — never speculate.\n3. **Plan** — Outline the approach. Identify risks. Share the plan with the user if the change is non-trivial.\n4. **Build** — One file at a time. Write or update tests alongside each change. Read before edit; reuse before create.\n5. **Verify** — Run `scripts\u002Fverify-tests.sh` after each significant change. Address failures before moving to the next file.\n6. **Pre-PR check** — Run `scripts\u002Fpre-pr-checklist.sh` once all commits are ready. Fix every error before opening the PR.\n7. **Deliver** — Push with a clear commit message. Summarize what changed and why.\n\n## Gotchas\n\n- **Scope creep**: if the work reveals adjacent issues, flag them to the user rather than expanding the change silently.\n- **Missing dependencies**: propose adding any missing library with a rationale before installing it.\n- **Pre-PR checklist is blocking**: if `scripts\u002Fpre-pr-checklist.sh` returns `status: error`, fix the reported step before proceeding.\n- **No test runner detected**: if `scripts\u002Fverify-tests.sh` returns `status: blocked` with `code: NO_TEST_COMMAND`, inform the user and agree on a manual verification step.\n\n## Failure modes\n\nIf `scripts\u002Fpre-pr-checklist.sh` returns `status: error`, read `error.code`:\n\n- `TYPECHECK_FAILED` — TypeScript errors present. Fix them before continuing.\n- `LINT_FAILED` — Lint violations present. Fix or suppress with justification.\n- `TESTS_FAILED` — Test suite is red. Fix failing tests before opening the PR.\n- `BUILD_FAILED` — Build command failed. Fix compilation\u002Fbundling errors.\n- `NO_TEST_COMMAND` — Project has no detectable test script. Discuss with user.\n- `NO_BUILD_COMMAND` — Project has no detectable build script. Typecheck and lint are still enforced.\n",{"name":5,"license":15,"metadata":49,"description":52},{"harness-tags":50,"harness-author":32,"harness-status":33,"harness-related":51},"methodology,development,shipping","read-before-edit,search-before-create","Ship a feature end-to-end: understand the ask, research the codebase, plan,\nbuild test-first with small commits, verify via scripts, and deliver. Use this\nskill when starting any non-trivial feature, bug fix, or refactor that needs\nthe full understand → plan → build → verify → deliver cycle.\n","main","0f67103affd30a3c778874b890dbd5801cdbd94f","defaults\u002Fskills\u002Fship-feature",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":63,"prompt":73,"zipAvailable":74},[64,67,70],{"tool":65,"command":66},"npx","npx skills add Phoenixrr2113\u002Fagent-harness --skill ship-feature",{"tool":68,"command":69},"bunx","bunx skills add Phoenixrr2113\u002Fagent-harness --skill ship-feature",{"tool":71,"command":72},"pnpm","pnpm dlx skills add Phoenixrr2113\u002Fagent-harness --skill ship-feature","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPhoenixrr2113\u002Fagent-harness\u002Fblob\u002Fmain\u002Fdefaults\u002Fskills\u002Fship-feature\u002FSKILL.md",true,[76,82,86,90,96,100],{"path":77,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":80,"sourceHtmlUrl":81},"evals\u002Fevals.json","REFERENCE","参考文档",1140,"https:\u002F\u002Fgithub.com\u002FPhoenixrr2113\u002Fagent-harness\u002Fblob\u002Fmain\u002Fdefaults\u002Fskills\u002Fship-feature\u002Fevals\u002Fevals.json",{"path":83,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":84,"sourceHtmlUrl":85},"evals\u002Ffiles\u002Fbranch-state.txt",586,"https:\u002F\u002Fgithub.com\u002FPhoenixrr2113\u002Fagent-harness\u002Fblob\u002Fmain\u002Fdefaults\u002Fskills\u002Fship-feature\u002Fevals\u002Ffiles\u002Fbranch-state.txt",{"path":87,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":88,"sourceHtmlUrl":89},"evals\u002Ftriggers.json",3188,"https:\u002F\u002Fgithub.com\u002FPhoenixrr2113\u002Fagent-harness\u002Fblob\u002Fmain\u002Fdefaults\u002Fskills\u002Fship-feature\u002Fevals\u002Ftriggers.json",{"path":91,"resourceType":92,"resourceTypeDesc":93,"sizeBytes":94,"sourceHtmlUrl":95},"scripts\u002Fpre-pr-checklist.sh","SCRIPT","脚本",12580,"https:\u002F\u002Fgithub.com\u002FPhoenixrr2113\u002Fagent-harness\u002Fblob\u002Fmain\u002Fdefaults\u002Fskills\u002Fship-feature\u002Fscripts\u002Fpre-pr-checklist.sh",{"path":97,"resourceType":92,"resourceTypeDesc":93,"sizeBytes":98,"sourceHtmlUrl":99},"scripts\u002Fverify-build.sh",6252,"https:\u002F\u002Fgithub.com\u002FPhoenixrr2113\u002Fagent-harness\u002Fblob\u002Fmain\u002Fdefaults\u002Fskills\u002Fship-feature\u002Fscripts\u002Fverify-build.sh",{"path":101,"resourceType":92,"resourceTypeDesc":93,"sizeBytes":102,"sourceHtmlUrl":103},"scripts\u002Fverify-tests.sh",8521,"https:\u002F\u002Fgithub.com\u002FPhoenixrr2113\u002Fagent-harness\u002Fblob\u002Fmain\u002Fdefaults\u002Fskills\u002Fship-feature\u002Fscripts\u002Fverify-tests.sh",[105,116,137,161,185,204],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":114,"publishedAt":44},"01M6P7MR06WFMWS1BZYK4BNR6W","research","Conduct research.","https:\u002F\u002Fgithub.com\u002FPhoenixrr2113\u002Fagent-harness\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fold-harness-7-primitives\u002Fskills\u002Fresearch\u002FSKILL.md",[111],{"categoryNo":112,"categoryName":113,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",[107,115],"conduct",{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":123,"publishedAt":44},"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",[122],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[124,125,126,127,128,129,130,131,32,132,133,134,135,136],"name","{{name=null}=null}","user","when to use","for","can","match","it","pattern","draft","use","prompt","model",{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":144,"publishedAt":44},"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",[143],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[145,146,147,148,149,150,151,152,153,154,155,156,157,128,158,159,160,26,134,37],"repo","git","working in a git repo","commit","Bash","file","verification","dev","lint","test","workflow","done","work","manual","operating","style",{"skillNo":162,"name":163,"nameZh":6,"description":164,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":165,"categories":166,"keywords":171,"publishedAt":44},"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",[167,170],{"categoryNo":168,"categoryName":169,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[154,172,173,174,175,176,128,177,33,32,178,179,180,134,181,182,149,152,183,184],"test runner","runner","output","with","you","call","project","test suite","reports","command","subagent","testing","default",{"skillNo":186,"name":187,"nameZh":6,"description":188,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":189,"categories":190,"keywords":192,"publishedAt":44},"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",[191],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[187,193,194,195,154,196,152,128,197,198,199,160,32,200,134,182,149,201,202,203],"code","pull request","change","review","gaps","bugs","reviews","diff","SET","pull","issues",{"skillNo":205,"name":206,"nameZh":6,"description":207,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":208,"categories":209,"keywords":211,"publishedAt":44},"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",[210],{"categoryNo":168,"categoryName":169,"taxonomyType":21,"taxonomyTypeDesc":22},[212,213,37,163,214,128,32,33,215,173,216,134,145,187,149,217,152,148,154,183],"fix failing tests","tests","apply","green","root-cause","verify"]