[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6P7JZA19PYZE9XKEWXMQBZ6":3,"skill-same:01M6P7JZA19PYZE9XKEWXMQBZ6":78},{"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":55,"commitSha":56,"skillDirectory":57,"forksCount":58,"repositoryHtmlUrl":59,"repositoryHomepageUrl":60,"ownerHtmlUrl":61,"ownerBlogUrl":6,"ownerDescription":62,"updatedAt":63,"install":64,"resources":77},"01M6P7JZA19PYZE9XKEWXMQBZ6","fix-failing-tests",null,"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.","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\u002Ftemplates\u002Fdev\u002Fdefaults\u002Fskills\u002Ffix-failing-tests\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量","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],"fix failing tests","tests","fix","root-cause","apply","for","human","active","green","test-runner","runner","testing","use","repo","reviewer","Bash","verify","dev","commit","test","2026-11-10 10:12:30",false,"---\nname: fix-failing-tests\ndescription: \"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.\"\nallowed-tools: \"Read Edit Bash\"\nmetadata:\n  harness-tags: \"playbook, testing, dev\"\n  harness-status: active\n  harness-author: human\n  harness-created: '2026-04-21'\n  harness-updated: '2026-04-30'\n  harness-related: \"reviewer, test-runner, working-in-a-git-repo\"\n---\n\n# Skill: Fix Failing Tests\n\n## When this skill applies\n\nTriggered by the human asking to fix failing tests, green the suite, or a related phrasing.\n\n## Step 1 — Reproduce\n\nWork in the assigned worktree (or request one per `working-in-a-git-repo`).\nRun the project's test command and identify which files are red, which\nspecific test cases fail, and the assertion that fails with actual vs.\nexpected values.\n\nIf no tests are red, STOP — there's nothing to fix. Report back to human.\n\n## Step 2 — Read the failing tests\n\nRead the entire test file where failures occur. Understand what behavior\nis under test and what the system-under-test is supposed to do. Read the\nproduction code the test is exercising. Do not guess; read.\n\n## Step 3 — Root-cause the failure\n\nAnswer: is the bug in the test, or in production code?\n\nCommon test-side bugs: hardcoded dates or timestamps going stale, shared\nstate across tests, caching that persists across assertions, mock drift\nfrom real implementation.\n\nIf I cannot determine root cause in one pass, STOP and surface what I\nfound to the human.\n\n## Step 4 — Propose the minimal fix\n\nState in one paragraph:\n- What I'm changing\n- Which file(s)\n- Why it resolves the failure without altering unintended behavior\n\nWait for the human's acknowledgement on non-trivial changes. For clear\ntest-only fixes with no production impact, proceed.\n\n## Step 5 — Apply the fix\n\n- ONE file at a time.\n- Specific lines only. Never rewrite a whole file for a spot change.\n- Follow existing patterns — check nearby tests for how they handle the\n  same concern (mocking time, fixtures, setup\u002Fteardown).\n\n## Step 6 — Verify\n\nAll three must pass:\n1. Targeted suite green.\n2. Full suite green (or no new failures beyond pre-existing unrelated ones).\n3. Linter: no new errors.\n\nIf any fail, debug before proceeding. Do not commit red tests.\n\n## Step 7 — Commit & report\n\n- Commit on the feature branch with a message matching project style.\n- Report to the human: branch name, commit SHA, files changed, one-line summary.\n- DO NOT push. DO NOT open a PR. DO NOT merge to main.\n\n## Failure handling\n\n- If root cause is ambiguous → STOP, ask human.\n- If the fix would require production-code changes (not just tests) → STOP,\n  describe what's needed, ask human.\n- If environment-specific issues emerge (CI git config, Node version, etc.) →\n  note them and proceed where possible.\n","# Skill: Fix Failing Tests\n\n## When this skill applies\n\nTriggered by the human asking to fix failing tests, green the suite, or a related phrasing.\n\n## Step 1 — Reproduce\n\nWork in the assigned worktree (or request one per `working-in-a-git-repo`).\nRun the project's test command and identify which files are red, which\nspecific test cases fail, and the assertion that fails with actual vs.\nexpected values.\n\nIf no tests are red, STOP — there's nothing to fix. Report back to human.\n\n## Step 2 — Read the failing tests\n\nRead the entire test file where failures occur. Understand what behavior\nis under test and what the system-under-test is supposed to do. Read the\nproduction code the test is exercising. Do not guess; read.\n\n## Step 3 — Root-cause the failure\n\nAnswer: is the bug in the test, or in production code?\n\nCommon test-side bugs: hardcoded dates or timestamps going stale, shared\nstate across tests, caching that persists across assertions, mock drift\nfrom real implementation.\n\nIf I cannot determine root cause in one pass, STOP and surface what I\nfound to the human.\n\n## Step 4 — Propose the minimal fix\n\nState in one paragraph:\n- What I'm changing\n- Which file(s)\n- Why it resolves the failure without altering unintended behavior\n\nWait for the human's acknowledgement on non-trivial changes. For clear\ntest-only fixes with no production impact, proceed.\n\n## Step 5 — Apply the fix\n\n- ONE file at a time.\n- Specific lines only. Never rewrite a whole file for a spot change.\n- Follow existing patterns — check nearby tests for how they handle the\n  same concern (mocking time, fixtures, setup\u002Fteardown).\n\n## Step 6 — Verify\n\nAll three must pass:\n1. Targeted suite green.\n2. Full suite green (or no new failures beyond pre-existing unrelated ones).\n3. Linter: no new errors.\n\nIf any fail, debug before proceeding. Do not commit red tests.\n\n## Step 7 — Commit & report\n\n- Commit on the feature branch with a message matching project style.\n- Report to the human: branch name, commit SHA, files changed, one-line summary.\n- DO NOT push. DO NOT open a PR. DO NOT merge to main.\n\n## Failure handling\n\n- If root cause is ambiguous → STOP, ask human.\n- If the fix would require production-code changes (not just tests) → STOP,\n  describe what's needed, ask human.\n- If environment-specific issues emerge (CI git config, Node version, etc.) →\n  note them and proceed where possible.\n",{"name":5,"metadata":49,"description":7,"allowed-tools":54},{"harness-tags":50,"harness-author":30,"harness-status":31,"harness-created":51,"harness-related":52,"harness-updated":53},"playbook, testing, dev","2026-04-21","reviewer, test-runner, working-in-a-git-repo","2026-04-30","Read Edit Bash","main","0f67103affd30a3c778874b890dbd5801cdbd94f","templates\u002Fdev\u002Fdefaults\u002Fskills\u002Ffix-failing-tests",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":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add Phoenixrr2113\u002Fagent-harness --skill fix-failing-tests",{"tool":70,"command":71},"bunx","bunx skills add Phoenixrr2113\u002Fagent-harness --skill fix-failing-tests",{"tool":73,"command":74},"pnpm","pnpm dlx skills add Phoenixrr2113\u002Fagent-harness --skill fix-failing-tests","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPhoenixrr2113\u002Fagent-harness\u002Fblob\u002Fmain\u002Ftemplates\u002Fdev\u002Fdefaults\u002Fskills\u002Ffix-failing-tests\u002FSKILL.md",true,[],[79,90,111,131,150,168],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":88,"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",[85],{"categoryNo":86,"categoryName":87,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",[81,89],"conduct",{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":99,"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",[96],{"categoryNo":97,"categoryName":98,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[100,101,102,103,29,104,105,106,30,107,108,36,109,110],"name","{{name=null}=null}","user","when to use","can","match","it","pattern","draft","prompt","model",{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":118,"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",[117],{"categoryNo":97,"categoryName":98,"taxonomyType":21,"taxonomyTypeDesc":22},[119,120,37,121,39,122,123,124,41,125,42,43,126,26,29,127,128,129,130,36],"working in a git repo","git","work","workflow","file","verification","lint","done","manual","operating","style","feature",{"skillNo":132,"name":33,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":138,"publishedAt":44},"01M6P7K87FD7EHXJJ81F9SFC7J","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",[136,137],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":97,"categoryName":98,"taxonomyType":21,"taxonomyTypeDesc":22},[43,139,34,29,140,141,142,143,30,31,144,145,146,36,147,148,39,41,35,149],"test runner","you","with","output","project","reports","default","test suite","command","subagent","call",{"skillNo":151,"name":38,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":156,"publishedAt":44},"01M6P7K3QMV9Z7DRA720HBYTS9","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",[155],{"categoryNo":97,"categoryName":98,"taxonomyType":21,"taxonomyTypeDesc":22},[38,41,157,158,159,43,160,161,29,162,163,164,129,30,165,36,148,39,166,167],"code","pull request","change","review","issues","gaps","bugs","reviews","diff","SET","pull",{"skillNo":169,"name":170,"nameZh":6,"description":171,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":172,"categories":173,"keywords":183,"publishedAt":44},"01M6P7JFP1SMF8QRKH42D1Y2FY","writing-plans","Use when you have a spec or requirements for a multi-step task, before touching code","https:\u002F\u002Fgithub.com\u002FPhoenixrr2113\u002Fagent-harness\u002Fblob\u002Fmain\u002Fdefaults\u002Fskills\u002Fwriting-plans\u002FSKILL.md",[174,177,178],{"categoryNo":175,"categoryName":176,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":97,"categoryName":98,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":179,"categoryName":180,"taxonomyType":181,"taxonomyTypeDesc":182},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[184,185,186,187,29,140,188,189,30,31,190,191,36,192,193,157,194,195],"plans","writing","writing plans","requirements","multi-step task","multi","task","superpowers","https","license","github","spec"]