[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6GGS30NJW4Q7QN4KVT0CV08":3,"skill-same:01M6GGS30NJW4Q7QN4KVT0CV08":65},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":6,"ownerHtmlUrl":49,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":50,"install":51,"resources":64},"01M6GGS30NJW4Q7QN4KVT0CV08","systematic-debugger",null,"When applying debugging techniques during any investigation — root cause tracing, bisect, defense-in-depth. Enforces hypothesis-first analysis and prohibits guess-and-check changes. Use standalone or inside the debug-issue workflow.","ahmadulhoq\u002Fagentskel","ahmadulhoq","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F3884252?v=4","01M6GGC32SQTQ52FY4JB14FYSY","Ahmadul Hoq","01M6GGC37CJEYM63V3WEHY4Y8V",13,"MIT","https:\u002F\u002Fgithub.com\u002Fahmadulhoq\u002Fagentskel\u002Fblob\u002Fmain\u002Froles\u002Fdev\u002Fskills\u002Fsystematic-debugger\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"systematic debugger","systematic","debugger","investigation","standalone","root","issue workflow","issue","use","check","bisect","workflow","analysis","first","defense","hypothesis","defense-in-depth","tracing","debugging","debug","2026-11-10 10:12:30",false,"---\nname: systematic-debugger\nlicense: MIT\ndescription: When applying debugging techniques during any investigation — root cause tracing, bisect, defense-in-depth. Enforces hypothesis-first analysis and prohibits guess-and-check changes. Use standalone or inside the debug-issue workflow.\n---\n\n# Systematic Debugger Skill\n\n**Purpose:** Stop hallucination loops. Every code change requires a verified hypothesis and a failing test first.\n\n## Prohibited Behaviors\n- Adding `console.log` \u002F `print` \u002F debug statements without a stated hypothesis.\n- Changing code to \"see what happens.\"\n- Fixing code before a failing test exists.\n- Treating the first hypothesis as confirmed without ruling out alternatives.\n\n## Techniques\n\n| Technique | When to use |\n|-----------|-------------|\n| Root Cause Tracing | Follow the call stack up to the originating decision point |\n| Defense in Depth | Audit every layer: input validation → business logic → persistence |\n| Bisect | Binary-search commits or code paths to find the introduction point |\n\n## Required Steps (in order)\n1. **Reproduce** the bug reliably. If unable, state why and stop.\n2. **Hypothesize:** \"The bug is caused by [X] because [evidence Y].\"\n3. **List alternatives:** at least 2 other hypotheses to rule out.\n4. **Create a failing test** that reproduces the bug. Run it — must fail.\n5. **Isolate root cause** using a technique above. Rule out alternatives explicitly.\n6. **Fix** with minimum code targeting the confirmed root cause only.\n7. **Verify:** failing test now passes; full suite has no regressions.\n8. **Log:** update `.memory\u002FLESSONS.md` with root cause + prevention rule.\n\n## Common Rationalizations\n\n| Rationalization | Why it's wrong | Do this instead |\n|---|---|---|\n| \"I'll just try changing X and see\" | That's the loop we're breaking | State a hypothesis first |\n| \"The test is hard to write here\" | Difficulty ≠ exemption | Document why and get explicit sign-off |\n| \"I'm pretty sure it's Y\" | Pretty sure ≠ confirmed | Rule out alternatives before fixing |\n| \"I'll add a log to check\" | Logs without hypotheses produce noise | State what you expect the log to show first |\n\n---\n\n**Gate:** Do not change production code until step 4 (failing test) is complete and\nstep 5 (root cause confirmed) is documented.\n","# Systematic Debugger Skill\n\n**Purpose:** Stop hallucination loops. Every code change requires a verified hypothesis and a failing test first.\n\n## Prohibited Behaviors\n- Adding `console.log` \u002F `print` \u002F debug statements without a stated hypothesis.\n- Changing code to \"see what happens.\"\n- Fixing code before a failing test exists.\n- Treating the first hypothesis as confirmed without ruling out alternatives.\n\n## Techniques\n\n| Technique | When to use |\n|-----------|-------------|\n| Root Cause Tracing | Follow the call stack up to the originating decision point |\n| Defense in Depth | Audit every layer: input validation → business logic → persistence |\n| Bisect | Binary-search commits or code paths to find the introduction point |\n\n## Required Steps (in order)\n1. **Reproduce** the bug reliably. If unable, state why and stop.\n2. **Hypothesize:** \"The bug is caused by [X] because [evidence Y].\"\n3. **List alternatives:** at least 2 other hypotheses to rule out.\n4. **Create a failing test** that reproduces the bug. Run it — must fail.\n5. **Isolate root cause** using a technique above. Rule out alternatives explicitly.\n6. **Fix** with minimum code targeting the confirmed root cause only.\n7. **Verify:** failing test now passes; full suite has no regressions.\n8. **Log:** update `.memory\u002FLESSONS.md` with root cause + prevention rule.\n\n## Common Rationalizations\n\n| Rationalization | Why it's wrong | Do this instead |\n|---|---|---|\n| \"I'll just try changing X and see\" | That's the loop we're breaking | State a hypothesis first |\n| \"The test is hard to write here\" | Difficulty ≠ exemption | Document why and get explicit sign-off |\n| \"I'm pretty sure it's Y\" | Pretty sure ≠ confirmed | Rule out alternatives before fixing |\n| \"I'll add a log to check\" | Logs without hypotheses produce noise | State what you expect the log to show first |\n\n---\n\n**Gate:** Do not change production code until step 4 (failing test) is complete and\nstep 5 (root cause confirmed) is documented.\n",{"name":5,"license":15,"description":7},"main","d94c109a4fad51623dc6048315860e53b32673fb","roles\u002Fdev\u002Fskills\u002Fsystematic-debugger",3,"https:\u002F\u002Fgithub.com\u002Fahmadulhoq\u002Fagentskel","https:\u002F\u002Fgithub.com\u002Fahmadulhoq","2026-11-07 00:53:22",{"source":8,"skillName":5,"commands":52,"prompt":62,"zipAvailable":63},[53,56,59],{"tool":54,"command":55},"npx","npx skills add ahmadulhoq\u002Fagentskel --skill systematic-debugger",{"tool":57,"command":58},"bunx","bunx skills add ahmadulhoq\u002Fagentskel --skill systematic-debugger",{"tool":60,"command":61},"pnpm","pnpm dlx skills add ahmadulhoq\u002Fagentskel --skill systematic-debugger","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fahmadulhoq\u002Fagentskel\u002Fblob\u002Fmain\u002Froles\u002Fdev\u002Fskills\u002Fsystematic-debugger\u002FSKILL.md",true,[],[66,85,112,138,163,177],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":39},"01M6GGSN2D57Y8BR50X08Y695H","setup-project","When setting up agentskel on a new project that does not yet have .memory\u002F or .agents\u002F. Use when the user says \"set up agentskel\", \"install agentskel\", or \"add agent memory to this project\".","https:\u002F\u002Fgithub.com\u002Fahmadulhoq\u002Fagentskel\u002Fblob\u002Fmain\u002Fskills\u002Fsetup-project\u002FSKILL.md",[],[73,74,75,76,77,78,27,79,80,81,82,83,84],"setup","setup project","project","memory","add","up","install","add agent","user","new project","SET","agent memory",{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":39},"01M6GGSJ6HD2DFVZQTESJ81GYM","using-git-worktrees","When running long feature implementations, parallel branch work, or build\u002Ftest scripts that must not interfere with the user's active working directory. Creates isolated execution environments via git worktrees in sibling directories.","https:\u002F\u002Fgithub.com\u002Fahmadulhoq\u002Fagentskel\u002Fblob\u002Fmain\u002Froles\u002Fdev\u002Fskills\u002Fusing-git-worktrees\u002FSKILL.md",[],[92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111],"using git worktrees","worktrees","git worktrees","Using git","git","branch","work","parallel","directory","execution","test","build","directories","environments","with","via","long","scripts","feature","active",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":123,"publishedAt":39},"01M6GGSCFPK7MDSZH96XTNZR9B","test-engineer","When designing test strategy, analysing coverage, or writing tests outside the TDD cycle. Also use when working with CI pipelines or validating changes end-to-end.","https:\u002F\u002Fgithub.com\u002Fahmadulhoq\u002Fagentskel\u002Fblob\u002Fmain\u002Froles\u002Fdev\u002Fskills\u002Ftest-engineer\u002FSKILL.md",[118],{"categoryNo":119,"categoryName":120,"taxonomyType":121,"taxonomyTypeDesc":122},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",[102,124,125,126,127,128,106,129,130,131,27,132,133,134,135,136,137],"test engineer","engineer","end","strategy","tests","tdd cycle","test strategy","pipelines","coverage","ci","writing tests","tdd","writing","cycle",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":148,"publishedAt":39},"01M6GGS8YA9XZB6DWV22JC0YTB","test-driven-development","When implementing logic changes during develop-feature or implement-task. Use the Red-Green-Refactor cycle to write a failing test before any production code.","https:\u002F\u002Fgithub.com\u002Fahmadulhoq\u002Fagentskel\u002Fblob\u002Fmain\u002Froles\u002Fdev\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[144,147],{"categoryNo":145,"categoryName":146,"taxonomyType":121,"taxonomyTypeDesc":122},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":119,"categoryName":120,"taxonomyType":121,"taxonomyTypeDesc":122},[149,150,151,102,152,153,154,155,156,157,110,158,159,137,160,161,27,162],"driven","development","test driven development","refactor","Production","code","implement","develop","red","logic","green","task","red-green-refactor","write",{"skillNo":164,"name":165,"nameZh":6,"description":166,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":167,"categories":168,"keywords":169,"publishedAt":39},"01M6GGS61D41ZJG4D8XAS97H62","task-planner","When decomposing a feature or spec into implementable subtasks, estimating scope, or orchestrating multi-step work across subagents.","https:\u002F\u002Fgithub.com\u002Fahmadulhoq\u002Fagentskel\u002Fblob\u002Fmain\u002Froles\u002Fdev\u002Fskills\u002Ftask-planner\u002FSKILL.md",[],[170,160,171,98,172,173,110,174,175,176],"task planner","planner","multi","scope","across","subagents","spec",{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":183,"publishedAt":39},"01M6GGS04EDQVVJRW5CTB3V60K","domain-expert","When working on features that require domain knowledge — business rules, terminology, or invariants specific to this project. [Replace this description and the content below with your project's domain.]","https:\u002F\u002Fgithub.com\u002Fahmadulhoq\u002Fagentskel\u002Fblob\u002Fmain\u002Froles\u002Fdev\u002Fskills\u002Fdomain-expert\u002FSKILL.md",[],[184,185,186,187,106,75,188,189,190,191,192],"domain expert","domain","expert","invariants","terminology","business","Rules","knowledge","content"]