[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CS9N4GGN5QB8Y677P54KQN":3,"skill-same:01M7CS9N4GGN5QB8Y677P54KQN":49},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":31,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M7CS9N4GGN5QB8Y677P54KQN","root-cause-debugging",null,"Root-cause debugging discipline. Use when a test, build or pipeline fails, behaviour does not match expectations, a bug task arrives, or a task comes back in need_revision — before proposing any fix.","makifbaysal\u002Ftasktrooper","makifbaysal","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F25031940?v=4","01M7CRG3ZCSYZSSEVDMW3DEYC8","Mehmet Akif Baysal","01M7CRG401FJ8YAXH5ER730XYV",122,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fmobile-developer\u002Fskills\u002Froot-cause-debugging\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: root-cause-debugging\ncategory: quality\ndescription: Root-cause debugging discipline. Use when a test, build or pipeline fails, behaviour does not match expectations, a bug task arrives, or a task comes back in need_revision — before proposing any fix.\nsource: obra\u002Fsuperpowers (MIT), adapted\n---\n# Root-Cause Debugging\n\n## Overview\n\nRandom fixes waste time and create new bugs. Quick patches mask underlying issues.\n\n**Core principle:** ALWAYS find the root cause before attempting fixes. Symptom fixes are failure.\n\n## The Iron Law\n\n```\nNO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST\n```\n\nUse this for ANY technical issue: a task returned to need_revision, a failing test, a red pipeline, unexpected behavior. Use it ESPECIALLY under time pressure — systematic is faster than guess-and-check thrashing.\n\n## The Four Phases\n\nComplete each phase before the next.\n\n### Phase 1 — Build a feedback loop, then investigate\n\nThis is the skill: before anything else, name ONE command you have already run that goes red on THIS symptom — a failing test, a `curl` against the running service, a `browser_read_dom` that doesn't find what it should, a replayed payload. No loop, no hypothesis. If none exists, write the smallest one that reproduces it (a test is the default; a `curl`\u002FDOM read is the fallback when the bug is only visible live) before reading another line of code.\n\n1. **Read the feedback completely**: the reviewer\u002FQA\u002Fpipeline comment on the task, the full error output, stack traces, exact files\u002Flines\u002Fmessages. They often contain the exact answer.\n2. **Reproduce consistently** in the task workspace with the loop from above: does it happen every time? Not reproducible → gather more data, don't guess.\n3. **Check recent changes**: git diff, recent commits on the task branch, config changes.\n4. **Stage\u002Fprod symptom** (a runtime error, not a local failure): before reading code, `get_environment` for the environment, `list_runtime_errors` with `new: true` to see whether the group started with the latest deploy, then `query_runtime_logs` with `text:` set to the error message. You hold these tools; use them before guessing from the code alone.\n5. **Multi-component systems** (API → service → database): add diagnostic logging at each component boundary — what enters, what exits — run once, and locate WHICH layer breaks before touching anything. Tag every line you add with a unique marker, e.g. `[DEBUG-a4f2]`, so cleanup is one `grep_code` for the tag before you finish — an untagged debug log left behind is a review finding.\n6. **Trace the bad value backward** from where the error appears to where it originates. Fix at the source, not at the symptom.\n\n### Phase 2 — Pattern analysis\n- Find working examples of the same pattern in the codebase (codebase_search, grep_code).\n- Read the reference implementation completely — don't skim.\n- List every difference between working and broken; don't assume \"that can't matter\".\n\n### Phase 3 — Hypothesis and testing\n- List 3–5 hypotheses, ranked by likelihood. Each must be falsifiable: \"If X is the cause, then changing Y will make the symptom disappear.\"\n- Test the top one with the SMALLEST possible change. One variable at a time.\n- Didn't work? Move to the next ranked hypothesis. Do NOT stack more fixes on top.\n\n### Phase 4 — Implementation\n1. Write a failing test that reproduces the issue (see tdd-workflow).\n2. Implement the single fix that addresses the root cause. No bundled refactoring.\n3. Verify: the test passes, no other test breaks, the original symptom is gone.\n4. Address EVERY point from the revision comment explicitly — partial fixes come straight back.\n\n## Was the test red before you started?\n\nBefore fixing a test you didn't write that's failing on your branch, check whether it failed on the base commit too: `git stash -u && \u003Cfocused test command>; git stash pop`. If it was already red there, it's pre-existing, not something your change broke.\n- **Small and adjacent to your change** → fix it in its own commit, separate from your feature commit.\n- **Otherwise** → one comment naming the test, the failure, and the base commit SHA: that's a blocker a person must see, not something to silently carry or silently fix.\n\nA regression that appeared somewhere in recent history (not clearly your change): `git bisect run \u003Cfocused test>` to find the exact commit before theorizing about the cause.\n\n## Test-failure triage\n\nA test fails on code you touched: decide, don't assume. Did your change touch what this test covers?\n- **Yes, and the test's expectation is still correct** → your code has a bug. Fix the code.\n- **Yes, and the behavior genuinely changed on purpose** → the test is outdated. Update it to match, and say so in your closing message — never weaken or delete it to make it pass without that explicit call.\n\n## When you don't know\n\nIf after Phase 1–3 you genuinely cannot identify the mechanism, say so plainly — \"I don't understand why X happens\" — rather than proposing a fix you don't believe in. Before declaring \"no root cause\": 95% of \"no root cause\" conclusions are incomplete investigation, so document exactly what you checked and where it dead-ended, add defensive handling\u002Flogging at the boundary you suspect, and say in your closing message what the next investigator should try first.\n\n## The 3-Fix Rule\n\nIf 3 fixes have failed, STOP. Each fix revealing a new problem elsewhere means the architecture or approach is wrong, not the code. Question the pattern — add a task comment describing the architectural concern instead of attempting fix #4.\n\n## Close\n\nThe root cause — not just \"fixed it\" — goes in your closing message: what broke, why, and the guard test that proves it. That message becomes the commit body the next debugger reads when this breaks again.\n\n## Red Flags — STOP and return to Phase 1\n\n- \"Quick fix for now, investigate later\"\n- \"Just try changing X and see if it works\"\n- \"It's probably X, let me fix that\"\n- Proposing solutions before tracing data flow\n- Multiple changes at once\n- \"One more fix attempt\" after 2+ failures\n- A debug log left in the diff without its `[DEBUG-xxxx]` tag removed\n\n## Common Rationalizations\n\n| Excuse | Reality |\n|--------|---------|\n| \"Issue is simple, no need for process\" | Simple issues have root causes too; the process is fast for them. |\n| \"Emergency, no time\" | Systematic debugging is faster than thrashing. |\n| \"I see the problem, let me fix it\" | Seeing symptoms is not understanding root cause. |\n| \"Multiple fixes at once saves time\" | You can't isolate what worked, and you create new bugs. |\n| \"I'll write the test after the fix works\" | Untested fixes don't stick. Test first proves it. |\n","# Root-Cause Debugging\n\n## Overview\n\nRandom fixes waste time and create new bugs. Quick patches mask underlying issues.\n\n**Core principle:** ALWAYS find the root cause before attempting fixes. Symptom fixes are failure.\n\n## The Iron Law\n\n```\nNO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST\n```\n\nUse this for ANY technical issue: a task returned to need_revision, a failing test, a red pipeline, unexpected behavior. Use it ESPECIALLY under time pressure — systematic is faster than guess-and-check thrashing.\n\n## The Four Phases\n\nComplete each phase before the next.\n\n### Phase 1 — Build a feedback loop, then investigate\n\nThis is the skill: before anything else, name ONE command you have already run that goes red on THIS symptom — a failing test, a `curl` against the running service, a `browser_read_dom` that doesn't find what it should, a replayed payload. No loop, no hypothesis. If none exists, write the smallest one that reproduces it (a test is the default; a `curl`\u002FDOM read is the fallback when the bug is only visible live) before reading another line of code.\n\n1. **Read the feedback completely**: the reviewer\u002FQA\u002Fpipeline comment on the task, the full error output, stack traces, exact files\u002Flines\u002Fmessages. They often contain the exact answer.\n2. **Reproduce consistently** in the task workspace with the loop from above: does it happen every time? Not reproducible → gather more data, don't guess.\n3. **Check recent changes**: git diff, recent commits on the task branch, config changes.\n4. **Stage\u002Fprod symptom** (a runtime error, not a local failure): before reading code, `get_environment` for the environment, `list_runtime_errors` with `new: true` to see whether the group started with the latest deploy, then `query_runtime_logs` with `text:` set to the error message. You hold these tools; use them before guessing from the code alone.\n5. **Multi-component systems** (API → service → database): add diagnostic logging at each component boundary — what enters, what exits — run once, and locate WHICH layer breaks before touching anything. Tag every line you add with a unique marker, e.g. `[DEBUG-a4f2]`, so cleanup is one `grep_code` for the tag before you finish — an untagged debug log left behind is a review finding.\n6. **Trace the bad value backward** from where the error appears to where it originates. Fix at the source, not at the symptom.\n\n### Phase 2 — Pattern analysis\n- Find working examples of the same pattern in the codebase (codebase_search, grep_code).\n- Read the reference implementation completely — don't skim.\n- List every difference between working and broken; don't assume \"that can't matter\".\n\n### Phase 3 — Hypothesis and testing\n- List 3–5 hypotheses, ranked by likelihood. Each must be falsifiable: \"If X is the cause, then changing Y will make the symptom disappear.\"\n- Test the top one with the SMALLEST possible change. One variable at a time.\n- Didn't work? Move to the next ranked hypothesis. Do NOT stack more fixes on top.\n\n### Phase 4 — Implementation\n1. Write a failing test that reproduces the issue (see tdd-workflow).\n2. Implement the single fix that addresses the root cause. No bundled refactoring.\n3. Verify: the test passes, no other test breaks, the original symptom is gone.\n4. Address EVERY point from the revision comment explicitly — partial fixes come straight back.\n\n## Was the test red before you started?\n\nBefore fixing a test you didn't write that's failing on your branch, check whether it failed on the base commit too: `git stash -u && \u003Cfocused test command>; git stash pop`. If it was already red there, it's pre-existing, not something your change broke.\n- **Small and adjacent to your change** → fix it in its own commit, separate from your feature commit.\n- **Otherwise** → one comment naming the test, the failure, and the base commit SHA: that's a blocker a person must see, not something to silently carry or silently fix.\n\nA regression that appeared somewhere in recent history (not clearly your change): `git bisect run \u003Cfocused test>` to find the exact commit before theorizing about the cause.\n\n## Test-failure triage\n\nA test fails on code you touched: decide, don't assume. Did your change touch what this test covers?\n- **Yes, and the test's expectation is still correct** → your code has a bug. Fix the code.\n- **Yes, and the behavior genuinely changed on purpose** → the test is outdated. Update it to match, and say so in your closing message — never weaken or delete it to make it pass without that explicit call.\n\n## When you don't know\n\nIf after Phase 1–3 you genuinely cannot identify the mechanism, say so plainly — \"I don't understand why X happens\" — rather than proposing a fix you don't believe in. Before declaring \"no root cause\": 95% of \"no root cause\" conclusions are incomplete investigation, so document exactly what you checked and where it dead-ended, add defensive handling\u002Flogging at the boundary you suspect, and say in your closing message what the next investigator should try first.\n\n## The 3-Fix Rule\n\nIf 3 fixes have failed, STOP. Each fix revealing a new problem elsewhere means the architecture or approach is wrong, not the code. Question the pattern — add a task comment describing the architectural concern instead of attempting fix #4.\n\n## Close\n\nThe root cause — not just \"fixed it\" — goes in your closing message: what broke, why, and the guard test that proves it. That message becomes the commit body the next debugger reads when this breaks again.\n\n## Red Flags — STOP and return to Phase 1\n\n- \"Quick fix for now, investigate later\"\n- \"Just try changing X and see if it works\"\n- \"It's probably X, let me fix that\"\n- Proposing solutions before tracing data flow\n- Multiple changes at once\n- \"One more fix attempt\" after 2+ failures\n- A debug log left in the diff without its `[DEBUG-xxxx]` tag removed\n\n## Common Rationalizations\n\n| Excuse | Reality |\n|--------|---------|\n| \"Issue is simple, no need for process\" | Simple issues have root causes too; the process is fast for them. |\n| \"Emergency, no time\" | Systematic debugging is faster than thrashing. |\n| \"I see the problem, let me fix it\" | Seeing symptoms is not understanding root cause. |\n| \"Multiple fixes at once saves time\" | You can't isolate what worked, and you create new bugs. |\n| \"I'll write the test after the fix works\" | Untested fixes don't stick. Test first proves it. |\n",{"name":5,"source":24,"category":25,"description":7},"obra\u002Fsuperpowers (MIT), adapted","quality","main","910394a0b6db9fc8c9a8f36328ec421d3ebd8b38","catalog\u002Fagents\u002Fmobile-developer\u002Fskills\u002Froot-cause-debugging",18,"https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper","https:\u002F\u002Ftasktrooper.ai","https:\u002F\u002Fgithub.com\u002Fmakifbaysal","Senior Software Developer","2026-11-15 04:50:29",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add makifbaysal\u002Ftasktrooper --skill root-cause-debugging",{"tool":41,"command":42},"bunx","bunx skills add makifbaysal\u002Ftasktrooper --skill root-cause-debugging",{"tool":44,"command":45},"pnpm","pnpm dlx skills add makifbaysal\u002Ftasktrooper --skill root-cause-debugging","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fmobile-developer\u002Fskills\u002Froot-cause-debugging\u002FSKILL.md",true,[],[50,56,63,70,77,84],{"skillNo":51,"name":52,"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":53,"categories":54,"keywords":55,"publishedAt":19},"01M7CSVEPQW6J6TD6CS2T5FPNZ","visual-craft","https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fui-designer\u002Fskills\u002Fvisual-craft\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7CSVAQG91ETHQ0HBNZDG5FR","ux-copy","Use when you write any words a user reads in a mockup or a hand-off - content language and voice, buttons, labels, errors, empty states, confirmations, numbers and dates, and the longest-string check","https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fui-designer\u002Fskills\u002Fux-copy\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7CSV6H0J38659NDXHJQ8396","screen-mockup-html","Use when you draw screens as the design task's HTML mockup - ONE canvas document holding every screen and every variant side by side, the sanitizer-safe recipe, phone and wide frames, the states grid, static control states, and the loopback self-check with screenshots at 375, 768 and 1440 attached to the task","https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fui-designer\u002Fskills\u002Fscreen-mockup-html\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7CSV3JFRF3BM3XK52M7YEYR","performance-awareness","How the performance score moves for your role. Use when the score context shows a declining trend, or before handing off work you have not self-checked against every criterion.","https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fui-designer\u002Fskills\u002Fperformance-awareness\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7CSTZDH00YRF5SCT7BRT9QD","design-variants","Use when a screen design needs variants - how many, variants as side-by-side rows on the one canvas, what makes two variants genuinely different, recommending one, how the human's choice is read, and narrowing to the chosen one in revision","https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fui-designer\u002Fskills\u002Fdesign-variants\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7CSTV6P3SM3PAE28DB0RF77","design-system-authoring","Use when you derive, change or extend a design system - where tokens live per stack, the DTCG token tree, role-based names for both themes, base vs layer vs drift, the DESIGN.md section order, the inventory format, the contrast check and the lint every proposal returns","https:\u002F\u002Fgithub.com\u002Fmakifbaysal\u002Ftasktrooper\u002Fblob\u002Fmain\u002Fcatalog\u002Fagents\u002Fui-designer\u002Fskills\u002Fdesign-system-authoring\u002FSKILL.md",[],[]]