[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ATHNJ7A1YQW3T2SECYYMSS":3,"skill-same:01M7ATHNJ7A1YQW3T2SECYYMSS":50},{"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":29,"commitSha":30,"skillDirectory":31,"forksCount":14,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":34,"ownerDescription":6,"updatedAt":35,"install":36,"resources":49},"01M7ATHNJ7A1YQW3T2SECYYMSS","systematic-debugging",null,"Root-cause-first discipline for any bug, failing test, build failure, or unexpected behaviour. Use before proposing any fix, especially under time pressure or after a previous fix did not hold. Reproduces, traces the bad value to its origin, compares against working code, tests one hypothesis at a time, and stops to question the design after three failed fixes.","coltonbearden\u002Fawakened","coltonbearden","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F208834784?v=4","01M7ATATS86H87M6N7DGFWJXWA","Colton Bearden","01M7ATATSYZ652XPQKRKYQ3Q3P",0,"MIT","https:\u002F\u002Fgithub.com\u002Fcoltonbearden\u002Fawakened\u002Fblob\u002Fmain\u002Fplugins\u002Fsuper-saiyan\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: systematic-debugging\ndescription: Root-cause-first discipline for any bug, failing test, build failure, or unexpected behaviour. Use before proposing any fix, especially under time pressure or after a previous fix did not hold. Reproduces, traces the bad value to its origin, compares against working code, tests one hypothesis at a time, and stops to question the design after three failed fixes.\nallowed-tools: [Read, Grep, Glob, Edit]\n---\n\n# Systematic Debugging\n\n## Purpose\n\nA fix applied before the cause is understood is a guess, and guesses compound. This skill orders the work so that\nthe fix comes last: understand, compare, hypothesize, then change one thing. It contains the tracing and bisection\nprocedures inline so nothing needs a script. It does not build the reproduction harness — `diagnosing-bugs` covers\nthat when a bug resists a simple repro — and it hands the fix itself to `test-driven-development`.\n\n## Trigger Conditions\n\nUse this skill for test failures, production bugs, build breaks, integration failures, performance problems, and\nany behaviour that does not match expectation. Use it most deliberately when the fix \"seems obvious\", when time is\nshort, and when earlier fixes did not work.\n\nDo not skip it because the bug looks simple; simple bugs have root causes and the process is fast for them.\n\n## Workflow\n\n1. Investigate before touching anything. Read the full error and stack trace; note file, line, and code. Reproduce\n   the failure on demand with exact steps — if it cannot be reproduced, gather more evidence rather than guessing.\n   Check what changed recently: diff, commits, dependency and configuration changes, environment differences.\n2. Trace the bad value to its origin. Start at the failure and walk backwards: what produced this value, what\n   called that, what supplied its input. Continue until the first place the data is wrong. The fix belongs there,\n   not where the symptom surfaced. In a multi-component path, log what enters and leaves each boundary once, run\n   once, and read where the data first goes wrong before reasoning further.\n3. Compare against something that works. Find similar code in the same codebase that behaves correctly, or read the\n   reference implementation completely. List every difference, including the ones that \"cannot matter\". Note the\n   dependencies, configuration, and assumptions the broken path relies on.\n4. Form one hypothesis and state it: \"the cause is X because Y\". Test it with the smallest possible change, one\n   variable at a time. If it does not hold, form a new hypothesis; do not stack a second change on the first.\n5. Fix through a failing test. Write the smallest reproduction as a test, watch it fail, apply one change at the\n   root cause, watch it pass, and run the surrounding suite. No bundled refactoring, no unrelated improvements.\n6. Count the attempts. After a second failed fix, return to step 1 with what was learned. After a third, stop:\n   when each fix reveals coupling in a new place, the design is the problem. Say so and discuss it with the user\n   before trying a fourth.\n7. Report the cause. State what the root cause was, how it was confirmed, and what the fix changed, so the next\n   reader learns from it.\n\n## Isolating a Polluting Test\n\nWhen a suite fails or leaves state behind only in combination, bisect the test set instead of reading every test.\nConfirm the polluted state is absent, run the first half of the test files, and check whether it appeared. Keep\nthe half that produced it and split again until one file remains; then apply the same halving inside that file's\ntests. Each round takes one run, so even a large suite yields the culprit in a handful of runs. Record the pair\n(polluter, victim) in the fix commit.\n\n## Red Flags\n\nStop and return to step 1 when you notice any of: \"quick fix now, investigate later\"; \"just try changing X\"; several\nchanges made before one test run; a fix proposed before the data flow was traced; a sentence beginning \"it is\nprobably\"; and the user asking \"is that not happening?\" or \"stop guessing\".\n\n## When No Root Cause Emerges\n\nIf the investigation genuinely ends at something environmental, timing-dependent, or external, document what was\nexamined, handle the condition explicitly (a bounded retry, a timeout, a clear error), and add the logging that\nwould answer the question next time. Most \"no root cause\" verdicts are an investigation that stopped early.\n\n## Safety Checks\n\n- Bash runs the project's own tests and read-only git commands; no installation, no network.\n- Temporary diagnostic output carries a unique tag so a single search removes it before the work is reported.\n- Redact secrets from any output shown; name their location and kind instead.\n\n## Output Contract\n\nReproduction steps, the traced origin of the fault, the hypothesis and how it was tested, the failing-then-passing\ntest, the single change made, and the suite result.\n","# Systematic Debugging\n\n## Purpose\n\nA fix applied before the cause is understood is a guess, and guesses compound. This skill orders the work so that\nthe fix comes last: understand, compare, hypothesize, then change one thing. It contains the tracing and bisection\nprocedures inline so nothing needs a script. It does not build the reproduction harness — `diagnosing-bugs` covers\nthat when a bug resists a simple repro — and it hands the fix itself to `test-driven-development`.\n\n## Trigger Conditions\n\nUse this skill for test failures, production bugs, build breaks, integration failures, performance problems, and\nany behaviour that does not match expectation. Use it most deliberately when the fix \"seems obvious\", when time is\nshort, and when earlier fixes did not work.\n\nDo not skip it because the bug looks simple; simple bugs have root causes and the process is fast for them.\n\n## Workflow\n\n1. Investigate before touching anything. Read the full error and stack trace; note file, line, and code. Reproduce\n   the failure on demand with exact steps — if it cannot be reproduced, gather more evidence rather than guessing.\n   Check what changed recently: diff, commits, dependency and configuration changes, environment differences.\n2. Trace the bad value to its origin. Start at the failure and walk backwards: what produced this value, what\n   called that, what supplied its input. Continue until the first place the data is wrong. The fix belongs there,\n   not where the symptom surfaced. In a multi-component path, log what enters and leaves each boundary once, run\n   once, and read where the data first goes wrong before reasoning further.\n3. Compare against something that works. Find similar code in the same codebase that behaves correctly, or read the\n   reference implementation completely. List every difference, including the ones that \"cannot matter\". Note the\n   dependencies, configuration, and assumptions the broken path relies on.\n4. Form one hypothesis and state it: \"the cause is X because Y\". Test it with the smallest possible change, one\n   variable at a time. If it does not hold, form a new hypothesis; do not stack a second change on the first.\n5. Fix through a failing test. Write the smallest reproduction as a test, watch it fail, apply one change at the\n   root cause, watch it pass, and run the surrounding suite. No bundled refactoring, no unrelated improvements.\n6. Count the attempts. After a second failed fix, return to step 1 with what was learned. After a third, stop:\n   when each fix reveals coupling in a new place, the design is the problem. Say so and discuss it with the user\n   before trying a fourth.\n7. Report the cause. State what the root cause was, how it was confirmed, and what the fix changed, so the next\n   reader learns from it.\n\n## Isolating a Polluting Test\n\nWhen a suite fails or leaves state behind only in combination, bisect the test set instead of reading every test.\nConfirm the polluted state is absent, run the first half of the test files, and check whether it appeared. Keep\nthe half that produced it and split again until one file remains; then apply the same halving inside that file's\ntests. Each round takes one run, so even a large suite yields the culprit in a handful of runs. Record the pair\n(polluter, victim) in the fix commit.\n\n## Red Flags\n\nStop and return to step 1 when you notice any of: \"quick fix now, investigate later\"; \"just try changing X\"; several\nchanges made before one test run; a fix proposed before the data flow was traced; a sentence beginning \"it is\nprobably\"; and the user asking \"is that not happening?\" or \"stop guessing\".\n\n## When No Root Cause Emerges\n\nIf the investigation genuinely ends at something environmental, timing-dependent, or external, document what was\nexamined, handle the condition explicitly (a bounded retry, a timeout, a clear error), and add the logging that\nwould answer the question next time. Most \"no root cause\" verdicts are an investigation that stopped early.\n\n## Safety Checks\n\n- Bash runs the project's own tests and read-only git commands; no installation, no network.\n- Temporary diagnostic output carries a unique tag so a single search removes it before the work is reported.\n- Redact secrets from any output shown; name their location and kind instead.\n\n## Output Contract\n\nReproduction steps, the traced origin of the fault, the hypothesis and how it was tested, the failing-then-passing\ntest, the single change made, and the suite result.\n",{"name":5,"description":7,"allowed-tools":24},[25,26,27,28],"Read","Grep","Glob","Edit","main","b192e49d15e524b1a88cd89bc42ed677c1019c9f","plugins\u002Fsuper-saiyan\u002Fskills\u002Fsystematic-debugging","https:\u002F\u002Fgithub.com\u002Fcoltonbearden\u002Fawakened","https:\u002F\u002Fgithub.com\u002Fcoltonbearden","https:\u002F\u002Fcoltonbearden.com\u002F","2026-09-25 06:56:45",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add coltonbearden\u002Fawakened --skill systematic-debugging",{"tool":42,"command":43},"bunx","bunx skills add coltonbearden\u002Fawakened --skill systematic-debugging",{"tool":45,"command":46},"pnpm","pnpm dlx skills add coltonbearden\u002Fawakened --skill systematic-debugging","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcoltonbearden\u002Fawakened\u002Fblob\u002Fmain\u002Fplugins\u002Fsuper-saiyan\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",true,[],[51,58,65,72,79,86],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":19},"01M7ATJM35P1TKP3CPE240A8KY","good-skill","Fixture - a skill whose name equals its directory and whose description clears the forty-character floor (N-2).","https:\u002F\u002Fgithub.com\u002Fcoltonbearden\u002Fawakened\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fgood-skill\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M7ATJJYPD2HBMA6H5KQ28YNM","wrong-name","Too short.","https:\u002F\u002Fgithub.com\u002Fcoltonbearden\u002Fawakened\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fbad-skill\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7ATJG19YSBW0PZCP9YN2S0K","\u003Cskill-name>","\u003CWhat the skill does, then the situations that should trigger it. Concrete and situational, third person, never marketing. Minimum 40 characters — this text is the auto-invocation surface (N-2).>","https:\u002F\u002Fgithub.com\u002Fcoltonbearden\u002Fawakened\u002Fblob\u002Fmain\u002Ftemplates\u002Fskill.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7ATJCEBSD2HYJAC4BE22AR1","writing-plans","Turns an agreed design or spec into a step-by-step implementation plan that an engineer with no context could execute. Use when a multi-step change is understood well enough to sequence but no plan exists yet, before touching code. Produces a plan file with exact paths, test-first steps, interfaces between tasks, and no placeholders.","https:\u002F\u002Fgithub.com\u002Fcoltonbearden\u002Fawakened\u002Fblob\u002Fmain\u002Fplugins\u002Fsuper-saiyan\u002Fskills\u002Fwriting-plans\u002FSKILL.md",[],[],{"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":85,"publishedAt":19},"01M7ATJ8AF6T9VWJH3NXY5QRS7","verification-before-completion","Gate that runs before any claim that work is done, fixed, passing, or shipped. Identifies the command that would prove the claim, runs it fresh, reads the whole output, and only then reports — with the evidence attached and any gap stated. Use before committing, opening a pull request, marking a task complete, or telling the user something works.","https:\u002F\u002Fgithub.com\u002Fcoltonbearden\u002Fawakened\u002Fblob\u002Fmain\u002Fplugins\u002Fsuper-saiyan\u002Fskills\u002Fverification-before-completion\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7ATJ2AAB7VS5AVNPT6E9YNQ","using-skills","Session discipline that fires before the first action of any task. Checks whether an installed skill or command already covers the job, keeps every action inside the requested scope, and reports verification as evidence rather than confidence. Use at the start of a conversation, before answering a question, before exploring a codebase, and whenever a task changes shape mid-session.","https:\u002F\u002Fgithub.com\u002Fcoltonbearden\u002Fawakened\u002Fblob\u002Fmain\u002Fplugins\u002Fsuper-saiyan\u002Fskills\u002Fusing-skills\u002FSKILL.md",[],[]]