debug-fix
Skill1 starsChanged 5 months agoMITView on GitHub
Root-cause a bug and fix it at the cause, not with a workaround — reproduce, isolate, apply the minimal fix, and prove it with a failing-then-passing test. Use when something is broken, throwing, or behaving wrong. Trigger phrases "debug this", "fix this bug", "why is this failing".
3 other projects use a version of this.
Adopted by
Most recently taken up by
- krishnamallam/upboxtheir own version, first seen Oct 11, 2026
- poshan0126/dotclaudetheir own version, first seen Oct 8, 2026
- zebbern/termstacktheir own version, first seen Apr 16, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- poshan0126/dotclaude★ 871same name
- zebbern/termstack★ 4same name
- krishnamallam/upbox★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository16 other files it gives its agents.
- catchupSkill
- claude-mdSkill
- context-budgetSkill
- db-querySkill
- eval-agentSkill
- explainSkill
- fix-issueSkill
- incident-ruleSkill
- pr-reviewSkill
- refactorSkill
- secrets-checkSkill
- setup-projectSkill
- shipSkill
- tddSkill
- test-writerSkill
- trace-agentSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 34
Prove it: Run the failing test — it now passes.
- Distinctive: line 39
If the fix reveals a deeper design problem, name it and offer to file a follow-up — don't silently expand scope.
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
debug-fix
Trigger: "debug this" / "fix this bug" / "why is this failing"
Standing rules: ../_conventions.md.
Fix the root cause, never a symptom. No workaround that hides the problem, no adjacent refactor, no scope creep. Prove the fix with a test that fails before and passes after. Never guess at the cause — reproduce it.
Steps
- Reproduce first. Get a deterministic repro: the exact command, input, or test that triggers it. Capture the real error output (full traceback for Python). If you can't reproduce it, STOP and say so — do not fix by guessing.
- Isolate. Narrow to the smallest failing unit. Read the traceback bottom-up to the first frame in our code. Add a focused failing test (or a temporary assert/print) that pins the exact wrong behavior. Confirm the test fails for the right reason.
- Find the cause, state it. Name the root cause in one sentence with
file:lineevidence — not the symptom. If two readings are possible, say which one you're acting on and why. Don't proceed on a hunch. - Minimal fix at the cause. Change the smallest thing that fixes the root cause. No swallowing the error to make it quiet. No touching unrelated code.
- Prove it. Run the failing test — it now passes. Run the surrounding test file (not the whole suite, for speed) to confirm no regression. Show the before/after.
- Report (terse): root cause · the one-line fix · test that now guards it. If the fix reveals a deeper design problem, name it and offer to file a follow-up — don't silently expand scope.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.