dev-debug
Skill1 starsChanged 14 days agoMITView on GitHub
Diagnose bugs, failing tests, crashes, regressions, and unexplained behavior whose cause is not yet known, before proposing a fix. Use when there is an observed failure or mismatch. Skip it when the report or one read of the named code already shows the cause (fix and verify directly), for spacing, size or color fixes, and for ordinary feature implementation.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- codeaholicguy/ai-devkittheir own version, first seen Oct 25, 2026
- browseros-ai/BrowserOS-agenttheir own version, first seen Oct 8, 2026
- amjadjibon/skillstheir own version, first seen Jul 12, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- codeaholicguy/ai-devkit★ 1.7ksame name
- browseros-ai/BrowserOS-agent★ 50same name
- amjadjibon/skills★ 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 repository14 other files it gives its agents.
- .agents/AGENTS.mdAGENTS.md
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- dev-debugSkill
- dev-planSkill
- dev-reviewSkill
- dev-ui-verifySkill
- dev-verifySkill
- project-contextSkill
- dev-planSkill
- dev-reviewSkill
- dev-ui-verifySkill
- dev-verifySkill
- project-contextSkill
The file
We split this skill into the rules it gives an agent
9 rules. 0 are common, 7 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
7
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Read the actual error, trace, or output.
- Distinctive: line 15
Check relevant recent changes, configuration, and environment differences.
- Distinctive: line 17
If reproduction is unreliable, gather more evidence instead of guessing.
- Distinctive: line 29
Check configuration, lifecycle, async/concurrency, retry, and cleanup assumptions.
- Distinctive: line 34
Test one variable at a time with the smallest useful experiment.
- Distinctive: line 35
If it fails, return to evidence.
- Very specific: line 41
Add a regression test when it meaningfully protects behavior.
- Very specific: line 45
Use dev-verify and specifically verify the original symptom or regression test.
- Distinctive: line 46
If several distinct hypotheses fail and reveal deeper coupling, reassess architecture instead of adding fallback layers.
“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
Systematic Debugging
Fix causes, not symptoms.
1. Establish evidence
- Read the actual error, trace, or output.
- Reproduce the failure when practical.
- Record the smallest reliable trigger.
- Check relevant recent changes, configuration, and environment differences.
If reproduction is unreliable, gather more evidence instead of guessing.
2. Localize the failing boundary
For multi-component flows inspect boundaries in order: input → caller → service/API → persistence/external dependency → output. Determine the earliest boundary where actual behavior diverges from expected behavior. Trace bad values backward until their source is identified.
3. Compare with working patterns
Find the closest working path in the same repository. List meaningful differences before editing. Check configuration, lifecycle, async/concurrency, retry, and cleanup assumptions.
4. Form one hypothesis
State a concrete causal hypothesis: X causes the failure because evidence Y shows divergence at boundary Z. Test one variable at a time with the smallest useful experiment. If it fails, return to evidence. Do not stack speculative fixes.
5. Implement the narrowest correct fix
Fix where incorrect state or decision originates. Avoid unrelated refactoring. Add a regression test when it meaningfully protects behavior; do not manufacture tests for trivial copy/style/static guarantees.
6. Verify
Use dev-verify and specifically verify the original symptom or regression test.
If several distinct hypotheses fail and reveal deeper coupling, reassess architecture instead of adding fallback layers.
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.