bug
Skill1 starsChanged 38 days agoMITView on GitHub
Investigate, reproduce, diagnose, fix, and verify software bugs with evidence-backed reasoning.
14 other projects use a version of this.
Adopted by
Most recently taken up by
- retospect/precis-mcptheir own version, first seen Nov 15, 2026
- ccch1mneyyy/dsh-Gotheir own version, first seen Nov 15, 2026
- SatanshuMishra/interphasetheir own version, first seen Nov 15, 2026
- yicheng47/runnertheir own version, first seen Nov 13, 2026
- paulocsb/worldcup-fifa-pooltheir own version, first seen Nov 8, 2026
- jisuzzzz/haechitheir own version, first seen Nov 8, 2026
Used with
Projects with it also use init and audit.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
MicrosoftSkillinit
Also in 3 projects that use this
OpenAISkillaudit
Audit or critique a product flow, journey, workflow, funnel, onboarding path, checkout path, settings path, screen, or multi-step product experience by capturing screenshots first, then reporting UX, design, and accessibility findings inline from that evidence. Use Figma only when the user explicitly asks for a board. Use when the user asks to audit, review, critique, inspect, assess, analyze, evaluate, or give feedback on a product experience.
Also in 3 projects that use this
Other versions14 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 14
- ccch1mneyyy/dsh-Go★ 24ksame name
- ccch1mneyyy/dsh-TUI★ 7.8ksame name
- me2resh/apexyard★ 542same name
- yicheng47/runner★ 519same name
- ulises-jeremias/agent-toolkit★ 20same name
- jisuzzzz/haechi★ 17same name
- jamillazarev/multica-ops★ 11same name
- retospect/precis-mcp★ 11same name
- savinofiore/lexi★ 4same name
- marcuskrogh/skills★ 1same name
4 more not listed
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 repository6 other files it gives its agents.
- AGENTS.mdAGENTS.md
- templates/AGENTS.mdAGENTS.md
- architectureSkill
- code-reviewSkill
- featureSkill
- releaseSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 11 edited versions we read keep these.
3
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 18
Run concrete experiments and keep receipts for the observed results.
- Distinctive: line 22
Add or update regression protection.
- Distinctive: line 24
Document root cause, resolution classification, regression evidence, and verification.
“Common” is measured: kept by at least 6 in 10 of the 11 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
Bug Skill
Purpose
Investigate and resolve software defects systematically without confusing plausible explanations with demonstrated causes.
Process
- Understand the reported symptom, expected behavior, actual behavior, environment, and reproduction steps.
- Establish one concrete reproduction signal before changing source.
- Record the pre-fix observation that demonstrates the defect.
- Form explicit falsifiable hypotheses. Each hypothesis needs a prediction and a falsifier.
- Run concrete experiments and keep receipts for the observed results.
- Mark root cause CONFIRMED only when supported by the experiment evidence. Otherwise keep it UNCONFIRMED.
- Distinguish an actual REPAIR from a WORKAROUND. Never silently label symptom suppression as repair.
- Determine affected components and implement the smallest appropriate authorized change.
- Add or update regression protection.
- Replay the exact frozen reproduction signal after the change.
- Document root cause, resolution classification, regression evidence, and verification.
Evidence Rules
- "I reproduced it" is not sufficient without an observable signal or procedure.
- A hypothesis that was not tested is not a confirmed cause.
- A regression check that already passed before the fix is not primary proof that the fix resolved the bug.
- For automated repairs, the same reproduction signal used before the change must be replayed after the change.
- Provider statements are reasoning; runtime receipts are execution evidence.
- Operational inability to investigate must not be confused with a product defect.
Output
Reproduction evidence, falsifiable hypotheses, experiment receipts, evidence-backed root cause, REPAIR or WORKAROUND classification, implemented change, regression protection, and same-signal post-fix verification.
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.

