fg-debug
Skill6 starsChanged 10 days agoNo licenceView on GitHub
Conversational diagnosis for hard bugs and performance regressions, vendored from mattpocock/skills diagnosing-bugs. Build a red-capable loop, reproduce and minimise, rank hypotheses with the human, then instrument. Diagnosis only — an active verified failure returns to fg-run fix-and-re-run; an independent diagnosis routes a trivial fix to fg-quick or an approved non-trivial fix to a new plan. Always skipped in fg-next all / fg-loop. Use for 'debug this', 'diagnose', '디버깅해줘', '버그 잡아줘', '왜 안 되지', '왜 느리지'.
In this repository27 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- issue-triageSkill
- fg-adversarial-reviewSkill
- fg-agendaSkill
- fg-agentsSkill
- fg-askSkill
- fg-cleanupSkill
- fg-configSkill
- fg-doctorSkill
- fg-doneSkill
- fg-dropSkill
- fg-helpSkill
- fg-learnSkill
- fg-loopSkill
- fg-mapSkill
- fg-mergeSkill
- fg-monitorSkill
- fg-nextSkill
- fg-quickSkill
- fg-rulesSkill
- fg-runSkill
- fg-securitySkill
- fg-showmeSkill
- fg-statuslineSkill
- fg-statusSkill
- fg-verifySkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
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.

