debug-investigation
Skill3 starsChanged 17 days agoNo licenceView on GitHub
Runs a disciplined, evidence-driven investigation to reproduce a bug, identify its root cause, and deliver a minimal verified fix. You MUST use this before touching any code in response to a bug, an error, a crash, a failing or flaky test, a regression, or anything described as not working, including one-line fixes and changes that look like an obvious typo: the hard gate (no fix without a reproduction and an identified root cause) applies however simple the fix looks. Enforces scope discipline, the investigation budget, and the minimal fix principle, and takes its own approval for the fix approach so bugs do not go through the design step.
In this repository12 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- design-committeeSkill
- design-dialogueSkill
- design-handoffSkill
- design-recoverySkill
- design-reviewSkill
- review-branchSkill
- work-review-receiveSkill
- work-review-requestSkill
- work-swarmSkill
- work-tddSkill
- work-verificationSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
20 rules. About 0 are common, 18 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈18
Distinctive · estimate
This author's own choices. Worth a look.
2
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 350,495 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.