fix-exploratory-debugging
Debug hard or unclear bugs with time-boxed hypothesis charters — bisect, minimize, instrument, compare working and broken states — and stop to escalate after repeated failed theories. Use when the root cause is not obvious after reading the trace.
71
89%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Passed
No findings from the security scan
Exploratory Debugging Charters
Each charter is 20–30 minutes: "Test hypothesis using to explain ."
Methods
git bisectbetween a known-good and the broken commit.- Minimize: shrink the input or steps until the bug still appears.
- Compare: diff the working state (other user, other browser, older record) against the broken one.
- Instrument: temporary logs with a correlation ID; remove them before commit.
- Isolate: stub one dependency at a time.
Rules
- Write the hypothesis before testing it, and the result after.
- After 3 failed hypotheses, stop and report what's ruled out; ask the tester for more evidence.
- Never commit a change "to see if it helps" to the fix branch.
Exit criteria
A confirmed root cause with evidence, or an escalation note listing the hypotheses ruled out.
Counterpart of tester skill: qa-exploratory-charters.
- Repository
itsablabla/qa-bug-agent-skills
- Revision
9a6f628
- Last updated
- First committed
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.