Help us improve
Share bugs, ideas, or general feedback.
From 9arm-skills
Guides debugging sessions with a four-step discipline: reproduce reliably, trace fail path, falsify hypotheses, cross-reference breadcrumbs. Activates on bug reports, error logs, or stack traces.
npx claudepluginhub thananon/9arm-skillsHow this skill is triggered — by the user, by Claude, or both
Slash command
/9arm-skills:debug-mantraThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Four-step discipline for any debug session. Recite verbatim, then apply in order.
Systematic debugging methodology using Zeller's scientific method: reproduce, hypothesize via binary search, isolate root cause, fix with regression test.
A structured debugging protocol with steps to reproduce, isolate, hypothesize, verify, and fix issues. Useful for systematic root cause analysis and avoiding random changes.
Forces a scientific-method loop (Observe → Hypothesize → Experiment → Conclude) to debug non-trivial bugs. Prevents guessing by ensuring evidence before fixes.
Share bugs, ideas, or general feedback.
Four-step discipline for any debug session. Recite verbatim, then apply in order.
Mantra:
- First is reproducibility. Can the issue be reproduced reliably?
- Know the fail path. Debugger first; then source trace + knob enumeration; then in-code instrumentation.
- Question your hypothesis. What would disprove it?
- Every run is a breadcrumb. Cross-reference all of them.
Then begin work.
Build a runnable repro before anything else.
Target: a fast (1–5 s), deterministic pass/fail signal. Pin time, seed the RNG, freeze network, isolate filesystem.
Once reproducible, find where the code breaks and what stops it from breaking. The differential narrows the search. Try in this order — escalate only when the prior tactic fails.
printf / log statements at the suspected fail site, dump the relevant internal state. Tag every probe with a unique prefix (e.g. [DBG-a4f2]) so cleanup is a single grep. Let the trace show where reality diverges from your model.When a candidate root cause surfaces, scrutinise it before testing it.
Maintain a running ledger of every experiment in this session. Each entry: what changed, what happened, what it ruled in or out.