| name | debugging |
| description | Systematic debugging workflow for diagnosing and fixing bugs, errors, and unexpected behavior. Use when investigating failures, reading stack traces, reproducing issues, root-causing regressions, or when the cause of a problem is unknown. Applies structured hypothesis-driven debugging before patching. |
On-demand loading: Read this skill only when the task clearly matches the description above. Do not load for unrelated work.
Debugging (Quick Triage Router)
Fast first pass before patching. For the full systematic workflow (iron law, four phases, escalation after 3+ failed fixes), read skills/systematic-debugging/SKILL.md and its references/ docs.
When to use
- An error, crash, or unexpected behavior needs initial triage
- A test is failing and you need a quick read of the symptom before deep investigation
- You want a compact checklist before routing to
systematic-debugging
Quick-triage checklist
- Read the full error — type, message, file:line, stack trace bottom-to-top
- Confirm reproduction — exact inputs, environment, intermittent vs consistent
- Narrow scope — read the failing function/file first; expand only when needed
- State 2–3 hypotheses ranked by likelihood — do not edit until you have them
- Route — if root cause is unclear or fixes have already failed, switch to
systematic-debugging
References
| File | Contents |
|---|
references/common-patterns.md | Stack overflow, null refs, races, wrong data, env/CI failures, debug report template |
Related skills
systematic-debugging — full phase-gated root-cause workflow (prefer when triage is insufficient)test-driven-development — write a failing repro test before fixing
