debug
Find and fix the root cause when something breaks: a failing test, a broken build, a bug report, or behavior that doesn't match expectations.
Works with
Agent Skills format with YAML frontmatter. Claude Code reads it as-is.
--- name: "debug" description: "Find and fix the root cause when something breaks: a failing test, a broken build, a bug report, or behavior that doesn't match expectations." license: "MIT" --- # Debug 1. Reproduce the failure. If you cannot, keep gathering information and report what you observed. 2. Trace it to the root cause and explain why it happens. 3. Add a small failing regression test when practical, then make the smallest fix that passes it. If no useful test is practical, say why and verify another way. 4. Run relevant checks. Report the cause, the fix, how it was verified, and anything still unexplained. ## Rules - Fix the cause, not the symptom. Do not delete the failing check, swallow the error, or weaken the assertion unless that is the real fix. - One bug at a time. - Do not pull unrelated failures or flaky infrastructure into the task. - Stop when the fix needs a product or code-owner decision.
More Debugging skills
diagnosing-bugs
mattpocock/skills
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
explore-code
lllllllama/rigorpilot-skills
Rigor Improve implementation leaf skill for auditable candidate implementation in deep learning research repositories. Use when the researcher explicitly authorizes exploratory work on an isolated branch or worktree to transplant modules, adapt a backbone, add LoRA or adapter layers, replace a head, or stitch together meaningful low-risk migration ideas with rollback-aware records in explore_outputs/. Do not use for end-to-end exploration orchestration on top of current_research, trusted baseline reproduction, conservative debugging, environment setup, verified contribution claims, or default repository analysis.
safe-debug
lllllllama/rigorpilot-skills
Rigor Debug / Rigor Audit skill for deep learning research work. Use when the user pastes a traceback, terminal error, CUDA OOM, checkpoint load failure, shape mismatch, NaN loss symptom, or training failure and wants conservative diagnosis before any patching, with debug fixes clearly separated from research contributions. Do not use for broad refactoring, speculative adaptation, automatic exploratory patching, or general repository familiarization.
