debug
Debugs production issues by reproducing bugs, running 5 Whys root cause analysis, and writing verifying test cases. Use when investigating a bug or production incident.
Works with
--- name: debug description: Debugs production issues by reproducing bugs, running 5 Whys root cause analysis, and writing verifying test cases. Use when investigating a bug or production incident. license: MIT --- # Production Debugging Skill **Use Case:** Investigating production issues, reproducing bugs from ticket information, and planning test cases. ## Core Debugging Workflow ### Phase 1: Understand & Reproduce 1. **Intake:** Gather error logs, user reports, and environment details (Browser, OS, Staging/Prod). 2. **Reproduce:** Replicate the exact conditions. Write failing test cases to prove the bug exists before touching any application code. - *If Frontend:* Look for race conditions in React hooks, stale closures, missing keys, or CORS. - *If Backend:* Look for N+1 queries, missing indexes, race conditions, or null reference errors. ### Phase 2: Root Cause Analysis (5 Whys) Do not just patch the error. Determine *why* it happened. - Why did the variable evaluate to null? - Why did the database allow a null value? - Why was validation missing? ### Phase 3: The Fix - Write the application code to fix the root cause. - Ensure the failing test written in Phase 1 now passes. - Assess performance impact (e.g., does this require a slow database migration?). ### Output Format When handling a debugging task, structure your response as follows: ```markdown ## 🔍 Debug Session ### Issue Summary [Brief description of the bug] ### Root Cause Hypothesis [Your technical explanation of what is breaking] ### Action Plan 1. [ ] Replicate via automated test 2. [ ] Apply application fix 3. [ ] Verify test passes ```
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.

