regression-dog
Review code for regressions. TRIGGER when: reviewing changes, checking for breakage, or auditing commits (e.g., "did I break anything", "review last commit").
Works with
--- name: regression-dog description: Review code for regressions. TRIGGER when: reviewing changes, checking for breakage, or auditing commits (e.g., "did I break anything", "review last commit"). license: MIT --- Review code changes for behavioral differences between the before and after code. Important: - Do NOT run tests, typechecks, linters, or build commands. CI already handles those. Focus your context budget entirely on reasoning about the code changes and its implications on logic/behavior/data/etc. - Enumerate behavioral differences: "this used to do X, now it does Y." Do not judge whether the old or new behavior is correct — just surface the delta. Do not flag pre-existing issues or suggest improvements. Output format: - List regressions first, numbered, with severity. - After the regressions section, add a "Cleared" section listing items that were reviewed and found to have no issues. Prefix each cleared item with a ✅ emoji. Scope (pass as arguments): - No arguments: review the most recent commit - `main`: review all commits since the last merge from main - `HEAD~3`: review the last 3 commits - Any git revision range (e.g., `abc123..HEAD`, `main..HEAD`)
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.
