regression-test
Use when the main task is to create a failing or proving regression test for a reported bug or edge case
Works with
--- name: regression-test description: Use when the main task is to create a failing or proving regression test for a reported bug or edge case license: Apache-2.0 --- <!-- GENERATED — DO NOT EDIT: generated by ai-kit installer from packages/ai-universal-rules/templates. --> ## What I Do I add the narrowest practical regression test or deterministic reproduction for a reported bug or edge case. ## When To Use Me - when the most important outcome is a focused regression test - when a reproduction step is needed before a fix - when proving an edge case with a deterministic assertion ## Do Not Use Me For - broad refactors or feature implementation - cases where the fix should be combined with the test in one pass (use bug-regression instead) ## Workflow 1. identify the smallest useful proving surface 2. add the narrowest practical test or reproduction 3. confirm failure or proving behavior when practical 4. stop unless the request also includes the fix ## Gotchas - do not widen into a broader refactor or feature task - do not weaken assertions to make a test pass
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.
