regression-compare
Compare decision behavior between rule versions using a stable corpus and highlight regressions.
Works with
--- name: regression-compare description: Compare decision behavior between rule versions using a stable corpus and highlight regressions. license: MIT --- # Regression Compare ## When to use Use this skill when validating a new rule version against a baseline before or after publish. ## Steps 1. Define baseline and candidate ruleset/version IDs explicitly. 2. Collect a stable corpus of representative field-value payloads. 3. Execute `aethis_decide` for each payload against both versions. 4. Compare outcomes and classify each case: - unchanged - improved - regressed 5. Return a concise diff report with payload IDs and outcome deltas. ## Guardrails - Use identical payloads for both versions. - Keep corpus immutable during comparison. - Do not mask regressions with expectation edits unless policy text justifies the change. ## Failure handling - `not_found`: re-resolve version identifiers before rerun. - `validation_error`: remove or fix invalid payload rows and continue with valid set.
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.
