trimlisted

# trim A butcher trims fat so the cut is worth cooking; nobody trims by weight. This skill holds every test to one value bar: a test earns its maintenance cost by protecting behavior, a credible regression, or an independently meaningful contract. Tests that re-assert the source, repeat stronger proof, couple to implementation, or keep test-only production seams alive are fat. **Core principle:** optimize for confidence, not deletion count. A deletion without written evidence is a guess, and an uncertain candidate stays. Three modes, one value bar: - **Authoring gate** - every new or changed test, at write time. Runs alongside [taste](../taste/SKILL.md). - **Audit** - a focused, read-only-first sweep of one area for junk tests and the seams they demand. Lands as small coherent batches. - **Campaign** - prune one whole subsystem's test surface in one pass. Read [references/campaign.md](references/campaign.md) before starting one. ## Authoring gate Before adding any test, answer four questions. A missing answer means do not add it yet: redesign the test (a different boundary, a different assertion) until it passes the gate. It never means skipping the test. Under [taste](../taste/SKILL.md), no production code lands until a test passes this gate and fails. If an existing test already fails for the change, that test is the RED step; run it and cite it. 1. **What does it protect?** An observable behavior, invariant, or independent contract. 2. **What regression makes it fai