← ClaudeAtlas

test-auditlisted

Audit and consolidate an existing test suite — low-value, implementation-coupled or duplicated tests, duplicated setup, and the test-only production seams they keep alive. Evidence first, then one approved batch of edits. Campaign mode prunes a whole subsystem's test surface.
emaballarin/ccplugins · ★ 4 · Testing & QA · score 80
Install: claude install-skill emaballarin/ccplugins
# /ws:test-audit — prune and consolidate a test suite Audits the tests in the scope the operator names: tests that re-assert source, duplicate stronger proof, couple behaviour to implementation, or keep test-only production seams alive — and the duplicated setup `/ws:test-gate` deliberately left behind. Optimise for confidence, not deletion count. Continue a broad audit as separate coherent batches. The value bar, junk patterns, retention bar, and the notes file live in `${CLAUDE_PLUGIN_ROOT}/references/test-value.md`; read it first. **Campaign mode** prunes one subsystem's whole test surface — every test file one package or area owns — in one change; before starting one, read [references/campaign.md](references/campaign.md), beside this file. ## 1. Scope and seed - The scope is exactly what the operator named. - Read the root and scoped `AGENTS.md` / `CLAUDE.md` and `PROJECT.md` first. - Seed the candidate list with every `ws:test-gate` entry in the notes file that falls inside the scope. ## 2. Discovery — read-only Hunt for the junk patterns and for duplicated setup. For a broad scope, run parallel read-only discovery lanes through subagents, split along production-owner boundaries — core packages, plugins or extensions, apps and scripts and tooling, plus one cross-cutting pattern sweep. Outside campaign mode, prefer a few high-confidence candidates over a large speculative inventory. Before judging a candidate, read the complete test and its production owner, the