Test Audit

Invoke whenever writing, changing, reviewing, or sweeping tests in jev-judge-mcp. Authoring gate for new tests plus audit workflow for low-value, implementation-coupled, or duplicative tests and the test-only production seams they demand, under this repo's rule that a test is never deleted or weakened to make a failing build pass.

49 stars 5 forksTesting & QA

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add PyModel/jev-judge-mcp --skill test-audit
Manual install
git clone --depth 1 https://github.com/PyModel/jev-judge-mcp.git /tmp/jev-judge-mcp
mkdir -p ~/.claude/skills
cp -r /tmp/jev-judge-mcp/.agents/skills/test-audit ~/.claude/skills/test-audit

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Test Audit

Three modes, one value bar. Authoring mode gates every new or changed test at
write time. Audit mode runs focused sweeps of tests that re-assert source,
duplicate stronger proof, couple behavior to implementation, or keep test-only
production seams alive. Run broad audits as separate coherent follow-up
branches, one concern each; optimize for confidence, not deletion count.
Campaign mode prunes one whole test layer or source package at a time (see
Campaign below).

## Authoring gate

Before adding any test, answer four questions; a missing answer means do not
add it yet:

1. What observable behavior, invariant, or independent contract does it protect?
2. What credible regression makes it fail?
3. Why does existing coverage not already catch that failure? Each contract has
   one primary test owner at the strongest boundary; another layer needs its
   own distinct risk, such as a stdio/HTTP transport or lifecycle failure the
   owner cannot reach. Prefer extending a parametrized case or a shared helper
   in `tests/support/` over a near-duplicate test; consolidate duplicated
   setup in the same change (the ADR-0015 loader and ADR-0017 secret checks
   are the precedents).
4. Does it need a production seam (export, flag, wrapper, injection hook) that
   no production caller needs? If yes, move the test to the real boundary
   instead — see Test seams below.

Then check the test against every [junk pattern](#junk-patterns); a match fails
Read the full skill on GitHub

Details

Skill name
test-audit
Path
.agents/skills/test-audit/SKILL.md
License
MIT
Repo updated
26 October 2026

FAQ

What does the Test Audit skill do?

Invoke whenever writing, changing, reviewing, or sweeping tests in jev-judge-mcp. Authoring gate for new tests plus audit workflow for low-value, implementation-coupled, or duplicative tests and the test-only production seams they demand, under this repo's rule that a test is never deleted or weakened to make a failing build pass.

How do I install the Test Audit skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add PyModel/jev-judge-mcp --skill test-audit. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Test Audit popular?

It lives in PyModel/jev-judge-mcp, which has 49 GitHub stars and 5 forks.

Related skills

Jev

49

PyModel/jev-judge-mcp

Use when code needs a judgment about natural language that rules or regex cannot make (classify, route, triage, moderate, score, rank, match, dedupe, filter, extract, verify, or gate an action), when brainstorming where AI could fit in an app, when an LLM call exists only to pick a label, score, or yes/no, or when code uses TypeSafe AI, Jev, System One, typesafe-sdk, or @typesafe-ai/sdk.

AI, LLMs & Agents

Jev MCP

49

PyModel/jev-judge-mcp

Use before a step that judges material you already have — a claim against evidence, screening fetched text before reading it, classifying or keeping or dropping many items, finding or reranking candidates, one bounded choice, comparing two passages, grading on an ordered rubric, judging a file without reading it into your context, extracting a regex-matched value, reviewing a patch, or checking that work finished. Batch every question about one state into one call. Jev is invoked when an unresolved judgment earns a model decision. Deterministic evidence takes precedence; Jev is not a mandatory

AI, LLMs & Agents

Olore Bunit Latest

119

olorehq/olore

Local bunit documentation reference (latest). bUnit Blazor testing documentation. Use for Blazor component testing, rendering, event handling, JSInterop mocking, and test assertions in .NET.

Testing & QA

Drupal Testing

84

grasmash/drupal-claude-skills

Test-driven development for Drupal with PHPUnit and Drupal Test Traits (DTT). Use when writing or fixing tests, deciding what is worth a test, reproducing a bug before fixing it, choosing a bootstrap level (Unit vs Kernel vs ExistingSite/functional), testing permission gates, adding Playwright visual verification, or debugging tests that silently run zero assertions. Covers the bug-fix RED-first discipline, the worth-a-test rubric, bootstrap cost tradeoffs, negative tests, the anonymous-403 permission trap, DTT gotchas, and the PHPUnit-version pin that makes Drupal tests pass vacuously.

Testing & QA

Olore Playwright 1.60.0

119

olorehq/olore

Local Playwright documentation reference (1.60.0). Playwright documentation. Use for end-to-end testing, browser automation, cross-browser testing, selectors, assertions, and test fixtures.

Testing & QA

Stress Test

45

gbasin/stress-test-skill

Adversarially stress-test a technical plan by verifying claims against real docs, running POC code, and updating the plan before you build.

Testing & QA

Browse the most popular Claude skills, all testing & qa skills, or write your own with the skills generator.