Test Review Quality — Testing & QA agent for Claude Code
Adversarially audits tests against their code-under-test — re-derives what each test verifies from the body alone, names the regression each would catch, and flags tests that assert nothing, couple to.
How to install Test Review Quality
Installs to ~/.claude/agents/spardutti-claude-skills-test-review-quality.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/Spardutti/claude-skills/HEAD/agents/test-review-quality.md -o ~/.claude/agents/spardutti-claude-skills-test-review-quality.md Restart Claude Code, or start a new session, for it to be picked up.
What Test Review Quality does
name: test-review-quality description: Adversarially audits tests against their code-under-test — re-derives what each test verifies from the body alone, names the regression each would catch, and flags tests that assert nothing, couple to internals, mock the world, or cover only the happy path. Read-only. model: sonnet tools: Read, Grep, Glob
You are a test-quality falsifier. Your job is **not** to approve tests — it is to find tests that would let a bug slip through. Default to reject
Alternatives in Testing & QA
- Review Test Crash Safety — Reviews test code for crash safety testing quality and production assert statements: whether crash/recovery sc 432 ★
- API Tester — Test all API endpoints for correctness and robustness 116 ★
- Figma Executor — Runs an architect's Figma spec — resolves stable names to nodeIds at run time, builds into a named working fra 76 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
QA Author
Blind QA-plan author. Spawned by /blueprint immediately after context.md is written — reads ONLY context.md an
Confirmer
Independent confirmation subagent for spec packages. Re-derives a handed-off finding from the handoff material
Design Archeologist
Long-running codebase scan. Extracts de-facto design tokens from existing UI code, clusters them by frequency,
Deceptive Test Hunter
Audits test changes for deceptive or redundant tests. Use after writing or changing any _test.py file. Reports
Scope Drift Detector
Compare the current diff against the active plan.md spec to detect scope expansion. Flags files and features n
Shadowcat Spec Reviewer
Read-only review of whether an implementation matches its spec/plan — completeness, nothing skipped or downgra
Related Skills
Docs Drift
Use to catch documentation that has silently gone stale — it spawns ONE fresh sibling session via CCC that ext
QA Integration
Run integration/E2E QA against a RUNNING app via a real browser — execute new + regression test cases, assert
Code Review Pipeline
Run the full code review pipeline on your changes. Creates an agent team of parallel reviewers covering both t