TE

Test Coverage Reviewer

Evaluates test suites for meaningful coverage, ensuring assertions actually verify program behavior.

Install

mkdir -p .claude/skills/test-coverage-reviewer && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/14616" && unzip -o skill.zip -d .claude/skills/test-coverage-reviewer && rm skill.zip

Installs to .claude/skills/test-coverage-reviewer

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Reviews test quality, assertions, and edge case coverage
56 charsno explicit “when” trigger
Advanced

Key capabilities

  • Review each test file completely.
  • Verify that every test has meaningful assertions.
  • Check for missing edge cases or scenarios.
  • Ensure no mocked business logic on the thing being tested.
  • Confirm test names describe expected behavior.

How it works

The skill reads test files and evaluates them against criteria for meaningful assertions, edge case coverage, and proper mocking, then categorizes their quality.

Inputs & outputs

You give it
One or more test files.
You get back
A JSON array indicating the quality of each test (CARGO-CULT, GAP, WEAK, GOOD) and cross-cutting findings.

When to use Test Coverage Reviewer

  • Reviewing test files for assertion quality
  • Identifying missing edge case coverage
  • Checking for mocked business logic issues

About this skill

Test Coverage Reviewer

Role

Review tests for meaningful assertions, edge case coverage, and absence of cargo-cult patterns. Ensures tests actually verify behavior, not just run without errors.

Instructions

  1. Read each test file completely
  2. Verify every test has meaningful assertions (not just expect(true))
  3. Check that tests would fail if the implementation is wrong
  4. Look for missing edge cases (empty input, nulls, boundaries)
  5. Verify no mocked business logic (vi.mock on the thing being tested)
  6. Check test names describe expected behavior
  7. Ensure property-based tests exist for pure functions
  8. For many test files, spawn opus subagents to review test files in parallel (1 per test file).

Literature

  • Consult docs/compound/research/tdd/ for test quality assessment and coverage methodology
  • Consult docs/compound/research/property-testing/ for property-based testing theory
  • Run ca knowledge "test coverage quality" for indexed knowledge

Collaboration

Share cross-cutting findings via SendMessage: cargo-cult tests hiding security issues go to security-reviewer; unnecessary test complexity goes to simplicity-reviewer.

Deployment

AgentTeam member in the review phase. Spawned via TeamCreate. Communicate with teammates via SendMessage.

Output Format

  • CARGO-CULT: Test passes regardless of implementation
  • GAP: Missing edge case or scenario
  • WEAK: Assertion exists but is insufficient
  • GOOD: Test is meaningful and complete

When not to use it

  • When only running tests without quality review is needed.
  • When tests are known to be high quality and complete.
  • When the goal is to write new tests rather than review existing ones.

Limitations

  • The skill focuses on test quality, not on fixing implementation code.
  • The skill relies on specific literature for test quality assessment.
  • The skill can spawn subagents for parallel review, which may have resource implications.

How it compares

This workflow specifically reviews the quality and effectiveness of existing tests, identifying common anti-patterns and gaps, unlike simply executing tests or checking code coverage metrics.

Compared to similar skills

Test Coverage Reviewer side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
Test Coverage Reviewer (this skill)04moNo flagsAdvanced
python-testing-patterns772moReviewIntermediate
dependency-upgrade265moReviewIntermediate
test-cases577moNo flagsBeginner

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry