Test Review Skill

Trigger

• Keywords: test coverage, test review, are tests sufficient, generate tests, test gen, coverage

When NOT to Use

• Code review (use codex-code-review)
• Document review (use doc-review)
• Just want to run tests (use /verify)

Commands

Command	Description	Use Case
/codex-test-review	Review test sufficiency	Required
/codex-test-gen	Generate unit tests	Add missing tests
/check-coverage	Test coverage analysis	After feature dev

Workflow: /codex-test-review

Smart detect target → Read test + source → Codex review (5 dimensions) → Coverage assessment + Gate → Loop if Needs additions

Step 1: Smart Detection

Input	Behavior
File path	Review that file directly
Directory	Review all tests in directory
Description	Auto-find related test files
Module name	Search related test files
No parameter	Auto-detect from git diff

Step 2: Read Test and Source

• Read test file (TEST_FILE)
• Read corresponding source (SOURCE_FILE, inferred from test path)

Step 3: Codex Review

First review: mcp__codex__codex with test review prompt. See @references/codex-prompt-test-review.md.

Loop review: mcp__codex__codex-reply with re-review template. See @references/codex-prompt-test-review.md.

Config: sandbox: 'read-only', approval-policy: 'never'

Save the returned threadId.

Workflow: /codex-test-gen

Read source → Derive test path → Codex generate → Save test file → Suggest review

Steps

1. Read source file
2. Derive test path: src/service/xxx.ts → test/unit/service/xxx.test.ts
3. Codex generates tests. See @references/codex-prompt-test-gen.md.
4. Save to target path
5. Suggest: run tests then /codex-test-review

Review Dimensions

Dimension	Scoring Criteria	Weight
Happy path	All public methods, main flows	High
Error handling	try/catch, error callbacks	High
Edge cases	null/undefined, extremes, empty sets	Medium
Mock quality	Not excessive, not insufficient	Medium

Three-Layer Tests

Type	Directory	Mock	Focus
Unit	test/unit/	Full	Single function
Integration	test/integration/	Only external	Inter-module
E2E	test/e2e/	Prohibited	Complete flow

Common Boundaries

Type	Cases
String	"", " ", null, undefined, very long
Number	0, -1, NaN, Infinity, MAX_SAFE_INTEGER
Array	[], [null], very large, nested
Object	{}, null, circular reference

Review Loop

⚠️ @CLAUDE.md auto-loop: fix → re-review → ... → ✅ PASS ⚠️

⛔ Needs additions → add tests → /codex-test-review --continue <threadId> → repeat until ✅ Sufficient.

Max 3 rounds. Still failing → report blocker.

Output

## Test Coverage Review
| Dimension | Coverage | Rating |
|-----------|----------|--------|
| ...       | ...      | ⭐1-5  |

### Gate: ✅ Tests sufficient / ⛔ Needs additions

Verification

• Coverage assessment includes all dimensions
• Gate is clear (✅ Tests sufficient / ⛔ Needs additions)
• Missing tests have specific code suggestions
• Codex independently researched source code branches

References

• Test review prompt: references/codex-prompt-test-review.md
• Test gen prompt: references/codex-prompt-test-gen.md
• Standards: @rules/testing.md

Examples

Input: /codex-test-review test/unit/service/xxx.test.ts
Action: Read test + source → Codex review → Coverage assessment + Gate

Input: /codex-test-gen src/service/xxx.ts
Action: Read source → Codex generate → Save test → Suggest review

Input: Are this service's tests sufficient?
Action: /codex-test-review → Assess coverage → Output gaps + Gate