Content
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill uses progressive disclosure well, offloading code and detail to a real reference file, but the body's instructional sections are abstract descriptions rather than concrete, executable guidance and lack validation checkpoints.
Suggestions
Replace the conceptual opening sentence with a terse purpose line, or move the rationale into rule.md, to stop re-explaining what mocking is.
Make Check/Fix/Code Review actionable with concrete steps or a short inline example (e.g., grep for jest.mock without a matching afterEach(restoreAllMocks), then flag the file), instead of describing the task.
Add an explicit validation checkpoint in the Code Review workflow (e.g., confirm the CI step fails when the mock rule is violated, and re-run until it blocks the regression).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly lean, but the opening sentence explaining what mocking is and why over-mocking is risky covers a concept Claude already knows and could be cut. | 2 / 3 |
Actionability | Quick Reference offers a few concrete directives (jest.restoreAllMocks() in afterEach, use MSW), but the Check/Fix/Explain sections describe tasks abstractly ('Review this test file...', 'Improve mocking strategy by...') with no executable code in the body. | 2 / 3 |
Workflow Clarity | Check, Fix, Explain, and Code Review form a loose sequence but there are no explicit validation checkpoints or feedback loops, and CI/batch verification contexts are capped at 2 without them. | 2 / 3 |
Progressive Disclosure | A well-organized overview points via a clearly signaled, one-level-deep reference to references/rule.md (verified to exist and hold the code examples and details), splitting content appropriately. | 3 / 3 |
Total | 9 / 12 Passed |