Use when writing unit/integration tests for Vite projects - configure vitest.config.ts, write test suites with describe/it, create mock implementations with vi.fn and vi.mock, set up code coverage thresholds, and run tests in parallel
95
100%
Does it follow best practices?
Impact
78%
1.50xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly identifies its niche (Vitest testing for Vite projects), lists specific concrete actions, and includes an explicit 'Use when' trigger clause. The description includes both high-level concepts (unit/integration tests, code coverage) and framework-specific terms (vi.fn, vi.mock, vitest.config.ts) that make it highly distinguishable and easy to match against user requests.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: configure vitest.config.ts, write test suites with describe/it, create mock implementations with vi.fn and vi.mock, set up code coverage thresholds, and run tests in parallel. | 3 / 3 |
Completeness | Explicitly answers both what (configure vitest, write test suites, create mocks, set up coverage, run tests in parallel) and when ('Use when writing unit/integration tests for Vite projects') with a clear 'Use when' clause at the start. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'unit tests', 'integration tests', 'Vite', 'vitest', 'mock', 'vi.fn', 'vi.mock', 'code coverage', 'describe/it', 'vitest.config.ts'. These cover both high-level concepts and specific API terms users would mention. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to Vitest and Vite projects specifically, with distinct triggers like 'vitest.config.ts', 'vi.fn', 'vi.mock' that would not overlap with Jest, Mocha, or other testing framework skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill that exemplifies good progressive disclosure and conciseness. The main file serves as a lean entry point with executable quick-start code, then routes to detailed reference files based on task context. The 'Loading Files' checklist with explicit guidance to not load all files at once is a particularly effective pattern for token efficiency.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It doesn't explain what Vitest is beyond a one-line description, assumes Claude knows how testing frameworks work, and every section serves a clear purpose. The 'When to Use' section is brief and useful for routing. No unnecessary padding. | 3 / 3 |
Actionability | Provides fully executable code: npm install command, a complete vitest.config.ts, and a working test file with proper imports. The quick start is copy-paste ready and covers the essential setup pattern. | 3 / 3 |
Workflow Clarity | For a testing framework skill, the workflow is clear: install → configure → write tests. The 'Loading Files' section provides an explicit decision checklist for which references to load based on the task. Since this is primarily a reference-routing skill rather than a destructive multi-step operation, the workflow is appropriately scoped. | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a concise overview and quick start in the main file, then a well-organized reference table with five clearly-labeled reference files. The 'Loading Files' checklist with task-based guidance is a strong pattern. References are one level deep and clearly signaled. However, no bundle files were provided to verify the references actually exist. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
6b12458
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.