Content
37%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is concise and well-structured at a high level, but critically lacks actionability—there are zero code examples for a code-centric testing skill. The content reads more like a checklist of tools and conventions than an instructional guide Claude can follow to produce correct test files. The referenced implementation.md file is not provided, so the skill's usefulness depends entirely on content that cannot be evaluated.
Suggestions
Add concrete, executable code examples for each test type (e.g., a ViewModel unit test with MockK and runTest, a Compose UI test with HiltAndroidRule and createAndroidComposeRule).
Include a step-by-step workflow for writing a test: e.g., 1) Create test class with annotations, 2) Set up rules, 3) Mock dependencies, 4) Write test body, 5) Run and verify.
Provide the referenced 'references/implementation.md' file or inline its key content (like MainDispatcherRule implementation and @TestInstallIn module patterns) so the skill is self-contained.
Add a concrete example of the anti-patterns and their correct alternatives (e.g., show Thread.sleep replaced with waitUntil).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It avoids explaining what unit tests, MockK, or Hilt are, and assumes Claude's competence with Android testing concepts. Every line adds specific, non-obvious guidance. | 3 / 3 |
Actionability | The skill provides no executable code examples, no concrete test snippets, and no copy-paste ready patterns. It describes what to use (e.g., 'Use MockK', 'Use runTest') but never shows how with actual code, making it vague direction rather than concrete guidance. | 1 / 3 |
Workflow Clarity | There is no sequenced workflow for writing tests. The content lists tools and anti-patterns but doesn't describe a step-by-step process for creating a test file, setting up test infrastructure, or validating test correctness. | 1 / 3 |
Progressive Disclosure | The skill references 'references/implementation.md' for test rules, which is a good signal of progressive disclosure. However, the bundle has no files, so the reference is unverifiable, and the main content is thin enough that it's unclear what value the reference file adds versus just including the content inline. | 2 / 3 |
Total | 7 / 12 Passed |