mobile-app-testing
Mobile app testing with unit tests, UI automation, performance testing. Use for test infrastructure, E2E tests, testing standards, or encountering test framework setup, device farms, flaky tests, platform-specific test errors.
89
86%
Does it follow best practices?
Impact
93%
1.09xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
92%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 articulates specific mobile testing capabilities and provides explicit trigger conditions. The description uses appropriate third-person voice and covers a good range of natural trigger terms. Minor improvement could be made by adding platform-specific terms (iOS, Android) to further distinguish from general testing skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'unit tests, UI automation, performance testing' and specific concerns like 'test infrastructure, E2E tests, testing standards, device farms, flaky tests, platform-specific test errors'. | 3 / 3 |
Completeness | Clearly answers both what ('Mobile app testing with unit tests, UI automation, performance testing') and when ('Use for test infrastructure, E2E tests, testing standards, or encountering test framework setup, device farms, flaky tests, platform-specific test errors'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'unit tests', 'UI automation', 'E2E tests', 'flaky tests', 'device farms', 'test framework setup' - these are all terms developers naturally use when discussing mobile testing. | 3 / 3 |
Distinctiveness Conflict Risk | While 'mobile app testing' and 'device farms' are distinctive, terms like 'unit tests', 'E2E tests', and 'flaky tests' could overlap with general testing skills not specific to mobile. Could benefit from more explicit mobile platform mentions (iOS, Android). | 2 / 3 |
Total | 11 / 12 Passed |
Implementation
79%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides excellent, actionable code examples across multiple mobile platforms with good conciseness. However, it lacks workflow guidance for test infrastructure setup, CI/CD integration, and handling common issues like flaky tests or device farm configuration that were mentioned in the skill description. The content would benefit from clearer multi-step processes and references to advanced topics.
Suggestions
Add a workflow section with explicit steps for setting up test infrastructure, running tests, and interpreting results (e.g., '1. Configure test runner → 2. Run unit tests → 3. If passing, run E2E → 4. Review coverage report')
Include guidance on handling flaky tests with concrete strategies (retry logic, test isolation, waiting strategies) since this is mentioned in the skill description
Add references to separate files for advanced topics like device farm setup, CI/CD integration, and platform-specific troubleshooting
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, presenting information in tables and code examples without unnecessary explanation. It assumes Claude knows what testing pyramids, Jest, XCTest, and Espresso are without explaining basic concepts. | 3 / 3 |
Actionability | Provides fully executable, copy-paste ready code examples for all three major platforms (React Native, iOS, Android). Each example is complete and demonstrates a real login flow test scenario. | 3 / 3 |
Workflow Clarity | While the testing pyramid provides a clear coverage strategy, there's no explicit workflow for setting up test infrastructure, running tests, or handling failures. Missing validation checkpoints for test execution and no guidance on CI/CD integration or handling flaky tests. | 2 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but everything is inline in one file. Given the breadth (3 platforms, multiple test types), this could benefit from references to separate files for platform-specific details, device farm setup, or flaky test handling mentioned in the skill description. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- secondsky/claude-skills
- Commit
90d6bd7
- Reviewed
Table of Contents
Is this your skill?
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.