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.
61
72%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/mobile-app-testing/skills/mobile-app-testing/SKILL.mdQuality
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 description that clearly communicates both what the skill does and when to use it, with good coverage of natural trigger terms. The mobile app domain is reasonably well-scoped, though some testing terms are generic enough to potentially overlap with non-mobile testing skills. Adding mobile-specific framework names would further sharpen distinctiveness.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: unit tests, UI automation, performance testing, E2E tests, test framework setup, device farms, flaky tests. These are concrete, actionable areas within mobile app testing. | 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'). The 'Use for...' clause provides explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'unit tests', 'UI automation', 'performance testing', 'E2E tests', 'flaky tests', 'device farms', 'platform-specific test errors', 'test framework setup'. These cover a wide range of terms a developer would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | The 'mobile app' qualifier helps distinguish from general testing skills, but terms like 'unit tests', 'E2E tests', and 'performance testing' could overlap with web or backend testing skills. The description could be more explicit about mobile-specific frameworks (e.g., XCTest, Espresso, Appium) to further reduce conflict risk. | 2 / 3 |
Total | 11 / 12 Passed |
Implementation
52%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides good, actionable code examples across multiple mobile testing frameworks, making it easy to get started with basic test writing. However, it lacks workflow guidance for test infrastructure setup, CI/CD integration, flaky test handling, and device farm configuration — all topics mentioned in the skill description. The best practices section is generic advice Claude already knows, wasting tokens that could be used for more valuable operational guidance.
Suggestions
Add a workflow section covering test setup, execution, and CI integration steps (e.g., how to configure Detox, set up device farms, run tests in sequence with validation checkpoints)
Replace the generic 'Best Practices' and 'Avoid' sections with mobile-specific operational guidance like handling flaky tests, platform-specific test errors, and device farm configuration
Add a section on debugging common test failures (e.g., Detox synchronization issues, Espresso IdlingResource, XCTest timing) since these are non-obvious and high-value
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably efficient with good use of tables and code examples, but the 'Best Practices' and 'Avoid' sections contain generic testing advice that Claude already knows (e.g., 'mock external dependencies', 'test both success and failure paths'). The testing pyramid table is useful but the coverage percentages are somewhat arbitrary. | 2 / 3 |
Actionability | Provides fully executable code examples across four frameworks (Jest, Detox, XCTest, Espresso) with concrete, copy-paste-ready test implementations. Each platform has a complete, runnable test example with realistic assertions. | 3 / 3 |
Workflow Clarity | There is no workflow or sequencing guidance for setting up test infrastructure, running tests, handling flaky tests, or configuring device farms — all mentioned in the skill description. The content presents isolated code snippets without any process for test execution, CI integration, or validation of test results. | 1 / 3 |
Progressive Disclosure | The content is organized into clear sections by platform, which is helpful, but everything is inline in a single file with no references to deeper materials. Given the breadth of topics mentioned in the description (device farms, flaky tests, test infrastructure), the skill would benefit from separate reference files for advanced topics. | 2 / 3 |
Total | 8 / 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 |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- secondsky/claude-skills
- Commit
5e92b71
- 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.