android-testing
Comprehensive testing strategy involving Unit, Integration, Hilt, and Screenshot tests.
59
48%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.github/skills/android-testing/SKILL.mdQuality
Discovery
32%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description identifies a clear testing domain with specific test types but fails to provide actionable guidance on when to use this skill. The lack of a 'Use when...' clause significantly limits Claude's ability to select this skill appropriately. The Hilt reference suggests Android context but this isn't made explicit.
Suggestions
Add a 'Use when...' clause with explicit triggers like 'Use when writing Android tests, setting up test infrastructure, or when the user mentions unit tests, UI tests, Hilt testing, or screenshot testing'
Specify concrete actions the skill enables, such as 'Generates test cases, configures Hilt test modules, creates screenshot test baselines, and sets up test fixtures'
Make the Android/mobile context explicit if this is Android-specific, e.g., 'Android testing strategy' to distinguish from general testing skills
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (testing) and lists specific test types (Unit, Integration, Hilt, Screenshot), but doesn't describe concrete actions like 'write tests', 'generate test cases', or 'run test suites'. | 2 / 3 |
Completeness | Describes what (testing strategy with specific test types) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'Unit', 'Integration', 'Screenshot tests', and 'Hilt' (Android-specific), but misses common variations users might say like 'test coverage', 'write tests', 'testing', 'TDD', or 'mock'. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'Hilt' and 'Screenshot tests' suggests Android/mobile context which adds some distinctiveness, but 'Unit' and 'Integration' tests are generic enough to potentially conflict with other testing-related skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides solid, actionable code examples for Android testing with Roborazzi and Hilt, making it immediately useful. However, it includes some unnecessary explanatory content Claude already knows (testing pyramid basics) and lacks validation/troubleshooting guidance for when tests fail or screenshots don't match.
Suggestions
Remove the 'Testing Pyramid' section - Claude already understands test categorization
Add validation steps: what to do when screenshot verification fails, how to review diffs, when to update baselines
Include a troubleshooting section for common Roborazzi issues (e.g., font rendering differences, CI vs local discrepancies)
Consider splitting detailed examples into separate files (e.g., SCREENSHOT_TESTING.md, HILT_TESTING.md) with SKILL.md as overview
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient but includes some unnecessary explanation like the 'Testing Pyramid' section which Claude already knows, and phrases like 'This skill provides expert guidance' add no value. | 2 / 3 |
Actionability | Provides fully executable code examples for screenshot tests, Hilt tests, and concrete Gradle commands. Dependencies are copy-paste ready with specific versions. | 3 / 3 |
Workflow Clarity | Setup steps for Roborazzi are clear, but lacks validation checkpoints. No guidance on what to do if tests fail, how to interpret screenshot diffs, or feedback loops for fixing regressions. | 2 / 3 |
Progressive Disclosure | Content is reasonably structured with clear sections, but everything is inline in one file. For a comprehensive testing strategy, detailed examples for each test type could be split into separate reference files. | 2 / 3 |
Total | 9 / 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.
- Commit
3f68e39
- 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.