Testing methodologies, test-driven development (TDD), unit and integration testing, and testing best practices across multiple frameworks. Use when the user needs to write tests, implement TDD, or improve test coverage and quality.
74
Quality
69%
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 ./claude/skills/test-expert/SKILL.mdQuality
Discovery
82%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 solid description that clearly communicates both purpose and trigger conditions. It uses appropriate third-person voice and includes natural trigger terms. The main weakness is moderate specificity - it describes categories of testing rather than concrete actions, and the broad 'multiple frameworks' claim could create conflicts with more specialized testing skills.
Suggestions
Add more concrete actions like 'write unit tests', 'create mocks and stubs', 'set up test fixtures', 'configure test runners' to improve specificity
Consider specifying which frameworks are covered or adding distinguishing details to reduce potential conflicts with framework-specific testing skills
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (testing) and lists some actions/concepts like 'TDD', 'unit and integration testing', but doesn't list concrete specific actions like 'write unit tests', 'mock dependencies', 'generate test fixtures'. The terms are more categorical than action-oriented. | 2 / 3 |
Completeness | Clearly answers both what ('Testing methodologies, TDD, unit and integration testing, testing best practices') and when ('Use when the user needs to write tests, implement TDD, or improve test coverage and quality') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Good coverage of natural terms users would say: 'tests', 'TDD', 'test-driven development', 'unit testing', 'integration testing', 'test coverage'. These are terms users naturally use when asking for testing help. | 3 / 3 |
Distinctiveness Conflict Risk | While testing is a specific domain, 'testing best practices across multiple frameworks' is broad and could overlap with framework-specific skills. The description doesn't specify which frameworks or languages, creating potential conflict with language-specific testing skills. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides comprehensive, actionable testing guidance with excellent code examples across multiple languages and frameworks. However, it suffers from being overly verbose with explanations of concepts Claude already knows, and critically fails at progressive disclosure by cramming everything into one massive file. The content would benefit significantly from being restructured into a concise overview with links to language-specific and topic-specific reference files.
Suggestions
Split content into separate files: SKILL.md (overview + quick start), PYTHON_TESTING.md, JAVASCRIPT_TESTING.md, MOCKING.md, INTEGRATION_TESTING.md, and link from the main skill
Remove explanatory content Claude already knows (test pyramid concept, FIRST principles definitions, TDD benefits) and keep only the actionable patterns and code
Add explicit validation steps: 'Run tests after each change', 'If tests fail unexpectedly, check X before Y', 'Verify coverage report shows expected files'
Reduce the main SKILL.md to under 100 lines with a quick-start example and clear navigation to detailed reference files
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains useful information but includes explanations Claude already knows (what TDD is, what the test pyramid is, basic testing principles). The ASCII art pyramid and extensive principle explanations add tokens without adding value for an AI that understands these concepts. | 2 / 3 |
Actionability | Excellent executable code examples across multiple languages (Python/pytest, JavaScript/Jest, bash/bats, Playwright). All code snippets are copy-paste ready with proper imports and complete syntax. | 3 / 3 |
Workflow Clarity | The TDD Red-Green-Refactor cycle is clearly explained with examples, but the skill lacks validation checkpoints for test execution. No guidance on what to do when tests fail unexpectedly or how to debug flaky tests. The workflow is more conceptual than operational. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no references to external files. At 400+ lines covering unit testing, integration testing, E2E testing, mocking, fixtures, factories, CI, and multiple languages, this content should be split across multiple files with clear navigation. | 1 / 3 |
Total | 8 / 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.
b1b2fe0
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.