test-master
tessl i github:jeffallan/claude-skills --skill test-masterUse when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.
Review Score
64%
Validation Score
12/16
Implementation Score
42%
Activation Score
82%
Generated
Validation
Total
12/16Score
Passed| Criteria | Score |
|---|---|
metadata_version | 'metadata' field is not a dictionary |
license_field | 'license' field is missing |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata |
body_examples | No examples detected (no code fences and no 'Example' wording) |
Implementation
Suggestions 4
Score
42%Overall Assessment
This skill excels at progressive disclosure with a well-organized reference table, but critically lacks actionability - there are no concrete code examples, test patterns, or executable guidance. The content reads more like a job description than a practical skill that teaches Claude how to write tests. The workflow is present but missing validation checkpoints essential for testing contexts.
Suggestions
- Add concrete, executable test examples for at least one framework (e.g., a complete Jest unit test with assertions, mocking, and error case handling)
- Replace the abstract 'Write tests with proper assertions' step with specific patterns showing what good assertions look like vs bad ones
- Add validation checkpoints to the workflow, such as 'Run tests locally before committing' and 'Verify coverage meets threshold before merging'
- Remove the role-playing persona and 'Knowledge Reference' sections - they consume tokens without adding actionable value
| Dimension | Score | Reasoning |
|---|---|---|
Conciseness | 2/3 | The skill is reasonably efficient but includes some unnecessary elements like the role-playing persona definition ('12+ years experience') and the 'Knowledge Reference' section which lists technologies Claude already knows. The three-mode thinking framework adds minimal value. |
Actionability | 1/3 | The skill provides no executable code, no concrete test examples, and no specific commands. It describes what to do abstractly ('Write tests with proper assertions') but never shows how. The entire content is descriptive rather than instructive. |
Workflow Clarity | 2/3 | The 5-step core workflow provides a clear sequence but lacks validation checkpoints. For testing workflows involving CI/CD and automation, there are no feedback loops for handling test failures or verification steps before proceeding. |
Progressive Disclosure | 3/3 | Excellent use of reference table with clear signaling of when to load each reference file. Content is appropriately split with the main skill as an overview pointing to one-level-deep detailed references for specific topics. |
Activation
Suggestions 2
Score
82%Overall Assessment
This description has strong trigger term coverage and completeness with explicit 'Use when' and 'Invoke for' clauses. However, it lacks specificity in describing concrete actions (what exactly does it do with tests?) and has moderate conflict risk due to its broad scope covering security and performance testing domains.
Suggestions
- Add specific concrete actions like 'generate test cases', 'create mock objects', 'analyze code coverage reports', 'scaffold test suites' to improve specificity
- Consider narrowing scope or clarifying boundaries with security/performance skills to reduce conflict risk (e.g., 'for code-level security tests, not penetration testing')
| Dimension | Score | Reasoning |
|---|---|---|
Specificity | 2/3 | Names the domain (testing) and lists types of tests (unit, integration, E2E, performance, security) but doesn't describe concrete actions - it says 'writing tests' and 'creating test strategies' which are somewhat vague rather than specific operations like 'generate test fixtures' or 'mock dependencies'. |
Completeness | 3/3 | Explicitly answers both what ('writing tests, creating test strategies, building automation frameworks') and when ('Use when... Invoke for...') with clear trigger guidance. The 'Use when' and 'Invoke for' clauses provide explicit selection criteria. |
Trigger Term Quality | 3/3 | Good coverage of natural terms users would say: 'tests', 'unit tests', 'integration tests', 'E2E', 'coverage analysis', 'performance testing', 'security testing', 'automation frameworks'. These are terms developers naturally use when requesting testing help. |
Distinctiveness Conflict Risk | 2/3 | Testing is a clear domain, but 'security testing' could overlap with security-focused skills, and 'performance testing' could conflict with performance/profiling skills. The broad scope increases potential for overlap with more specialized skills. |