jbvc/test-fixing
Run tests and systematically fix all failing tests using smart error grouping. Use when user asks to fix failing tests, mentions test failures, runs test suite and failures occur, or requests to make tests pass.
85
85%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
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 what the skill does and when to use it, with good natural trigger terms. Its main weaknesses are moderate specificity — it could enumerate more concrete actions (e.g., parsing error output, grouping by root cause, applying fixes iteratively) — and some potential overlap with general debugging or testing skills.
Suggestions
Add more specific concrete actions to improve specificity, e.g., 'Parses test output, groups failures by root cause, iteratively applies fixes and re-runs until all tests pass.'
Differentiate from general debugging skills by mentioning specific techniques or scope boundaries, e.g., 'Focuses on unit/integration test failures rather than runtime debugging.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (tests) and some actions ('run tests', 'fix failing tests', 'smart error grouping'), but doesn't list multiple concrete specific actions beyond running and fixing. 'Smart error grouping' hints at a technique but is somewhat vague. | 2 / 3 |
Completeness | Clearly answers both what ('Run tests and systematically fix all failing tests using smart error grouping') and when ('Use when user asks to fix failing tests, mentions test failures, runs test suite and failures occur, or requests to make tests pass'). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'fix failing tests', 'test failures', 'test suite', 'make tests pass' — these are phrases users would naturally say when encountering this need. | 3 / 3 |
Distinctiveness Conflict Risk | Fairly specific to test fixing, but could overlap with general testing skills, debugging skills, or CI/CD skills. The 'smart error grouping' aspect adds some distinctiveness but the overall scope of 'fix failing tests' is broad enough to potentially conflict. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
N/AReviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
Something went wrong
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.
Reviewed
Table of Contents