Use when you have lint errors, formatting issues, or before committing code to ensure it passes CI.
66
47%
Does it follow best practices?
Impact
100%
3.22xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/fix/SKILL.mdQuality
Discovery
22%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 description only addresses when to use the skill but entirely omits what the skill actually does, making it incomplete. It includes some useful trigger terms but lacks concrete actions, tool names, or specific capabilities. The description needs a 'what it does' clause and more specific language to be effective for skill selection.
Suggestions
Add a clear 'what' clause describing concrete actions, e.g., 'Runs linters and formatters to fix code style issues, auto-corrects formatting errors, and validates code against project lint rules.'
Include specific tool names or file types as trigger terms, e.g., 'eslint', 'prettier', 'pylint', 'black', 'code style', 'auto-format'.
Restructure to lead with capabilities before the 'Use when...' clause, following the pattern: '[What it does]. Use when [trigger conditions].'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description does not list any concrete actions (e.g., 'run linter', 'auto-fix formatting', 'check style rules'). It only references situations ('lint errors', 'formatting issues') without specifying what the skill actually does. | 1 / 3 |
Completeness | The description answers 'when' fairly well with explicit trigger conditions, but completely fails to answer 'what does this do'—there is no explanation of the skill's capabilities or actions. The 'what' is entirely missing. | 1 / 3 |
Trigger Term Quality | Includes some natural keywords like 'lint errors', 'formatting issues', 'committing code', and 'CI', which users might naturally mention. However, it misses common variations like 'eslint', 'prettier', 'code style', 'linting', 'format code', or specific tool names. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'lint errors', 'formatting issues', and 'CI' provides some specificity, but without naming concrete tools or actions, it could overlap with general code quality, testing, or CI/CD skills. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A concise, well-structured skill that provides clear commands for a straightforward lint/format workflow. Its main weaknesses are the lack of a feedback loop (re-run after fixing) and the vague final step about 'reporting' manual fixes rather than giving concrete guidance on resolving common lint errors.
Suggestions
Add a feedback loop: after fixing lint issues, re-run `yarn linc` to verify all errors are resolved before committing.
Make step 3 more actionable by providing examples of common lint errors and specific fix patterns, or at least guidance on what 'manual fixes' typically look like.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Very lean and efficient. No unnecessary explanations of what linting or formatting are. Every line serves a purpose. The common mistakes section adds genuine value without padding. | 3 / 3 |
Actionability | Provides specific commands (`yarn prettier`, `yarn linc`) which is good, but lacks guidance on what to do when lint errors are found (step 3 is vague: 'report any remaining manual fixes needed'). No examples of common lint errors or how to fix them. | 2 / 3 |
Workflow Clarity | Steps are clearly sequenced, but there's no validation/feedback loop — e.g., after fixing lint issues, should you re-run `yarn linc` to confirm? There's no explicit checkpoint confirming all issues are resolved before committing. | 2 / 3 |
Progressive Disclosure | For a simple, single-purpose skill under 50 lines with no need for external references, the content is well-organized with clear sections (Instructions and Common Mistakes). No bundle files are needed. | 3 / 3 |
Total | 10 / 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.
cafd63b
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.