fix
Use when you have lint errors, formatting issues, or before committing code to ensure it passes CI.
71
Quality
55%
Does it follow best practices?
Impact
100%
3.22xAverage score across 3 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/fix/SKILL.mdQuality
Discovery
37%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 is essentially a 'Use when...' clause without the core capability statement. While it has good trigger terms that users would naturally say, it completely fails to explain what the skill actually does - does it run linters, fix errors automatically, format code, or something else? The description is backwards: it has the 'when' but lacks the 'what'.
Suggestions
Add a capability statement at the beginning describing what the skill does (e.g., 'Runs linters and formatters to fix code style issues' or 'Automatically fixes lint errors and formats code').
Specify which tools or languages are supported to improve distinctiveness (e.g., 'ESLint, Prettier, Black' or 'JavaScript, Python').
Restructure to follow the pattern: '[What it does]. Use when [triggers].' to ensure both components are present.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description mentions 'lint errors, formatting issues' but does not describe any concrete actions the skill performs. It lacks verbs describing what the skill actually does (e.g., 'fixes', 'runs', 'checks'). | 1 / 3 |
Completeness | The description only addresses 'when' to use the skill but completely omits 'what' the skill does. There's no explanation of the actual capabilities or actions performed. | 1 / 3 |
Trigger Term Quality | Contains good natural trigger terms users would say: 'lint errors', 'formatting issues', 'committing code', 'CI'. These are terms developers naturally use when needing this type of help. | 3 / 3 |
Distinctiveness Conflict Risk | The triggers are somewhat specific to linting/formatting domain, but without describing what the skill actually does, it could overlap with multiple code quality tools (linters, formatters, CI runners, etc.). | 2 / 3 |
Total | 7 / 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.
This is a concise, well-structured skill that efficiently communicates the basic lint/format workflow. However, it could be more actionable by showing example lint errors and their fixes, and the workflow would benefit from explicit validation steps (e.g., 'run linc again after fixes to confirm').
Suggestions
Add an example of common lint errors and how to fix them (e.g., 'unused import' -> remove the import line)
Include a validation step after fixing lint issues: 'Run yarn linc again to confirm all issues resolved before committing'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean and efficient. No unnecessary explanations of what linting or formatting is. Every line serves a purpose and assumes Claude's competence. | 3 / 3 |
Actionability | Provides specific commands (yarn prettier, yarn linc) but lacks concrete examples of what 'remaining manual fixes' might look like or how to address common lint errors. No example output shown. | 2 / 3 |
Workflow Clarity | Steps are clearly sequenced (1-2-3), but lacks validation checkpoints. No guidance on what to do if linc fails beyond 'fix them' - missing a feedback loop for error recovery. | 2 / 3 |
Progressive Disclosure | For this simple, single-purpose skill under 50 lines, the structure is appropriate. Clear sections (Instructions, Common Mistakes) with no need for external references. | 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.
- 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.