fmt
Run `make fmt` to check the code format.
77
Quality
66%
Does it follow best practices?
Impact
95%
1.69xAverage score across 3 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/fmt/SKILL.mdDiscovery
32%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 too minimal and lacks the completeness needed for effective skill selection. While it specifies a concrete command, it fails to provide trigger guidance and doesn't cover the full scope of when this skill should be used. The description reads more like a command hint than a proper skill description.
Suggestions
Add a 'Use when...' clause specifying triggers like 'when the user asks to format code', 'check formatting', 'run formatter', or 'before committing changes'
Expand the capabilities beyond just running the command - describe what make fmt does (e.g., 'Formats code according to project style guidelines, checks for style violations')
Include natural language variations users might say: 'format my code', 'fix formatting', 'style check', 'prettify code'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names a specific action ('Run `make fmt`') and purpose ('check the code format'), but describes only a single action rather than multiple concrete capabilities. | 2 / 3 |
Completeness | Only describes what (run make fmt to check format) but completely lacks any 'Use when...' clause or explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes 'make fmt' and 'code format' which are relevant technical terms, but misses common variations users might say like 'formatting', 'lint', 'style check', or 'code style'. | 2 / 3 |
Distinctiveness Conflict Risk | The specific command 'make fmt' provides some distinctiveness, but 'code format' is generic enough to potentially conflict with other formatting or linting skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted, concise skill that provides exactly what Claude needs to check code formatting. It includes a concrete command, specific rules for what gets checked, actionable fix instructions for common issues, and an explicit feedback loop. The content respects Claude's intelligence by not over-explaining.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, providing only the necessary command and specific rules without explaining what formatting is or why it matters. Every line serves a purpose. | 3 / 3 |
Actionability | Provides a concrete, copy-paste ready command with the full path, and gives specific, actionable guidance on how to fix log format issues (lowercase first character, remove trailing punctuation). | 3 / 3 |
Workflow Clarity | For this simple single-task skill, the workflow is clear: run command, check results, fix issues following specific rules, re-run until clean. The feedback loop is explicitly stated. | 3 / 3 |
Progressive Disclosure | For a simple skill under 50 lines with no need for external references, the content is well-organized with clear sections and appropriate structure. | 3 / 3 |
Total | 12 / 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.