Execute automatically formats and validates code files using Prettier and other formatting tools. Use when users mention "format my code", "fix formatting", "apply code style", "check formatting", "make code consistent", or "clean up code formatting". Handles JavaScript, TypeScript, JSON, CSS, Markdown, and many other file types. Trigger with relevant phrases based on skill purpose.
79
76%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/examples/formatter/skills/code-formatter/SKILL.mdQuality
Discovery
89%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 skill description with strong trigger terms and clear completeness. The 'Use when...' clause with multiple natural phrases is well done, and the file type enumeration adds helpful specificity. The main weakness is that the core capability description could list more specific actions beyond just 'formats and validates', and the trailing sentence 'Trigger with relevant phrases based on skill purpose' is vague filler that adds no value.
Suggestions
Remove the vague trailing sentence 'Trigger with relevant phrases based on skill purpose' as it adds no information and is filler.
Expand the specific actions beyond 'formats and validates' — consider adding actions like 'auto-indents code', 'enforces consistent quotes and semicolons', 'fixes trailing whitespace', or 'applies project .prettierrc configuration'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (code formatting) and mentions specific tools (Prettier) and file types, but the actual actions are somewhat limited — 'formats and validates' are the only concrete actions listed. It doesn't enumerate multiple distinct operations like a score-3 description would. | 2 / 3 |
Completeness | Clearly answers both 'what' (formats and validates code files using Prettier and other formatting tools, handles multiple file types) and 'when' (explicit 'Use when...' clause with specific trigger phrases). | 3 / 3 |
Trigger Term Quality | Includes excellent natural trigger phrases users would actually say: 'format my code', 'fix formatting', 'apply code style', 'check formatting', 'make code consistent', 'clean up code formatting'. Also lists specific file types (JavaScript, TypeScript, JSON, CSS, Markdown) which are natural keywords. | 3 / 3 |
Distinctiveness Conflict Risk | The focus on code formatting with Prettier is a clear, distinct niche. The trigger terms are specifically about formatting and style consistency, which is unlikely to conflict with other skills like linting, testing, or general code editing. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a competent skill with a well-structured workflow and clear sequencing, but it suffers from moderate verbosity and incomplete actionability. The commands are specific but presented inline rather than as executable code blocks, and the referenced bundle files don't exist, undermining the progressive disclosure strategy. The error handling table is a nice touch but partially redundant with the referenced errors.md.
Suggestions
Wrap CLI commands in fenced code blocks (```bash) to make them copy-paste ready and improve actionability.
Provide the actual bundle files (references/implementation.md and references/errors.md) or remove references to them—broken references hurt more than they help.
Trim the prerequisites section (Claude knows what file extensions are) and reduce repetition of supported file types across sections.
In the Examples section, show exact command sequences in code blocks rather than describing the process in prose.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some unnecessary verbosity. The prerequisites section explains things Claude would know (what file extensions are supported is repeated multiple times), and the output section describes a report format that could be more concise. The error handling table, while useful, partially duplicates what would be in the referenced errors.md. | 2 / 3 |
Actionability | The instructions provide specific CLI commands (e.g., `npx prettier --check`, `npx prettier --write`) which is good, but they lack complete executable code blocks—commands are inline rather than in fenced code blocks, and the examples section describes processes in prose rather than showing exact command sequences. The reference to implementation.md for 'sensible defaults' defers key actionable content without the bundle file actually existing. | 2 / 3 |
Workflow Clarity | The 7-step workflow is clearly sequenced: check availability → detect config → check formatting → apply formatting → set up ignore file → optional hooks → final validation. Step 7 provides an explicit validation checkpoint, and the error handling table covers recovery scenarios. The check-before-write pattern is a good feedback loop. | 3 / 3 |
Progressive Disclosure | The skill references `${CLAUDE_SKILL_DIR}/references/implementation.md` and `${CLAUDE_SKILL_DIR}/references/errors.md`, which is good progressive disclosure structure, but no bundle files were provided, meaning these references are broken. The error handling table partially duplicates what errors.md would contain, and the main body could offload more detail to references if they existed. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
3a2d27d
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.