CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

code-formatter

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.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable skill: every step carries a concrete executable command, the sequence is logically ordered with an explicit final verification, and bundle references are real, one-level-deep, and well labeled. The main weaknesses are mild redundancy between the body and the bundle files (error handling, examples), an orphaned references/examples.md that is never linked, and an implicit rather than explicit retry loop after the final check.

DimensionReasoningScore

Conciseness

The body is efficient with concrete commands throughout, but the Overview ("Formats and validates code files using Prettier and related formatting tools") duplicates the frontmatter description and the Examples section ("Run `npx prettier --write src/app.js`. Report the file as reformatted or already conformant.") restates instructions already given, so minor trims are possible. This matches anchor 4 ("Efficient; minor instances of over-explanation that could be trimmed") rather than 5, and it is clearly above anchor 3 since no section explains concepts Claude would not already know.

4 / 5

Actionability

Guidance is copy-paste ready throughout: "`npx prettier --check "**/*.{js,jsx,ts,tsx,json,css,md}" --ignore-path .prettierignore`", "`npm install --save-dev prettier`", "installing `husky` and `lint-staged`, then configuring `lint-staged` in `package.json`", plus three concrete worked examples (single file, project-wide setup, check-only). This matches anchor 5 ("Fully executable; copy-paste ready code or commands; specific examples cover the common cases"); the only omissions (exact .prettierrc defaults, lint-staged config snippet) are deliberately deferred to the referenced guide, which is minor enough not to drop to 4.

5 / 5

Workflow Clarity

The 7-step sequence is clearly ordered with an explicit final validation ("Run a final `npx prettier --check` to confirm all target files now conform") and an error-handling table for recovery, so the batch-operation cap of 3 does not apply. It falls short of anchor 5 because the feedback loop is implicit — there is no step saying what to do when the final check still fails (recovery is delegated to the error table rather than a validate → fix → re-validate loop in the sequence itself), which is exactly the minor validation gap anchor 4 describes.

4 / 5

Progressive Disclosure

References are one level deep and clearly signaled with descriptive labels ("[`references/implementation.md`](references/implementation.md) -- detailed implementation guide with configuration examples", "[`references/errors.md`](references/errors.md) -- common error scenarios and solutions"), and both linked files exist in the bundle. Scored against the actual bundle structure, gaps remain: `references/examples.md` is orphaned (never linked from the body and contains only placeholder text), and the body's Error Handling table and Examples section duplicate content that exists in the bundle files — matching anchor 4 ("most content is appropriately placed; references mostly clear; minor organization gaps") rather than 5 ("content appropriately split").

4 / 5

Total

17

/

20

Passed

Description

78%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that clearly answers both what the skill does and when to use it, backed by six concrete, natural trigger phrases and a named tool. Weaknesses are the dangling opening word ("Execute automatically formats"), a pure filler sentence ("Trigger with relevant phrases based on skill purpose."), and a capability list limited to just two verbs, which keeps specificity at the midpoint.

Suggestions

Fix the malformed opening ("Execute automatically formats..." → "Executes...") and delete the filler sentence "Trigger with relevant phrases based on skill purpose." — it adds no information.

Broaden the capability statement beyond the two verbs "formats and validates" to mention configuration setup (.prettierrc/.prettierignore) and optional pre-commit enforcement, which the body actually performs.

Add tool- and extension-based trigger terms (e.g., "run Prettier", "prettify", ".js/.ts files") to sharpen trigger coverage and reduce overlap with generic linting or style-guide skills.

DimensionReasoningScore

Specificity

The description names the tool and only two concrete action verbs — "formats and validates code files using Prettier" — while "Handles JavaScript, TypeScript, JSON, CSS, Markdown, and many other file types" lists file types rather than actions. This matches anchor 3 ("Names domain and 1-2 concrete actions, but not comprehensive"); it does not reach anchor 4 because capabilities like config creation, ignore-file setup, or pre-commit enforcement are never mentioned, and it is clearly above anchor 2 since the domain and tool are explicit. The malformed opening ("Execute automatically formats") further blurs the capability statement.

3 / 5

Completeness

Both questions are explicitly answered: the what is concrete ("formats and validates code files using Prettier and other formatting tools. Handles JavaScript, TypeScript, JSON, CSS, Markdown, and many other file types") and the when is explicit with quoted trigger phrases ("Use when users mention 'format my code', 'fix formatting', ..."). This directly matches anchor 5 ("Clearly and explicitly answers both what AND when with concrete trigger phrases") and is clearly above anchor 4, where the 'when' would be less explicit.

5 / 5

Trigger Term Quality

It includes six natural phrases users would actually say: "format my code", "fix formatting", "apply code style", "check formatting", "make code consistent", or "clean up code formatting" — good keyword coverage matching anchor 4. It falls short of anchor 5 ("comprehensive coverage of natural terms including synonyms and file extensions") because tool-invocation phrasings like "run Prettier" and file-extension triggers (e.g., ".js", ".ts") are absent, though "Prettier" itself is named in the capability sentence.

4 / 5

Distinctiveness Conflict Risk

Code formatting with Prettier is a clear, well-scoped niche and most trigger phrases ("fix formatting", "clean up code formatting") are formatting-specific, matching anchor 4 ("Mostly distinct; minor overlap risk with closely related skills"). It does not reach anchor 5 because phrases like "apply code style" and "check formatting" could overlap with linting/style-guide skills, and the open-ended "many other file types" broadens the claimed scope slightly.

4 / 5

Total

16

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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

14

/

16

Passed

Repository

jeremylongshore/tons-of-skills-marketplace

Path

plugins/examples/formatter/skills/code-formatter/SKILL.md

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.