fix

Use when you have lint errors, formatting issues, or before committing code to ensure it passes CI.

3.22x

Quality

—

Does it follow best practices?

Impact

100%

3.22x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

70%

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

The body is appropriately concise and well-organized for a simple skill, with executable commands. Its weaknesses are a vague final reporting step and the absence of a validation/re-run feedback loop for the lint-and-commit workflow, which is risky enough to warrant a checkpoint.

Suggestions

Make the final step executable, e.g. 'Run `yarn linc` again after manual fixes until no errors remain' instead of the vague 'Report any remaining manual fixes needed'.

Add an explicit validation checkpoint: re-run lint after fixes and only proceed to commit when it passes cleanly.

Note that `yarn linc` may be a typo for `yarn lint`; verify the command is correct so the guidance is copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: three terse numbered commands and a short common-mistakes list, with every token earning its place and no padding or explanation of concepts Claude already knows.	3 / 3
Actionability	It gives concrete executable commands ('yarn prettier', 'yarn linc') but the final step 'Report any remaining manual fixes needed' is vague guidance rather than an executable instruction, leaving it incomplete versus fully copy-paste ready.	2 / 3
Workflow Clarity	Steps are clearly numbered and sequenced, but there is no validation checkpoint after the lint check — the skill merely says 'report' remaining issues without a fix-and-revalidate loop, and linting that gates CI is a context where missing feedback caps clarity at 2.	2 / 3
Progressive Disclosure	This is a simple under-50-line skill with no external references needed; the content is well-organized into clear Instructions and Common Mistakes sections, which the rubric's simple-skill note allows to score 3.	3 / 3
	Total	10 / 12 Passed

Description

67%

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

The description uses third person, has an explicit 'Use when...' trigger covering both what and when, and includes reasonably natural trigger terms. It is limited by a lack of multiple concrete named actions and slight overlap risk with broad pre-commit workflows.

Suggestions

Enumerate specific concrete actions the skill performs (e.g., 'runs prettier and eslint, reports unfixable violations') to lift specificity to 3.

Add common user phrasings like 'linting', 'code style', or 'format my code' to broaden trigger-term coverage.

Sharpen the trigger to reduce overlap, e.g. 'Use when fixing lint/formatting failures before pushing or in CI' rather than the broad 'before committing code'.

Dimension	Reasoning	Score
Specificity	It names the domain (lint errors, formatting issues, CI) and an action (passes CI) but does not enumerate multiple concrete actions like specific fix commands, capping it at 'names domain and some actions, but not comprehensive'.	2 / 3
Completeness	It explicitly states what it does (fix lint errors, formatting issues, ensure CI passes) and when to use it ('Use when you have lint errors, formatting issues, or before committing code'), clearly answering both what AND when with an explicit trigger clause.	3 / 3
Trigger Term Quality	It includes natural terms a user might say ('lint errors', 'formatting issues', 'before committing code', 'CI'), but misses common variations like 'linting', 'code style', or 'prettier'; relevant keywords present but not comprehensive.	2 / 3
Distinctiveness Conflict Risk	The trigger space (lint/formatting/CI) is somewhat specific but 'before committing code' is broad and could overlap with general pre-commit or formatting skills, so it sits at 'somewhat specific but could still overlap with similar skills'.	2 / 3
	Total	9 / 12 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: facebook/react
Commit: e71a639

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.