fix

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

3.22x

Quality

66%

Does it follow best practices?

Impact

100%

3.22x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/fix/SKILL.md

Quality

Content

86%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.

The body is an exemplary lean instruction card: concrete commands, a clear fix-check-report sequence, and useful warnings against real failure modes. Its only notable gap is that it stops at 'check for remaining lint issues' without saying how to actually resolve them.

Dimension	Reasoning	Score
Conciseness	The 17-line body is lean and efficient with zero padding: a numbered 3-step instruction list and two terse common-mistakes bullets, each earning its place. No concepts Claude already knows are explained.	5 / 5
Actionability	Steps 1-2 give concrete, executable commands ('yarn prettier', 'yarn linc'), but step 3 ('Report any remaining manual fixes needed') and the mistakes section say to fix lint errors without giving any concrete fix procedure or command. Anchor 4 'mostly executable guidance; concrete code or commands with minor gaps'.	4 / 5
Workflow Clarity	Clear 3-step sequence with an explicit check step (run linc to catch remaining issues, then report), and the mistakes section reinforces the 'fix before committing' gate. Not level 5 because there is no fix-and-recheck loop for errors surfaced in step 2.	4 / 5
Progressive Disclosure	A simple, single-purpose skill under 50 lines with no bundle files (references/, scripts/, assets/ do not exist) and no need for external references; the two well-organized sections fully cover it, which satisfies the simple-skill exception.	5 / 5
	Total	18 / 20 Passed

Description

47%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.

The description has good natural trigger coverage but is structurally incomplete: it tells Claude when to use the skill without saying what the skill actually does. Adding one sentence of concrete actions (e.g., 'Runs prettier to format changed files and linc to catch remaining lint errors') would lift both completeness and specificity.

Suggestions

State the 'what' explicitly: prepend concrete actions like 'Fix lint and formatting issues by running prettier and lint checks' before the 'Use when' clause.

Include tool and workflow keywords users would recognize — e.g., 'prettier', 'eslint', 'yarn', 'pre-commit' — to strengthen trigger coverage and distinctiveness.

Distinguish the skill from generic code-review/commit skills by mentioning it operates on changed files in a yarn-based repo.

Dimension	Reasoning	Score
Specificity	The description names the domain ('lint errors, formatting issues', 'CI') but never states any concrete action the skill performs — what it does is only implied. This matches the anchor 'Names the domain but actions are minimal or generic', not level 3 which requires 1-2 explicit actions.	2 / 5
Completeness	The description is essentially one long 'when' clause ('Use when you have lint errors... or before committing code'); the 'what' is never explicitly stated, only weakly implied via 'to ensure it passes CI'. This mirrors the level-2 example 'Use when working with documents'.	2 / 5
Trigger Term Quality	'lint errors', 'formatting issues', 'before committing', and 'CI' are phrases users would naturally say. Not level 5 because common synonyms and tool names (eslint, prettier, style issues, pre-commit) are missing.	4 / 5
Distinctiveness Conflict Risk	The lint-and-format-before-commit niche is mostly distinct with clear triggers, though it has minor overlap risk with code-review and commit-related skills. Not level 5 because the description omits tool-specific terms (yarn/prettier/linc) that would fully disambiguate it.	4 / 5
	Total	12 / 20 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
Path: .claude/skills/fix/SKILL.md
Commit: 7c6ac13

Reviewed: 3 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.