react-doctor

Run after making React changes to catch issues early. Use when reviewing code, finishing a feature, or fixing bugs in a React project.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

The canonical home for this skill is react-doctor in millionco/react-doctor

Quality

Content

100%

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

The body is a tight, well-organized skill with an executable command and a clear run-fix-rerun feedback loop; it uses tokens efficiently and needs no external reference files at this scope.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — no concept explanations, no padding, and every line (overview, one command, workflow) earns its place.	3 / 3
Actionability	Provides a fully executable, copy-paste-ready command (`npx -y react-doctor@latest . --verbose --diff`) with specific flags rather than pseudocode or abstract guidance.	3 / 3
Workflow Clarity	For a simple skill, the sequence is unambiguous and includes a feedback loop: run, fix errors first, then re-run to verify the score improved.	3 / 3
Progressive Disclosure	Under 50 lines with no external references needed; content is well-organized into clear Usage and Workflow sections, fitting the simple-skill exception.	3 / 3
	Total	12 / 12 Passed

Description

65%

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 strong explicit trigger guidance and decent natural keywords, but the capability statement is vague ('catch issues early') and the generic review/fix triggers create some overlap risk with broader code-quality skills.

Suggestions

Replace 'catch issues early' with the concrete capabilities from the body (e.g., 'Scans for security, performance, correctness, and architecture issues and outputs a 0-100 score') so the 'what' is specific.

Tighten the trigger clause to React-specific framing (e.g., 'Use after making React changes — when reviewing components, finishing a feature, or fixing bugs') to reduce overlap with generic code-review skills.

Dimension	Reasoning	Score
Specificity	Names the React domain and the action 'catch issues early', but the action is vague and not comprehensive — it omits the specific scan categories (security, performance, correctness, architecture) and the scoring behavior that the body actually delivers.	2 / 3
Completeness	The 'when' is explicit via the 'Use when' clause, but the 'what' ('catch issues early') is vague and does not clearly convey the scan-and-score behavior, so it does not clearly answer both halves.	2 / 3
Trigger Term Quality	'Use when reviewing code, finishing a feature, or fixing bugs in a React project' covers natural phrases a user would actually say when they need this kind of post-change check.	3 / 3
Distinctiveness Conflict Risk	The 'React project' qualifier narrows the niche, but 'reviewing code' and 'fixing bugs' are generic tasks that could overlap with general code-review or linting skills.	2 / 3
	Total	9 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: freekmurze/dotfiles
Path: config/claude/skills/react-doctor/SKILL.md
Commit: d0073bc

Reviewed: about 11 hours 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.