react-best-practices

Provides React patterns for hooks, effects, refs, and component design. Covers escape hatches, anti-patterns, and correct effect usage. Must use when reading or writing React components (.tsx, .jsx files with React imports).

1.07x

Quality

—

Does it follow best practices?

Impact

96%

1.07x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

92%

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

A high-quality, code-driven best-practices reference with excellent actionability, conciseness, and a clear decision-tree workflow. The only notable gap is progressive disclosure: the large single-file body could benefit from splitting detailed pattern catalogs into one-level-deep reference files.

Suggestions

Split the larger pattern groups (Effects, Refs, Custom Hooks) into one-level-deep reference files (e.g. references/EFFECTS.md, references/REFS.md) and keep SKILL.md as a concise overview with clearly signaled links, so the body is not a monolithic 565-line wall.

Add a short 'Quick reference' or table-of-contents block near the top pointing to each section, improving in-file navigation now that all content lives in one file.

Dimension	Reasoning	Score
Conciseness	Lean and code-dense: nearly every section is a tight BAD/GOOD TSX pair with minimal prose, and it avoids explaining React basics Claude already knows; the closing decision tree recap is concise. Not a 2 because there is no padding or unnecessary concept explanation.	3 / 3
Actionability	Concrete, executable TSX examples throughout (e.g. the updater-function, key-reset, and useEffectEvent patterns) with specific do/don't pairs rather than pseudocode or vague direction.	3 / 3
Workflow Clarity	The 'Summary: Decision Tree' provides a clear numbered sequence (1-7) for choosing the right pattern, and the skill contains no destructive or batch operations that would demand validation checkpoints, so the missing-checkpoint cap does not apply.	3 / 3
Progressive Disclosure	Sections are well-organized with clear headers, but the entire 565-line reference is inline in SKILL.md with no split-out reference files — content that could live one level deep (e.g. an EFFECTS.md or REFS.md) is not separated. Not a 1 because organization is good; not a 3 because nothing is split across files.	2 / 3
	Total	11 / 12 Passed

Description

90%

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 states capabilities and provides an explicit, file-extension-based trigger. The only weakness is that the action verbs ('Provides', 'Covers') are somewhat abstract rather than naming concrete operations.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete areas ('hooks, effects, refs, and component design', 'escape hatches, anti-patterns'), but the verbs 'Provides' and 'Covers' are abstract rather than the concrete actions (extract/fill/merge) the top anchor calls for.	2 / 3
Completeness	Explicitly answers what ('Provides React patterns for hooks, effects, refs, and component design') and when ('Must use when reading or writing React components (.tsx, .jsx files with React imports)'), with an explicit trigger clause.	3 / 3
Trigger Term Quality	Strong natural terms users would actually say — 'React', 'hooks', 'effects', 'refs', 'component', '.tsx', '.jsx files with React imports' — giving good coverage of common phrasings.	3 / 3
Distinctiveness Conflict Risk	A clear React-specific niche with distinct file-extension triggers (.tsx, .jsx with React imports), making it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 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
skill_md_line_count	SKILL.md is long (571 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: NeverSight/skills_feed
Commit: 26d37ce

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.