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).
92
Quality
91%
Does it follow best practices?
Impact
96%
1.07xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description with excellent trigger terms and completeness. The explicit 'Must use when' clause with file extensions provides clear activation criteria. The main weakness is that capabilities are described as topic areas rather than specific actions Claude can perform.
Suggestions
Replace category listings with concrete actions, e.g., 'Guides custom hook creation, debugs useEffect dependencies, recommends ref patterns' instead of 'Provides React patterns for hooks, effects, refs'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (React) and lists several areas covered (hooks, effects, refs, component design, escape hatches, anti-patterns) but these are categories rather than concrete actions like 'create custom hooks' or 'debug useEffect dependencies'. | 2 / 3 |
Completeness | Clearly answers both what ('Provides React patterns for hooks, effects, refs, and component design. Covers escape hatches, anti-patterns, and correct effect usage') and when ('Must use when reading or writing React components (.tsx, .jsx files with React imports)'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'React', 'hooks', 'effects', 'refs', 'component', '.tsx', '.jsx', and 'React imports' - covering both conceptual terms and file extensions users encounter. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche - specifically targets React components with explicit file type triggers (.tsx, .jsx) and React-specific concepts (hooks, effects, refs), unlikely to conflict with general JavaScript or other framework skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality React skill that provides excellent actionable guidance through concrete BAD/GOOD code comparisons. The content is concise, assumes Claude's competence, and includes a helpful decision tree for workflow clarity. The main weakness is the monolithic structure - at this length, splitting into focused reference files would improve navigation.
Suggestions
Consider splitting detailed sections (Effect Dependencies, Refs, Custom Hooks) into separate reference files, keeping SKILL.md as a concise overview with links
Add a 'Quick Reference' section at the top with the decision tree, moving detailed examples to linked files for progressive disclosure
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient, using code examples to demonstrate patterns rather than explaining what React or hooks are. Every section provides actionable patterns without unnecessary preamble or concepts Claude already knows. | 3 / 3 |
Actionability | Provides fully executable, copy-paste ready code examples throughout. Each anti-pattern is paired with a concrete 'GOOD' alternative, making it immediately clear what to do and what to avoid. | 3 / 3 |
Workflow Clarity | The decision tree at the end provides an explicit workflow for choosing the right approach. For a patterns/best-practices skill, this is the appropriate level of workflow guidance - it's not a multi-step process requiring validation checkpoints. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear sections, but it's a long monolithic document (~350 lines). Some sections like 'Effect Dependencies' or 'Refs' could be split into separate reference files with the main skill providing an overview and links. | 2 / 3 |
Total | 11 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 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 | 10 / 11 Passed | |
- Repository
- NeverSight/skills_feed
- Commit
5342bca
- 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.