vercel-react-native-skills

React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.

2.15x

Quality

82%

Does it follow best practices?

Impact

99%

2.15x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

The canonical home for this skill is vercel-react-native-skills in vercel-labs/agent-skills

Quality

Content

65%

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 well-organized, concise rule catalog with a priority table and clear category prefixes, but it stops at terse directives and relies on rule files that are not present in the bundle. Actionability, workflow clarity, and progressive disclosure all suffer from the missing referenced files.

Suggestions

Include the referenced bundle (rules/*.md files and AGENTS.md) or, if omitted intentionally, inline a minimal executable code example for at least the CRITICAL list-performance rules so the body is self-sufficient.

Add a brief validation/checkpoint step for any destructive or batch-oriented rules (e.g., verifying list behavior after migrating to FlashList) so the workflow is more than a lookup.

Make the 'Full Compiled Document' / rule-file references resolvable by shipping those files in references/, or remove the references and inline a compact quick-start with concrete code.

Dimension	Reasoning	Score
Conciseness	The body is a lean rule index — a priority table plus one-line directives like 'Use FlashList for large lists' — that assumes Claude's competence and avoids explaining concepts Claude knows, matching the level-3 lean/efficient anchor rather than the padded level-2.	3 / 3
Actionability	Directives are concrete ('Animate only transform and opacity', 'Memoize list item components') but the body contains no executable code or examples, delegating those to referenced rule files; this fits 'some concrete guidance but incomplete' rather than the copy-paste-ready level 3.	2 / 3
Workflow Clarity	The 'How to Use' section explains that rule files contain incorrect/correct examples, but there is no sequenced multi-step process or validation checkpoints; it reads as a lookup reference rather than a guided workflow, matching the level-2 'steps listed but checkpoints missing' anchor.	2 / 3
Progressive Disclosure	References are well-signaled and one level deep ('rules/list-performance-virtualize.md', 'AGENTS.md'), but the bundle contains no references/, scripts/, assets/, rules/, or AGENTS.md files, so the overview points to detailed materials that are not actually present — structure is good but the references cannot be verified, fitting level 2.	2 / 3
	Total	9 / 12 Passed

Description

100%

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: it states concrete capabilities, gives explicit 'Use when' and 'Triggers on' guidance, uses natural trigger terms, and occupies a clear React Native/Expo niche. Voice is appropriately third-person with no over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'building React Native components, optimizing list performance, implementing animations, or working with native modules' — matching the anchor for multiple specific concrete actions rather than the single-domain level 2.	3 / 3
Completeness	Explicitly answers both what ('best practices for building performant mobile apps') and when ('Use when ... Triggers on ...'), satisfying the level-3 anchor for explicit triggers rather than the implied-when level 2.	3 / 3
Trigger Term Quality	Covers natural terms users would say — 'React Native, Expo, mobile performance, or native platform APIs' — with good breadth; not merely jargon or a single keyword, so it clears the level-2 'some relevant keywords' bar.	3 / 3
Distinctiveness Conflict Risk	Narrow React Native/Expo mobile niche with distinct triggers ('React Native, Expo, mobile performance, native platform APIs') makes conflict with unrelated skills unlikely, matching the level-3 clear-niche anchor.	3 / 3
	Total	12 / 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: zhukunpenglinyutong/desktop-cc-gui
Path: .agents/skills/vercel-react-native-skills/SKILL.md
Commit: 5347fbb

Reviewed: about 14 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.