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.
71
56%
Does it follow best practices?
Impact
99%
2.15xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/react-native-skills/SKILL.mdQuality
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 solid skill description that clearly identifies its domain (React Native/Expo), provides explicit trigger guidance, and occupies a distinct niche. Its main weakness is that the capability descriptions are somewhat categorical rather than listing highly specific concrete actions, which keeps specificity from reaching the top score.
Suggestions
Add more specific concrete actions such as 'optimize FlatList/SectionList rendering, configure Reanimated animations, bridge native modules, manage Expo config plugins' to increase specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (React Native/Expo) and mentions some actions like 'building components', 'optimizing list performance', 'implementing animations', 'working with native modules', but these are somewhat general categories rather than multiple specific concrete actions (e.g., doesn't specify FlatList optimization, Reanimated usage, bridging patterns, etc.). | 2 / 3 |
Completeness | Clearly answers both 'what' (best practices for building performant mobile apps, components, list performance, animations, native modules) and 'when' with explicit triggers ('Use when building React Native components...', 'Triggers on tasks involving...'). | 3 / 3 |
Trigger Term Quality | Good coverage of natural terms users would say: 'React Native', 'Expo', 'mobile performance', 'native modules', 'animations', 'list performance', 'native platform APIs'. These are terms developers would naturally use when seeking help with mobile app development. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to React Native and Expo mobile development, which is a distinct niche. The combination of 'React Native', 'Expo', 'native modules', and 'mobile performance' makes it unlikely to conflict with general web development or other framework skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill functions as a table of contents or index rather than an actionable skill document. While it is well-organized with clear categorization and priority levels, it contains zero executable code, no concrete examples, and no workflow guidance — all the actual content is deferred to referenced files that aren't provided. As a standalone skill, it gives Claude almost nothing actionable to work with.
Suggestions
Add at least one concrete, executable code example per high-priority category (e.g., FlashList usage for list performance, Reanimated animation pattern) directly in the SKILL.md
Include a brief workflow or decision tree for common scenarios (e.g., 'When optimizing a slow list: 1. Switch to FlashList, 2. Memoize items, 3. Profile with Flipper')
Replace the generic 'Each rule file contains' description with inline summaries of the most critical rules, so the skill is useful even without the referenced files
Provide the bundle files (rule markdown files, AGENTS.md) so the progressive disclosure structure actually delivers value, or inline the most important content
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably organized but includes some unnecessary framing (e.g., 'Comprehensive best practices', 'When to Apply' section listing obvious triggers). The priority table and quick reference lists are efficient, but the 'Each rule file contains' section explains things Claude can infer. Could be tightened. | 2 / 3 |
Actionability | The skill is essentially an index/table of contents with no executable code, no concrete examples, and no specific instructions. It tells Claude to 'read individual rule files' but provides no actionable guidance itself — it describes rather than instructs. | 1 / 3 |
Workflow Clarity | There is no workflow, sequence, or process described. The skill is purely a catalog of rule names with no guidance on how to apply them, in what order, or how to validate outcomes. For a skill covering performance optimization and animations, some workflow guidance would be expected. | 1 / 3 |
Progressive Disclosure | The structure attempts progressive disclosure by referencing individual rule files and a compiled AGENTS.md, which is good design. However, since no bundle files are provided, the references cannot be verified. The overview itself is well-organized with clear categories, but the references are only lightly signaled (just file paths, no descriptions of what each contains beyond a generic template). | 2 / 3 |
Total | 6 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- vercel-labs/agent-skills
- Commit
b9c8ee0
- 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.