react-native-expo
Build React Native 0.76+ apps with Expo SDK 52-54. Covers mandatory New Architecture (0.82+/SDK 55+), React 19 changes, SDK 54 breaking changes (expo-av, expo-file-system, Reanimated v4), and Swift iOS template. Prevents 16 documented errors. Use when building Expo apps, migrating to New Architecture, upgrading to SDK 54+, or fixing Fabric, TurboModule, propTypes, expo-updates crashes, or Swift AppDelegate errors.
Install with Tessl CLI
npx tessl i github:jezweb/claude-skills --skill react-native-expo87
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
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.
This is an excellent skill description that demonstrates all best practices. It provides highly specific technical details with version numbers, clearly lists what it covers and what errors it prevents, and includes an explicit 'Use when...' clause with natural trigger terms developers would actually search for. The description is concise yet comprehensive, using proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and technical details: 'Build React Native 0.76+ apps with Expo SDK 52-54', covers 'mandatory New Architecture', 'React 19 changes', 'SDK 54 breaking changes' with specific packages (expo-av, expo-file-system, Reanimated v4), and 'Swift iOS template'. Mentions preventing '16 documented errors'. | 3 / 3 |
Completeness | Clearly answers both what ('Build React Native 0.76+ apps with Expo SDK 52-54', covers specific technical areas) AND when with explicit 'Use when...' clause listing four distinct trigger scenarios: building Expo apps, migrating to New Architecture, upgrading to SDK 54+, or fixing specific error types. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'Expo apps', 'New Architecture', 'SDK 54+', 'Fabric', 'TurboModule', 'propTypes', 'expo-updates crashes', 'Swift AppDelegate errors'. These are specific technical terms developers would naturally use when encountering these issues. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with very specific version numbers (React Native 0.76+, 0.82+, Expo SDK 52-54, SDK 55+, React 19, Reanimated v4) and unique error types (Fabric, TurboModule, propTypes, expo-updates crashes, Swift AppDelegate). Unlikely to conflict with generic React or mobile development skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%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, production-ready skill with excellent actionability and clear workflows for React Native/Expo development. The comprehensive coverage of breaking changes with executable code examples is a major strength. However, the document is verbose in places and could benefit from splitting detailed reference content (like the 16 issues list) into separate files to improve token efficiency.
Suggestions
Move the 'Known Issues Prevention' section (16 issues) to a separate reference file like 'references/known-issues.md' and link to it from the main skill
Remove 'Why this matters' explanatory sections - Claude understands why New Architecture and Hermes matter without explanation
Condense the 'Common Patterns' section or move to a separate examples file, as the patterns are straightforward TypeScript/React code Claude can generate
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | While the skill is comprehensive and well-organized, it includes some unnecessary explanations (e.g., 'Why this matters' sections explaining concepts Claude knows) and could be tightened. The 'Knowledge Gap Filled' footer and some verbose explanations add tokens without proportional value. | 2 / 3 |
Actionability | Excellent actionability with fully executable code examples throughout, specific bash commands, copy-paste ready migration code, and concrete before/after comparisons. Every breaking change includes working code solutions. | 3 / 3 |
Workflow Clarity | The migration guide provides clear step-by-step sequences with explicit validation checkpoints (Step 4: Test Thoroughly with specific test items). The troubleshooting section and complete setup checklist provide feedback loops for error recovery. | 3 / 3 |
Progressive Disclosure | References external files (scripts/, references/, assets/) with clear signaling, but the main document is quite long (~800 lines) with content that could be split into separate files. The 16 documented issues section could be a separate reference file. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
75%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 12 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (1078 lines); consider splitting into references/ and linking | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 12 / 16 Passed | |
- 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.