react-native-architecture
Build production React Native apps with Expo, navigation, native modules, offline sync, and cross-platform patterns. Use when developing mobile apps, implementing native integrations, or architecting React Native projects.
60
71%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./tests/ext_conformance/artifacts/agents-wshobson/frontend-mobile-development/skills/react-native-architecture/SKILL.mdQuality
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 a strong skill description that concisely covers specific capabilities, includes natural trigger terms, and explicitly states both what the skill does and when to use it. It uses proper third-person voice and is clearly distinguishable from other skills. The description is well-structured and follows the pattern of good examples in the rubric.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and domains: 'Build production React Native apps with Expo, navigation, native modules, offline sync, and cross-platform patterns.' This covers several distinct capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Build production React Native apps with Expo, navigation, native modules, offline sync, and cross-platform patterns') and when ('Use when developing mobile apps, implementing native integrations, or architecting React Native projects'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'React Native', 'Expo', 'mobile apps', 'native modules', 'navigation', 'offline sync', 'cross-platform'. These are terms developers naturally use when seeking help with mobile development. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to React Native/Expo mobile development with specific triggers like 'native modules', 'offline sync', and 'React Native projects' that distinguish it from general web development or other mobile frameworks. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides highly actionable, executable code patterns covering a broad range of React Native/Expo topics, which is its primary strength. However, it is excessively verbose—much of the content (comparison tables, do's/don'ts, repetitive platform checks) is knowledge Claude already possesses. The monolithic structure with no supporting bundle files makes this a poor fit for the progressive disclosure model, and the lack of validation checkpoints in workflows (especially around builds and deployments) is a notable gap.
Suggestions
Split the six patterns into separate referenced files (e.g., NAVIGATION.md, AUTH.md, OFFLINE.md, NATIVE_MODULES.md) and keep SKILL.md as a concise overview with links to each.
Remove the 'When to Use This Skill' section, the Expo vs Bare RN comparison table, and the Do's/Don'ts list—Claude already knows these concepts and they consume significant tokens.
Add explicit validation checkpoints to the Quick Start and EAS Build workflows (e.g., 'Run npx expo start to verify setup before proceeding', 'Check build status with eas build:list').
Consolidate the haptics service into a single generic function with a style parameter instead of repeating the Platform.OS check five times.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines. The Expo vs Bare RN comparison table, the 'When to Use This Skill' section, and the Do's/Don'ts list all explain things Claude already knows. The haptics service wrapper repeats the same Platform.OS check pattern 5 times. Much of this could be cut by 60%+ without losing actionable value. | 1 / 3 |
Actionability | All code examples are fully executable TypeScript with proper imports, concrete configurations (eas.json), and real CLI commands. The patterns cover complete implementations including auth flow, offline-first setup, and push notifications that are copy-paste ready. | 3 / 3 |
Workflow Clarity | The Quick Start section provides a clear sequence for project setup, and EAS Build commands are well-ordered. However, there are no validation checkpoints—no steps to verify the build succeeded, no error recovery guidance for failed builds or OTA updates, and no testing/verification steps between creating the project and deploying it. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no bundle files to offload content into. All six patterns, the EAS config, best practices, and resources are crammed into a single file. The auth flow, offline-first setup, and native module patterns each warrant their own referenced files, but no such structure exists. | 1 / 3 |
Total | 7 / 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 (674 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- Dicklesworthstone/pi_agent_rust
- Commit
895269a
- 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.