expo-skill-eval

Evaluate Expo skills for trigger accuracy, code quality, and runtime rendering.

Updated Apr 14, 2026
One-click install
npx skills add https://github.com/KOU050223/animeishi --skill expo-skill-eval
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: expo-skill-eval
Source: https://github.com/KOU050223/animeishi/tree/main/.agents/skills/expo-skill-eval
Command: npx skills add https://github.com/KOU050223/animeishi --skill expo-skill-eval

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires expo, bun, python3, python3-pip, python3-dev, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill provides an end-to-end evaluation of Expo skills, including trigger accuracy, generated code quality, and runtime rendering on iOS and Android simulators. It helps in verifying skill outputs, benchmarking, and ensuring correct rendering.

Core Features & Use Cases

  • Skill Evaluation: Trigger accuracy, generated code quality, and runtime rendering assessment.
  • Platforms: Supports iOS, Android, and optionally web for visual rendering verification.
  • Use Case: When you need to evaluate a new Expo skill, this tool can be used to ensure it generates working code, performs accurately, and renders correctly on different platforms.

Quick Start

Run the expo-skill-eval skill with the following command to evaluate the skill 'expo-ui':

expo-skill-eval <skill-name>

Frequently Asked Questions about expo-skill-eval

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I evaluate Expo skill trigger accuracy and code quality?

Expo skill evaluation involves running automated Python scripts that perform static checks on generated code and verify trigger accuracy. This Skill automates that process, providing metrics on code quality and trigger performance for Expo skills.

Can I test Expo runtime rendering on both iOS and Android simulators?

Testing Expo runtime rendering on iOS and Android simulators is fully supported. The Skill requires macOS with Xcode and Android SDK with emulators to perform visual rendering verification across platforms using Expo Go or development builds.

What do I need to run end-to-end evaluation of Expo skills?

Running end-to-end evaluation of Expo skills requires bun, python3, python3-pip, python3-dev, and macOS with Xcode and Android SDK with emulators. These dependencies enable both static code quality checks and runtime rendering verification.

Does Expo skill evaluation work with multiple Expo SDK versions?

Expo skill evaluation supports multiple Expo SDK versions. The Skill is designed to accommodate different SDK releases, allowing you to benchmark and verify trigger accuracy and rendering across varying Expo environments.

What is the best way to benchmark Expo skills for rendering correctness?

Benchmarking Expo skills for rendering correctness is best achieved using an end-to-end evaluation tool that performs runtime checks on iOS, Android, and optionally web. This Skill uses Python scripts and Expo Go to automate visual rendering verification.

Why does Expo skill evaluation require macOS and Xcode?

Expo skill evaluation requires macOS and Xcode because it performs runtime rendering checks on iOS simulators. Verifying that generated code renders correctly on Apple platforms requires direct access to the iOS simulator environment provided by Xcode.