by Turbo1123 · Codex Skill · ★ 127
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
雷鸟 iO / RayNeo iO 非官方 SDK：原生鸿蒙 HarmonyOS SDK/客户端、iOS 客户端及 iOS/Android 官方 App 扩展。自有模型、联网搜索、眼镜导航、录音研究、Codex 与 Web 预览，各平台能力以文档为准。面向开发者，仅供非商业学习研究；只提供源码，不提供 IPA/APK/HAP 或签名包。
| Stars | 127 |
| Forks | 40 |
| Language | Swift |
| Category | Codex Skill |
| Quality Score | 50.5410463457025/100 |
| Open Issues | 3 |
| Last Updated | 2026-09-18 |
| Created | 2026-09-08 |
| Platforms | browser, codex |
| Est. Tokens | ~15k |
These tools work well together with Turbo-IO for enhanced workflows:
Looking for a Turbo-IO alternative? If you're comparing Turbo-IO with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Open-source iOS app connecting Meta Ray-Ban smart glasses to AI — 5 backends (on-device MLX models, Apple Inte
Claude Code skills for Apple platform development (iOS, macOS, iPadOS) — product validation, code generation,
Fantasy Premier League Kotlin/Compose Multiplatform sample
Galway Bus Kotlin Multiplatform project using Jetpack Compose and SwiftUI
iOS development ClaudeCode plugin for mindful token and context usage. Contains modular MCPs that group variou
Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server
Explore other popular codex skill tools:
Turbo-IO is 雷鸟 iO / RayNeo iO 非官方 SDK：原生鸿蒙 HarmonyOS SDK/客户端、iOS 客户端及 iOS/Android 官方 App 扩展。自有模型、联网搜索、眼镜导航、录音研究、Codex 与 Web 预览，各平台能力以文档为准。面向开发者，仅供非商业学习研究；只提供源码，不提供 IPA/APK/HAP 或签名包。. It is categorized as a Codex Skill with 127 GitHub stars.
Turbo-IO is primarily written in Swift. It covers topics such as asr, bes2800, codex.
You can find installation instructions and usage details in the Turbo-IO GitHub repository at github.com/Turbo1123/Turbo-IO. The project has 127 stars and 40 forks, indicating an active community.
The top alternatives to Turbo-IO on Agent Skills Hub include OpenVision, claude-code-apple-skills, FantasyPremierLeague. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: