No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by ThendCN · Codex Skill · ★ 97
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is ai-team-skills safe to install? View the security audit →
AI Team Skills for Claude Code 中文 | English 将 Gemini CLI 和 Codex CLI 集成为 Claude Code 的 skill，让 Claude Code 能够： 委派 UI 设计任务给 Gemini gemini-3-pro-preview（gemini-agent） 委派代码编写/审查任务给 Codex gpt-5.3-codex（codex-agent） 编排多 Agent 协作流水线（ai-team） 架构 Skills ai-team 多 Agent 协作流水线，自动编排 Claude (Lead) + Codex (代码) + Gemini (UI)。 适用于全栈开发、大型重构、UI→实现联动等需要多 agent 协作的场景。 流水线模板： gemini-agent Gemini (gemini-3-pro-preview) AI 代理 - UI 设计与前端开发专家。 包装脚本：（Linux/macOS）、（Windows） Prompt 模板： codex-agent Codex (gpt-5.3-codex, reasoning: high) AI 代理 - 代码编写与实现专家。支持 exec（编写）和 review（审查）两种模式。 包装脚本：（Linux/macOS）、（Windows） Prompt 模板： 支持 review 模式： 审查未提交变更 支持并行任务拆分，提升长时间任务效率 协作模式 单 Agent 委派 Claude Code 分析任务 → 构建 prom
| Stars | 97 |
| Forks | 5 |
| Language | PowerShell |
| Category | Codex Skill |
| Quality Score | 59.9078823145828/100 |
| Last Updated | 2026-02-24 |
| Created | 2026-02-09 |
| Platforms | claude-code, codex, gemini |
| Est. Tokens | ~4k |
Explore other popular codex skill tools:
ai-team-skills is AI Team Skills for Claude Code - Gemini (UI design) + Codex (code implementation). It is categorized as a Codex Skill with 97 GitHub stars.
ai-team-skills is primarily written in PowerShell.
You can find installation instructions and usage details in the ai-team-skills GitHub repository at github.com/ThendCN/ai-team-skills. The project has 97 stars and 5 forks, indicating an active community.
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: