AgentHubAgentHub

speech

SkillGitHub

io.github.openai/skills/speech · vmain

Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI (`scripts/text_to_speech.py`) with built-in voices and require `OPENAI_API_KEY` for live calls. Custom voice creation is out of scope.

在 GitHub 查看 ↗源仓库 ↗

概览

speech 是一个Agent Skill，收录自 GitHub。本页提供 Cursor、Claude Code 等客户端的安装配置片段。

Agent Skill 是带 SKILL.md 的指令包。安装后，AI 会根据 description 在匹配任务时自动加载，无需每次手动粘贴提示词。

安装

选择你的平台查看安装方式

# 通用 CLI（Cursor / Claude Code / Codex 等均支持）
npx skills add openai/skills@speech

使用方式

安装完成后，在对话中直接描述你的任务（或提及技能名称）。Agent 会先读取 SKILL.md 的 description 判断是否启用，再按其中的步骤执行。可用 /skills（Claude Code）或在设置中查看已加载的 Skills。

相关资源

winui-app

vmain

SkillGitHub

io.github.openai/skills/winui-app

Bootstrap, develop, and design modern WinUI 3 desktop applications with C# and the Windows App SDK using official Microsoft guidance, WinUI Gallery patterns, Windows App SDK samples, and CommunityToolkit components. Use when creating a brand new app, preparing a machine for WinUI, reviewing, refactoring, planning, troubleshooting, environment-checking, or setting up WinUI 3 XAML, controls, navigation, windowing, theming, accessibility, responsiveness, performance, deployment, or related Windows app design and development work.

source
在 GitHub 查看

security-threat-model

vmain

SkillGitHub

io.github.openai/skills/security-threat-model

Repository-grounded threat modeling that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, and writes a concise Markdown threat model. Trigger only when the user explicitly asks to threat model a codebase or path, enumerate threats/abuse paths, or perform AppSec threat modeling. Do not trigger for general architecture summaries, code review, or non-security design work.

source
在 GitHub 查看

统一 Manifest

{
  "id": "io.github.openai/skills/speech",
  "type": "skill",
  "version": "main",
  "displayName": "speech",
  "description": "Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI (`scripts/text_to_speech.py`) with built-in voices and require `OPENAI_API_KEY` for live calls. Custom voice creation is out of scope.",
  "author": {
    "name": "openai",
    "url": "https://github.com/openai"
  },
  "repository": {
    "url": "https://github.com/openai/skills",
    "source": "github",
    "subfolder": "skills/.curated/speech"
  },
  "homepage": "https://github.com/openai/skills/tree/main/skills/.curated/speech",
  "distribution": {
    "packages": [
      {
        "registryType": "source",
        "identifier": "openai/skills@speech",
        "version": "main",
        "runtimeHint": "npx skills add"
      }
    ],
    "remotes": []
  },
  "dependencies": [],
  "installTargets": [
    "claude-code",
    "claude-desktop",
    "cursor",
    "codex",
    "vscode"
  ],
  "keywords": [],
  "provenance": {
    "origin": "github",
    "originalId": "openai/skills/speech",
    "originalUrl": "https://github.com/openai/skills/tree/main/skills/.curated/speech",
    "isOfficial": false,
    "status": "active"
  }
}
speech — Agent Skill 安装与配置 · AgentHub