메뉴
When the user wants text-to-speech audio → generate voice files locally (macOS say + afconvert, outputs m4a).
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
When prompt, tool, or agent logic changes need regression testing → run eval benchmarks to detect regressions or improvements.
When a task can be parallelized (bulk code review, multi-module refactor, batch analysis) → split into subtasks running in isolated git worktrees via multiple workers.
When the user wants to research academic papers → search ArXiv, extract PDFs, summarize/review/Q&A, generate experiment code.
When you need to interact with web pages using the user's logged-in browser → control Chrome via @playwright/cli daemon, reusing cookies/session with persistent tabs.
When user needs AnyGenIO content generation → unified CLI for task execution with progressive disclosure.
When you need to persist files (reports, docs, evidence) beyond the session → create/query/delete durable artifacts.
| name | audio-tts |
| description | When the user wants text-to-speech audio → generate voice files locally (macOS say + afconvert, outputs m4a). |
| triggers | {"intent_patterns":["语音|读出来|朗读|TTS|配音|发个语音","念.*出来|read.*aloud|speak.*this|说出来","转成.*语音|convert.*speech|text.*to.*speech|生成.*音频","帮我.*录|record.*voice|旁白|narration|voiceover","听.*版本|audio.*version|播报|broadcast"],"context_signals":{"keywords":["语音","朗读","tts","配音","音频","念","读","说","speech","voice","audio","播报"]},"confidence_threshold":0.6} |
| priority | 6 |
| requires_tools | ["bash","write"] |
| max_tokens | 200 |
| cooldown | 30 |
| output | {"format":"markdown","artifacts":true,"artifact_type":"audio"} |
使用 macOS 自带 say 生成语音，并转成 m4a。
say）afconvert（macOS 自带）python3 skills/audio-tts/run.py speak --text '你好，这是语音测试'
| 参数 | 类型 | 必填 | 说明 |
|---|---|---|---|
| text | string | 是 | 朗读文本 |
| voice | string | 否 | voice 名称（如 Ting-Ting / Samantha），默认空（系统默认） |
| rate | int | 否 | 语速 WPM（say 的 -r 参数） |
| output | string | 否 | 输出路径（默认 /tmp/tts_.m4a） |