菜单
Transcribe speech using local STT. Use when the user wants voice input or offline audio transcription.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Capture the screen and inject a short text summary into Claude's context via an in-process VLM (llama-cpp-python). No daemon. Use to feed terminal/editor/browser state to Claude for debug, fix suggestions, or summarization with minimal token cost.
Speak text aloud using local TTS. Use when the user wants Claude's output read aloud or to toggle auto-read mode.
| name | listen |
| description | Transcribe speech using local STT. Use when the user wants voice input or offline audio transcription. |
Transcribe speech using local speech-to-text.
/listen — start/stop listening via microphone/listen recording.wav — transcribe an audio file/listen --toggle — enable/disable auto-listen modepython -m cc_stt $ARGUMENTS
See .cc-senses.example.toml [stt] section for the full schema and CC_STT_* env overrides.
Prototype — config, engine protocol, mic capture, utterance buffer, PTY injection, and live listen pipeline are implemented.