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。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/javimosch/open-claw-skills --skill whisnap命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
正在显示 SKILL.md
| name | whisnap |
| description | macOS CLI for transcribing audio and video files using local Whisper models or Whisnap Cloud. |
| homepage | https://whisnap.com |
| metadata | {"clawdbot":{"emoji":"🎙️","requires":{"bins":"[Truncated]"},"install":["[Truncated]"]}} |
Use whisnap for transcribing audio/video files from the terminal. Requires the Whisnap macOS app with at least one model downloaded.
Setup (once)
/usr/local/bin/whisnap symlink)Common commands
whisnap recording.wavwhisnap meeting.mp4whisnap recording.wav --cloudwhisnap lecture.m4a --jsonwhisnap interview.wav -m small-q5_1whisnap recording.wav --cloud --jsonwhisnap --list-modelswhisnap recording.wav -vSupported formats
Flags
-c, --cloud — Use Whisnap Cloud instead of local model (requires sign-in)-m, --model <ID> — Override model (e.g., small-q5_1). Defaults to app's selected model.-j, --json — Structured JSON output with text, segments, timestamps, model info-v, --verbose — Print progress and diagnostics to stderr--list-models — List available models and exitJSON output format
{
"text": "transcribed text",
"segments": [{ "start_ms": 0, "end_ms": 1000, "text": "segment" }],
"model": "small-q5_1",
"backend": "whisper",
"processing_time_ms": 5000
}
Notes
~/Library/Application Support/com.whisnap.desktop/).--json and pipe stdout. Diagnostics go to stderr.0 = success, 1 = error.