A community-driven registry for Claude, Cursor, Windsurf, Cline & more. Not affiliated with Anthropic.
Are you the author? Sign in to claim
Interview debrief skill for Claude Code — transcribe recordings, organize Q&A, generate evaluation, sync to Feishu docs
面试复盘 skill for Claude Code — 上传录音或转录文本,自动转录、整理问答、生成总评,保存到本地或飞书文档。
An interview debrief skill for Claude Code — upload a recording or transcript, get automatic transcription, Q&A summary, and evaluation, saved locally or to Feishu docs.
npx skills add realwooolf/voice-debrief
把录音文件路径发给 Claude,说「帮我整理这场面试」:
Paste the recording file path and say "帮我整理这场面试" (help me debrief this interview):
帮我整理这场面试 /Users/xxx/Desktop/面试录音.mp3
已有 PDF 转录文本也可以直接发过来,skill 会跳过转录阶段。
You can also pass an existing PDF transcript — the skill will skip transcription automatically.
# Apple Silicon Mac(推荐 / Recommended)
pip install mlx-whisper
brew install ffmpeg
# Other platforms
pip install faster-whisper
brew install ffmpeg # macOS
# sudo apt install ffmpeg # Ubuntu / Debian
# winget install ffmpeg # Windows
选择保存到飞书时需要配置,选本地保存可跳过。
Only required if you choose to save to Feishu. Skip if saving locally.
首次使用时 skill 会引导完成飞书自建应用配置(约 5 分钟),之后浏览器自动完成 OAuth 授权,无需重复操作。
On first use, the skill will guide you through setting up a Feishu app (~5 min). After that, OAuth is handled automatically.
| 平台 / Platform | 转录方式 / Engine | 速度 / Speed |
|---|---|---|
| Apple Silicon Mac (M1–M4) | mlx-whisper (GPU) | 41 min audio ≈ 3–5 min |
| Linux / Windows + NVIDIA GPU | faster-whisper (CUDA) | Auto-detected, fast |
| Intel Mac / No GPU | faster-whisper (CPU int8) | 2–4x faster than openai-whisper |
A Claude Code skill by Hao (駱君昊) that learns your Facebook voice and auto-posts to FB / IG / Threads / X with a 14-day c
1000+ skills curated from Anthropic, Vercel, Stripe, and other engineering teams
Claude Code skill for YouTube creators — channel audits, video SEO, retention scripts, thumbnails, content strategy, Sho
AI image generation skill for Claude Code -- Creative Director powered by Gemini