菜单
Use when the user asks to extract captions, subtitles, or transcribe audio/speech from a video file. Triggers on "extract captions", "transcribe video", "get subtitles", "transcrever vídeo", "legendas do vídeo", or when a video file path is provided alongside a transcription request.
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。
| name | video-captions |
| description | Use when the user asks to extract captions, subtitles, or transcribe audio/speech from a video file. Triggers on "extract captions", "transcribe video", "get subtitles", "transcrever vídeo", "legendas do vídeo", or when a video file path is provided alongside a transcription request. |
| disable-model-invocation | true |
Extract captions or subtitles from video files using video-captions (Whisper-based CLI).
| Option | Default | Description |
|---|---|---|
--language LANG | en | Source language code (en, pt, es, fr, …) |
--model MODEL | base | Model size: tiny, base, small, medium, large |
--format FORMAT | text | Output: text, srt, vtt, json |
--output FILE | stdout | Save to file instead of printing |
# Plain text to stdout
video-captions video.mp4
# Portuguese audio, small model
video-captions --language pt --model small video.mp4
# SRT file output
video-captions --format srt --output captions.srt video.mp4
# WebVTT with better accuracy
video-captions --model medium --format vtt talk.mkv
tiny / base — fast, good for short clips or clear speechsmall / medium — better accuracy, slower (recommended for accented speech)large — highest accuracy, requires more RAM (~10 GB)The base model is sufficient for most clear English audio. Use small or medium when:
Requires openai-whisper for Python 3.12:
pip install openai-whisper --break-system-packages
Use when working with Kubernetes clusters, manifests, and related tasks.
Read HANDOFF.md and continue from where we left off
Use when ending a session, completing a milestone, or stopping mid-task and context must be preserved for the next agent
Use when organizing raw content into slide-ready format, or when the user says "prepare slides", "structure this for a presentation", "brief for pptx".
Use when the user shares a URL or article and asks to extract key learnings, summarize topics, or generate a digest formatted for Google Chat, Slack, Discord, Telegram, or similar messaging tools. Accepts an optional format parameter.
Use when writing a CV, bio, LinkedIn post, or talk abstract for Silvio; when calibrating technical recommendations to Silvio's experience ("do I have experience with X?"); or when an introduction or speaker section is needed. Loads timeline, stack, credentials, and preferences on demand via the pointer table.