菜单
Extract screenshots from video at specific timestamps. Use when you need specific frames from a video for blog posts or other content.
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
/blog-schedule - Manage Post Schedule
Generate a blog post from source materials (text, PDFs, images, transcripts). Use when user wants to create a blog post or article.
Render carousel slides from social/carousel.md into 1080x1350 PNG images.
Push blog posts to Google Docs for review, then pull comments and suggestions back as feedback for discussion.
Generate AI images for content using Gemini or other image generation APIs. Use when user needs diagrams, illustrations, or visual content.
Initialize a new content project with the standard directory structure in projects). Use when user wants to create a new blog post and one doesn't exist for it.
| name | content-screenshot |
| description | Extract screenshots from video at specific timestamps. Use when you need specific frames from a video for blog posts or other content. |
Extract screenshots from video at specific timestamps.
/content-screenshot <video_path> <timestamp1> [timestamp2] [timestamp3] ...
All formats supported:
1:30 or 01:30 (MM:SS)1:30:45 (HH:MM:SS)90 or 90s (seconds)# Single screenshot at 1 minute 30 seconds
VIDEO=$(ls source/*.mp4 2>/dev/null | head -1)
uv run .claude/skills/content-screenshot/scripts/screenshot.py "$VIDEO" screenshots 1:30
# Multiple screenshots
uv run .claude/skills/content-screenshot/scripts/screenshot.py "$VIDEO" screenshots 0:45 2:15 5:30 10:00
Screenshots saved to output directory with timestamp names:
screenshot-00m45s.pngscreenshot-02m15s.pngscreenshot-05m30s.pngThis skill is typically called by the blog generation process:
/content-transcribe creates transcript and chapters/content-screenshot extracts specific frames