--- name: video-summary version: 1.6.4 description: "Video summarization for Bilibili, Xiaohongshu, Douyin, and YouTube. Extract insights from video content through transcription and summarization."

🔒 Security Declaration

This skill downloads videos/subtitles from YouTube/Bilibili/Xiaohongshu/Douyin.

It does NOT directly call external LLM APIs - it outputs structured requests for agent processing.

OPENAI_API_KEY and OPENAI_BASE_URL are optional - used by agent, not by this script.

Cookie files are read locally only, never transmitted externally.

No config files written. No secrets stored. No telemetry, no analytics.

metadata: openclaw: requires: bins: ["yt-dlp", "jq", "ffmpeg", "ffprobe", "bc"] credentials: - name: "OPENAI_API_KEY" required: false description: "API key for LLM summarization (optional, script outputs request for agent processing)" - name: "OPENAI_BASE_URL" required: false description: "Custom API endpoint (e.g., for Zhipu, DeepSeek)" - name: "VIDEO_SUMMARY_COOKIES" required: false description: "Path to cookies file for restricted video content" behavior: networkAccess: indirect description: "Downloads videos/subtitles from video platforms using yt-dlp. Summarization requests are output as structured text for agent/external LLM processing. Script itself makes no direct LLM API calls. Requires yt-dlp, jq, ffmpeg. Optional: VIDEO_SUMMARY_WHISPER_MODEL, VIDEO_SUMMARY_COOKIES, OPENAI_BASE_URL, OPENAI_MODEL." ---

Video Summary Skill

Intelligent video summarization for multi-platform content. Supports Bilibili, Xiaohongshu, Douyin, YouTube, and local video files.

What It Does

• Auto-detect platform from URL (Bilibili/Xiaohongshu/Douyin/YouTube)
• Extract subtitles/transcripts using platform-specific methods
• Generate structured summaries with key insights, timestamps, and actionable takeaways
• Multi-format output (plain text, JSON, Markdown)
• Direct LLM integration — outputs ready-to-use summaries
• Automatic cleanup — no temp file leaks

---

Quick Setup

No API key required to run. This skill extracts video content and outputs structured requests for summarization. The agent (or external tool) handles LLM calls.

# Optional: If you want the agent to call LLM for summarization
export OPENAI_API_KEY="your-api-key-here"
export OPENAI_BASE_URL=https://open.bigmodel.cn/api/paas/v4

# Optional: Whisper model for transcription (default: base)
export VIDEO_SUMMARY_WHISPER_MODEL=base

How it works:

1. Script extracts video subtitles/transcript
2. Script outputs a structured summary request (JSON/text)
3. Agent or external tool calls LLM API with the request
4. Script does NOT directly call any external APIs

Supported LLM Providers

• OpenAI: https://platform.openai.com/api-keys
• Zhipu GLM: https://open.bigmodel.cn/
• DeepSeek: https://platform.deepseek.com/
• Moonshot: https://platform.moonshot.cn/

Just set OPENAI_BASE_URL to the provider's API endpoint.

Cookie Configuration (Optional)

Xiaohongshu and Douyin may need cookies for some videos:

# Set cookie file path
export VIDEO_SUMMARY_COOKIES=/path/to/cookies.txt

# Or use --cookies flag
video-summary "https://xiaohongshu.com/..." --cookies cookies.txt

⚠️ Cookie Security Note:

• Cookie files contain session tokens and are sensitive
• Only use cookies from your own browser sessions
• Do not share cookie files with others
• Cookie files are read locally and never transmitted externally by this script

Manual Trigger

If configuration is incomplete, say: > "help me configure video-summary"

---

Quick Start

Check Dependencies

# Check all required tools
yt-dlp --version && jq --version && ffmpeg -version

# If missing, install
pip install yt-dlp
apt install jq ffmpeg  # or: brew install jq ffmpeg

Basic Usage

# Standard summary
video-summary "https://www.bilibili.com/video/BV1xx411c7mu"

# With chapter segmentation
video-summary "https://www.youtube.com/watch?v=xxxxx" --chapter

# JSON output for programmatic use
video-summary "https://www.xiaohongshu.com/explore/xxxxx" --json

# Subtitle only (no AI summary)
video-summary "https://v.douyin.com/xxxxx" --subtitle

# Save to file
video-summary "https://www.bilibili.com/video/BV1xx" --output summary.md

# Use cookies for restricted content
video-summary "https://www.xiaohongshu.com/explore/xxxxx" --cookies cookies.txt

In OpenClaw Agent

Just say: > "Summarize this video: [URL]"

The agent will automatically:

1. Detect the platform
2. Extract video content
3. Generate a structured summary

---

Commands Reference

| Command | Description | |---------|-------------| | video-summary "" | Generate standard summary | | video-summary "" --chapter | Chapter-by-chapter breakdown | | video-summary "" --subtitle | Extract raw transcript only | | video-summary "" --json | Structured JSON output | | video-summary "" --lang | Specify subtitle language (default: auto) | | video-summary "" --output | Save output to file | | video-summary "" --cookies | Use cookies file | | video-summary "" --transcribe | Force Whisper transcription |

URL Input
    ↓
Platform Detection
    ↓
Subtitle Extraction (yt-dlp / Whisper)
    ↓
Content Chunking (if long)
    ↓
LLM Summarization (OpenAI API / Agent)
    ↓
Structured Output
    ↓
Auto Cleanup

pip install openai-whisper

export VIDEO_SUMMARY_WHISPER_MODEL=base  # tiny, base, small, medium, large

# Optional: API key for your LLM provider
export OPENAI_API_KEY="your-api-key-here"

...