A specialized tool for extracting and summarizing YouTube transcripts to save time on video content consumption.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install yt-summary
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install yt-summary using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is YouTube Summary?
The YouTube Summary skill is a robust tool designed for Openclaw Skills that enables users to instantly digest video content. By providing a YouTube URL, the agent extracts high-quality transcripts through TranscriptAPI.com, which utilizes residential proxies to bypass common IP blocking issues faced by data centers. This skill is essential for developers and researchers who need to process long-form video content, technical tutorials, or live streams without watching them in full.
It ensures technical accuracy by strictly adhering to extracted transcripts and preventing AI hallucinations. This Openclaw Skills component allows for a seamless workflow where video information is converted into actionable text directly within your AI agent environment.
YouTube Summary Use Cases
- Efficiently summarizing long technical tutorials or educational lectures for quick reference.
- Extracting key insights and notable quotes from YouTube Shorts or mobile-shared links.
- Generating structured summaries of webinars and live stream recordings to capture critical data points.
- Customizing summary output by adding specific instructions (e.g., focusing on technical implementation) alongside the URL.
How YouTube Summary Works
- The agent detects a YouTube URL in the conversation, covering standard, mobile, shorts, and live formats.
- It executes a Python script to securely extract the transcript using TranscriptAPI, which manages residential IP rotation.
- The skill evaluates the transcript length; if it exceeds 50,000 tokens, it intelligently truncates to the first 40K tokens to fit model context windows.
- Using the extracted text, it generates a structured Markdown summary including a TL;DR, key bullet points, and notable quotes.
- The final summary is delivered to the user, ensuring the response fits within platform-specific character limits like those found in Telegram.
YouTube Summary Setup
Prerequisites
- Python 3.10+
- A TranscriptAPI.com account
Installation
- Obtain your API key from TranscriptAPI.
- Configure your environment:
export TRANSCRIPT_API_KEY="your-key-here"
- Install the required Python dependencies:
pip install -r skills/youtube-summary/requirements.txt
Note: For enhanced security in Openclaw Skills deployments, you can use the Unix pass manager to store your keys.
YouTube Summary Data Schema & Taxonomy
The skill processes and returns data structured for clear analysis. Below is the metadata taxonomy used during the extraction phase:
| Attribute | Description |
|---|---|
header |
Contains the video title, channel name, and duration string. |
transcript |
The full raw text content extracted from the video captions. |
language |
The detected language code of the transcript. |
tokens |
The total count of tokens for context management. |
title |
The specific title of the YouTube video. |
YouTube Summary Advanced Features
- Support for custom natural language prompts to steer summary focus and depth.
- Seamless integration with the Unix password manager (pass) for secure credential storage.
- Automatic residential proxy routing to ensure reliable extraction from any hosting environment.
- Intelligent truncation logic for processing extremely long-form content over 50k tokens.
- Multi-platform URL detection supporting youtu.be, shorts, and live stream links within Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Typefully Social Media Manager
A powerful automation bridge for Typefully to manage social media drafts and multi-platform scheduling directly via the CLI.
Typefully Social Media Manager
A powerful CLI-driven tool for managing Typefully drafts and scheduling across multiple social platforms.
LLM Speedtest
A high-performance utility to measure and compare Time to First Token (TTFT) latency across major LLM providers in parallel.
Claude Watchdog
A robust monitoring tool for the Claude API that delivers real-time status and latency alerts directly to Telegram.
Voice Assistant
A high-performance, real-time voice interface for Openclaw agents featuring sub-2 second latency and multi-provider STT/TTS support.
People Memories Skill
A lightweight personal CRM and context-retention skill for AI agents to store and recall specific details about individuals.
Featured*
