Summarize | Agent Skills

23K installs

•

openclaw/openclaw

•

by Openclaw

Score

8.6

/ 10

Installs

23K

Repo Stars

388.9K

Last Updated

0d ago

Fresh

Quality Ratio

90%

Description

Verified

Language

TypeScript

First Published

Jan 2026

Summary

The Summarize agent skill empowers AI agents to quickly generate summaries or extract transcripts from a wide range of content sources, including web pages, local files, PDFs, and YouTube videos. It is particularly beneficial for developers building AI agents that need to quickly process and understand external content or for users seeking rapid information retrieval from digital resources. This is a skill with 23K installs, indicating broad adoption within the agent skill registry. Agents can invoke it using trigger phrases like "summarize this URL" or "transcribe this YouTube video," with support for specific commands to process URLs, local files, and YouTube links. It offers flags to control summary length, output format like JSON, or to simply extract content without an LLM, and can leverage various large language models by setting API keys. The skill also guides agents to provide a tight summary before expanding on huge transcripts, improving user experience.

Skill Definition

Fast CLI to summarize URLs, local files, and YouTube links.

When to use (trigger phrases)

Use this skill immediately when the user asks any of:

"use summarize.sh"
"what's this link/video about?"
"summarize this URL/article"
"transcribe this YouTube/video" (best-effort transcript extraction; no yt-dlp needed)

Quick start

summarize "https://example.com"
summarize "/path/to/file.pdf"
summarize "https://youtu.be/dQw4w9WgXcQ" --youtube auto

YouTube: summary vs transcript

Best-effort transcript (URLs only):

summarize "https://youtu.be/dQw4w9WgXcQ" --youtube auto --extract

If the user asked for a transcript but it's huge, return a tight summary first, then ask which section/time range to expand.

Model + keys

Set the API key for your chosen provider:

OpenAI: OPENAI_API_KEY
Anthropic: ANTHROPIC_API_KEY
xAI: XAI_API_KEY
Google: GEMINI_API_KEY (aliases: GOOGLE_GENERATIVE_AI_API_KEY, GOOGLE_API_KEY)

Default model is auto; config may choose the provider/model.

Useful flags

--length short|medium|long|xl|xxl|<chars>
--max-output-tokens <count>
--extract (print extracted content, no LLM summary)
--json (machine readable)
--firecrawl auto|off|always (fallback extraction)
--youtube auto (Apify fallback if APIFY_API_TOKEN set)

Config

Optional config file: ~/.summarize/config.json

{ "model": "openai/gpt-5.2" }

Optional services:

FIRECRAWL_API_KEY for blocked sites
APIFY_API_TOKEN for YouTube fallback

How to Use

Use in O-mega

Claude Code

npx skills add openclaw/openclaw summarize