Back to Skills

summarize

steipete
Updated Yesterday
31 views
468
45
468
View on GitHub
Documentspdf

About

This CLI tool summarizes web URLs, local files (including PDFs, images, audio), and YouTube links using various AI models. Developers can use it for quick content extraction by setting provider API keys and adjusting output length. It defaults to Google's Gemini model and is installed via Homebrew.

Documentation

Summarize

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

Quick start

summarize "https://example.com" --model google/gemini-3-flash-preview
summarize "/path/to/file.pdf" --model google/gemini-3-flash-preview
summarize "https://youtu.be/dQw4w9WgXcQ" --youtube auto

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 google/gemini-3-flash-preview if none is set.

Useful flags

  • --length short|medium|long|xl|xxl|<chars>
  • --max-output-tokens <count>
  • --extract-only (URLs only)
  • --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

Quick Install

/plugin add https://github.com/steipete/clawdis/tree/main/summarize

Copy and paste this command in Claude Code to install this skill

GitHub 仓库

steipete/clawdis
Path: skills/summarize
relaywhatsapp

Related Skills

canvas-design

Meta

The canvas-design skill generates original visual art in PNG and PDF formats for creating posters, designs, and other static artwork. It operates through a two-step process: first creating a design philosophy document, then visually expressing it on a canvas. The skill focuses on original compositions using form, color, and space while avoiding copyright infringement by never copying existing artists' work.

View skill

canvas-design

Meta

The canvas-design skill generates original visual art in PNG and PDF formats for creating posters, designs, and other static artwork. It operates through a two-step process: first creating a design philosophy document, then visually expressing that philosophy on a canvas. This skill focuses on original creations using form, color, and composition while avoiding copyright violations by never copying existing artists' work.

View skill

generating-test-reports

Meta

This skill generates comprehensive test reports by aggregating test results from various frameworks and calculating key metrics like coverage and pass rates. It produces stakeholder-friendly outputs (HTML, PDF, JSON) and performs trend analysis for historical comparisons. Use it when you need a test report, coverage analysis, or failure analysis.

View skill

cloudflare-browser-rendering

Meta

Cloudflare Browser Rendering provides a headless browser automation API for tasks like taking screenshots, generating PDFs, scraping dynamic content, and testing web applications. It supports multiple integration methods including a REST API, Workers Bindings for Puppeteer/Playwright, and MCP servers. Use this skill when you need to automate browser interactions or extract data from JavaScript-heavy websites.

View skill