summarize

steipete/clawdis

Fast CLI to summarize or transcribe URLs, videos, podcasts, articles, PDFs, and local files.

What is summarize?

A command-line tool that extracts and summarizes content from URLs, YouTube videos, PDFs, and local files using your choice of LLM provider. Use it when you need quick summaries or transcripts of web content, videos, or documents.

Summarize web URLs, articles, and web pages
Extract and transcribe YouTube videos and video content
Summarize PDFs and local files
Generate transcripts with best-effort extraction from video URLs
Adjust summary length from short to extra-long formats
Output results as JSON for machine-readable processing

How to install summarize

npx skills add https://github.com/steipete/clawdis --skill summarize

Prerequisites

Install via Homebrew: `brew install steipete/tap/summarize`
Set an API key for your LLM provider: `OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, `XAI_API_KEY`, or `GEMINI_API_KEY`
Optional: `FIRECRAWL_API_KEY` for blocked sites or `APIFY_API_TOKEN` for YouTube fallback

Claude Code

Cursor

Windsurf

Cline

How to use summarize

1.Run `summarize "<URL>"` to summarize a web page or article
2.Run `summarize "/path/to/file.pdf"` to summarize a local PDF or file
3.Run `summarize "<YouTube_URL>" --youtube auto` to summarize a YouTube video
4.Add `--extract` flag to get raw extracted content without LLM processing
5.Use `--length short|medium|long|xl|xxl` to control summary verbosity
6.Use `--json` flag to get machine-readable JSON output

Use cases

Good for

Quickly understand what a URL or article is about without reading the full text
Extract transcripts from YouTube videos for analysis or reference
Summarize long PDF documents or research papers
Get a quick overview of podcast or video content
Batch process multiple files or URLs for content review

Who it's for

Developers building content analysis workflows
Researchers processing multiple documents or videos
Content creators needing quick summaries of reference material
Anyone wanting fast CLI-based content extraction without browser overhead

summarize FAQ

What API keys do I need?

You need at least one API key from OpenAI, Anthropic, xAI, or Google Gemini. Set it as an environment variable (e.g., `OPENAI_API_KEY`). The tool defaults to `auto` model selection.

Can I get a transcript instead of a summary?

Yes, use the `--extract` flag with YouTube URLs to attempt transcript extraction. For very long transcripts, the tool will return a summary first and ask which section to expand.

What if a website blocks the summarizer?

Set `FIRECRAWL_API_KEY` to enable fallback extraction for blocked sites, or use `--firecrawl always` to force it.

How do I control summary length?

Use the `--length` flag with values like `short`, `medium`, `long`, `xl`, or `xxl`, or specify a character count directly.

Can I use this in scripts or automation?

Yes, use the `--json` flag to get machine-readable output suitable for piping into other tools or scripts.

Full instructions (SKILL.md)

Source of truth, from steipete/clawdis.

name: summarize description: "Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files." homepage: https://summarize.sh metadata: { "openclaw": { "emoji": "🧾", "requires": { "bins": ["summarize"] }, "install": [ { "id": "brew", "kind": "brew", "formula": "steipete/tap/summarize", "bins": ["summarize"], "label": "Install summarize (brew)", }, ], }, }

Summarize

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.