playbooks

home / skills / z980944038-dev / openclawwdl / summarize-1.0.0

summarize-1.0.0 skill

/skills/summarize-1.0.0

This skill quickly summarizes URLs, PDFs, images, and YouTube links using summarize CLI with customizable models and output options.

npx playbooks add skill z980944038-dev/openclawwdl --skill summarize-1.0.0

Review the files below or copy the command above to add this skill to your agents.

Files (2)
SKILL.md
1.4 KB
---
name: summarize
description: Summarize URLs or files with the summarize CLI (web, PDFs, images, audio, YouTube).
homepage: https://summarize.sh
metadata: {"clawdbot":{"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.

## Quick start

```bash
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`

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

Optional services:
- `FIRECRAWL_API_KEY` for blocked sites
- `APIFY_API_TOKEN` for YouTube fallback

Overview

This skill provides a fast command-line interface to summarize web pages, local files (PDFs, images, audio), and YouTube videos. It supports multiple LLM providers and configurable output length and format for quick human reading or machine integration. The tool is lightweight and designed for rapid extraction and concise summaries from diverse sources.

How this skill works

You run the summarize CLI with a URL, file path, or YouTube link; the tool fetches and extracts content using built-in or fallback extractors, then sends extracted text to your chosen model using the provider API key you set. It supports model selection, output-length presets, JSON output for automation, and optional fallback services for blocked sites or YouTube. Flags let you control extraction-only mode, token limits, and extraction behavior.

When to use it

  • Quickly distill long web articles or reports into concise summaries
  • Summarize local PDFs, images with OCR, or audio transcripts for review
  • Create machine-readable summaries for downstream automation (use --json)
  • Summarize YouTube videos when you need highlights or transcripts
  • Fallback extraction for sites behind blocks or when primary extractor fails

Best practices

  • Set an API key for the provider you plan to use (OPENAI_API_KEY, ANTHROPIC_API_KEY, XAI_API_KEY, or GEMINI_API_KEY) before running the CLI
  • Choose appropriate length presets (short, medium, long, xl, xxl) or specify exact character counts for predictable summaries
  • Use --json when integrating summaries into scripts or pipelines to avoid parsing errors
  • Enable --extract-only for debugging extraction results before sending to the model
  • Provide APIFY_API_TOKEN or FIRECRAWL_API_KEY when working with blocked sites or YouTube fallback scenarios

Example use cases

  • Summarize a news article to create a short newsletter blurb
  • Extract and compress a long research PDF into a one-page summary for meetings
  • Generate quick notes from a podcast audio file before a team discussion
  • Produce a machine-readable summary of a webpage to feed into a knowledge database (--json)
  • Get a concise highlight reel of a YouTube tutorial using the --youtube fallback

FAQ

Which models and keys are supported?

Set the provider API key: OPENAI_API_KEY, ANTHROPIC_API_KEY, XAI_API_KEY, or GEMINI_API_KEY. The CLI defaults to google/gemini-3-flash-preview if no model is specified.

How do I get consistent summary lengths?

Use the --length presets (short, medium, long, xl, xxl) or pass a specific character count. You can also cap tokens with --max-output-tokens for tighter control.