playbooks

home / skills / openclaw / skills / summarize

summarize skill

/skills/steipete/summarize

This skill summarizes URLs, files, or YouTube content using a fast CLI, delivering concise results across formats.

This is most likely a fork of the summarize-1.0.0 skill from z980944038-dev
npx playbooks add skill openclaw/skills --skill summarize

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 summarizer for web pages, PDFs, images, audio, and YouTube links. It supports multiple LLM providers and configurable models, letting you produce concise or extended summaries directly from URLs or local files. The tool is ideal for quick extraction and compression of long content into readable summaries or machine-friendly JSON output.

How this skill works

The CLI fetches content from the given source (web URL, local file, YouTube) and uses configurable extraction strategies to prepare text for summarization. It then calls the selected LLM provider with the chosen model and length settings to generate a summary. Optional fallbacks (Firecrawl, Apify) help extract content from blocked sites or handle YouTube when direct scraping fails.

When to use it

  • Quickly distill long web articles, reports, or whitepapers into short, actionable summaries.
  • Summarize local PDFs, slide decks, or documents without manual copy-paste.
  • Generate summaries for YouTube videos or audio files when you need highlights or captions.
  • Produce machine-readable summaries (JSON) to feed into pipelines or databases.
  • Archive or index large volumes of content for search and retrieval in a backup workflow.

Best practices

  • Set an appropriate model and API key environment variable for your provider before running requests.
  • Adjust --length or --max-output-tokens to match your use case: short for quick highlights, long for detailed summaries.
  • Use --extract-only to inspect what the extractor grabs before summarizing, especially on complex pages.
  • Provide APIFY_API_TOKEN or FIRECRAWL_API_KEY when targeting blocked sites or YouTube fallbacks.
  • Store preferred defaults in ~/.summarize/config.json to streamline repeated tasks.

Example use cases

  • Summarize a research paper PDF to get a one-paragraph summary and key findings.
  • Archive news articles by producing JSON summaries for a searchable archive.
  • Extract highlights from a recorded lecture or podcast audio for study notes.
  • Convert a long technical blog post into a medium-length summary for executive review.
  • Generate transcript-based summaries for YouTube tutorials to speed content indexing.

FAQ

Which API keys are supported?

OpenAI, Anthropic, xAI, and Google GAI keys are supported via environment variables such as OPENAI_API_KEY, ANTHROPIC_API_KEY, XAI_API_KEY, and GEMINI_API_KEY.

How do I handle blocked sites or YouTube extraction?

Provide FIRECRAWL_API_KEY for blocked sites and APIFY_API_TOKEN for YouTube fallback; use --firecrawl and --youtube flags to control behavior.