Site Summarizer for Openclaw

A powerful URL fetcher and summarization tool designed to extract key insights from web pages automatically.

cloudcompile
v4.1.0
Apr 5, 2026
1
735
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install site-summarizer

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install site-summarizer using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is Site Summarizer?

Site Summarizer is an essential addition to your collection of Openclaw Skills, enabling AI agents to interact with the live web by fetching and distilling information. It goes beyond simple scraping by performing automatic summarization, language detection, and keyword extraction, making it an ideal tool for research-heavy workflows. By integrating this into your Openclaw Skills library, you can significantly reduce the noise of raw HTML and focus on high-value data derived from any URL.

Site Summarizer Use Cases

  • Rapidly analyzing news articles or blog posts for research projects.
  • Automating content gathering for competitive intelligence and market analysis.
  • Enhancing AI agent capabilities with real-time web data extraction.
  • Building a localized knowledge base by caching summarized web content within your Openclaw Skills ecosystem.

How Site Summarizer Works

  1. The skill accepts a URL as input from the user or an automated process.
  2. It fetches the HTML content of the page while handling complex redirects and header parsing.
  3. The raw content is parsed to extract metadata like titles, descriptions, and authors.
  4. It generates a concise summary and performs text analysis for language and keywords.
  5. The processed data is returned as a structured JSON object or retrieved from cache if available.

Site Summarizer Setup

To begin using this tool in your Openclaw Skills environment, ensure you have Python installed and execute the following command:

python fetch_and_summarize.py <url>

Configuration is managed via environment variables to customize your Openclaw Skills experience:

  • SITE_SUMMARIZER_CACHE_DIR: Set the cache path (default: ~/.cache/site-summarizer).
  • SITE_SUMMARIZER_CACHE_TTL: Set the cache expiration in seconds (default: 3600).
  • SITE_SUMMARIZER_HIDE_IP: Set to true to redact IP information for privacy.

Site Summarizer Data Schema & Taxonomy

The skill produces a structured JSON output to ensure compatibility across Openclaw Skills integrations:

Field Description
success Boolean status of the operation
content The full extracted text content from the HTML
summary An AI-generated summary of the page
metadata Object containing title, description, and author
analysis Statistical data including language, keywords, word count, and read time
status HTTP response code
from_cache Boolean indicating if data was served from local storage

Site Summarizer Advanced Features

  • Configurable Caching: Optimize your Openclaw Skills performance with a customizable TTL and directory to reduce redundant network requests.
  • Privacy Protection: Mask resolved IP addresses in the output using a simple environment variable toggle.
  • Robust Parsing: Enhanced regex patterns and redirect handling for high-reliability content scraping across diverse websites.
  • Textual Analysis: Automatic language detection and keyword extraction for better data categorization and filtering.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*