Webfetch for Openclaw

A high-performance CLI tool for fetching web content and converting it into structured Markdown, plain text, or raw HTML.

lyhue1991
v0.1.1
Mar 21, 2026
1
856
0

Install & Download

1. ClawHub CLI

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

npx clawhub@latest install webfetch

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 webfetch 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 Webfetch?

Webfetch is a specialized command-line utility designed to bridge the gap between complex web pages and clean, readable formats. It enables users to scrape static web content seamlessly, making it an essential choice for developers and AI agents needing to digest online information quickly. As part of the Openclaw Skills ecosystem, Webfetch prioritizes format flexibility, allowing for easy integration into research workflows or documentation pipelines.

By default, it converts web content to Markdown, preserving the structural integrity of the original page while removing unnecessary noise. This makes it particularly valuable for feeding clean data into LLMs or personal knowledge management systems.

Webfetch Use Cases

  • Converting lengthy web articles into clean Markdown for personal knowledge management.
  • Fetching raw HTML or text data for automated research and analysis tasks.
  • Downloading web content for offline reading through shell scripts or AI agents.
  • Scraping specific online resources while operating behind a corporate proxy or restricted network.

How Webfetch Works

  1. The tool receives a target URL and optional parameters for format, timeout, or proxy settings.
  2. It initiates a network request, automatically respecting environment variables like HTTPS_PROXY if configured.
  3. The tool fetches the static HTML content of the page, supporting responses up to 5MB.
  4. It processes the fetched content based on the requested format (Markdown, Text, or HTML).
  5. The output is either printed directly to the console or saved to a specified local file.

Webfetch Setup

To get started with this entry in the Openclaw Skills library, install the package globally using npm:

npm install -g @lyhue1991/webfetch

Verify that the installation was successful by checking the version:

webfetch --version

Webfetch Data Schema & Taxonomy

The skill manages data through direct command-line arguments and environment variables. Key parameters and their functions are detailed below:

Argument Description
<url> The required target web address.
-f, --format Output format: markdown (default), text, or html.
-o, --output The destination file path for the fetched content.
--proxy Custom proxy server URL for network requests.
--timeout Request timeout in seconds (default 30s, max 120s).
--insecure Bypass TLS certificate validation for self-signed certificates.

Additionally, the tool utilizes system environment variables such as HTTP_PROXY, HTTPS_PROXY, and NO_PROXY to handle network routing.

Webfetch Advanced Features

  • Full proxy support with automatic environment variable detection for secure enterprise environments.
  • Insecure mode using the --insecure flag to bypass TLS/SSL certificate validation errors.
  • Quiet mode (-q) for silent execution, perfect for pipe redirection in automation scripts.
  • Custom timeout settings to handle slow-loading websites or high-latency connections.
  • Structured exit codes (0-3) to facilitate error handling within multi-agent Openclaw Skills workflows.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*