Web Search for Openclaw

A versatile web search skill that enables AI agents to retrieve real-time information, news, images, and videos via DuckDuckGo.

billyutw
v1.0.0
Jan 29, 2026
33
38.9k
0

Install & Download

1. ClawHub CLI

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

npx clawhub@latest install web-search

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 web-search 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 Web Search?

The Web Search skill provides a robust interface for AI agents to interact with the live internet without the need for complex API keys or authentication. By leveraging the DuckDuckGo API, this Openclaw Skills addition allows for deep technical research, fact-checking, and resource gathering across multiple media types. It is built to be developer-friendly, offering clean output in several formats suitable for both human reading and programmatic consumption.

This tool is essential for keeping agents up-to-date with current events, finding specific visual assets, or building localized knowledge bases from web data. With built-in support for advanced filtering—such as time ranges, regions, and safe search levels—it ensures that retrieved information is highly relevant and safe for use in professional environments.

Web Search Use Cases

  • Conducting deep-dive research on technical topics or recent software releases.
  • Fact-checking claims by verifying information against current web sources.
  • Automating the collection of news articles for specific industry sectors.
  • Searching for high-quality images and videos with specific dimensions or durations.
  • Gathering URLs and resource lists to feed into larger data processing pipelines.

How Web Search Works

  1. The agent identifies a search intent based on a query for web, news, image, or video content.
  2. Search parameters are configured, including result limits, time-range filters, and regional settings.
  3. The skill executes the search request using the underlying DuckDuckGo API interface.
  4. Results are retrieved and processed into the requested format (Text, Markdown, or JSON).
  5. The output is either returned to the terminal for immediate review or saved to a specified file path for persistent storage.

Web Search Setup

To use this within the ecosystem of Openclaw Skills, you must first install the required Python dependency:

pip install duckduckgo-search

Once installed, you can verify the setup by running a simple test search:

python scripts/search.py "Openclaw Skills tutorial"

Web Search Data Schema & Taxonomy

The skill organizes its output based on the chosen format. When using the JSON format, the data follows a structured schema ideal for Openclaw Skills automation:

Attribute Type Description
title String The title of the search result or article
href String The direct URL to the source content
body String A brief snippet or summary of the content
source String The publishing organization (news search only)
duration String The length of the clip (video search only)
dimensions String The width and height (image search only)

Web Search Advanced Features

  • Multi-format support (Text, Markdown, JSON) for seamless integration with different workflows.
  • Granular image filters including size, color, type (e.g., transparent, gif), and layout.
  • Time-range limiting to ensure results are restricted to the past day, week, month, or year.
  • Video-specific filters for duration and resolution (standard vs. high definition).
  • Region-specific search capabilities to retrieve localized results from specific countries.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*