Web-Claude Unified Search for Openclaw

A high-reliability search orchestration skill that implements a 3-tier fallback strategy using Brave, DuckDuckGo, and browser-based Claude.ai.

mupengi-bot
v1.0.0
Feb 16, 2026
0
2.8k
0

Install & Download

1. ClawHub CLI

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

npx clawhub@latest install mupeng-web-claude

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 mupeng-web-claude 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-Claude Unified Search?

The Web-Claude skill is a specialized search engine for Openclaw Skills designed to provide uninterrupted access to web data. It functions as a unified gateway that intelligently switches between different search providers based on availability and query complexity. By integrating multiple search tiers, this skill ensures that AI agents can always find the information they need, whether through high-speed structured APIs or deep browser-based analysis. It is a fundamental tool for any developer using Openclaw Skills who requires resilient and comprehensive web research capabilities.

Web-Claude Unified Search Use Cases

  • Performing real-time market research with automated insight generation.
  • Monitoring competitive intelligence using time-specific freshness filters.
  • Fact-checking and data gathering for content creation pipelines.
  • Ensuring search reliability in environments where API keys might be restricted or throttled.

How Web-Claude Unified Search Works

  1. The skill first attempts a Tier 1 search using the Brave API via the built-in web_search tool for the fastest results.
  2. If the Brave API key is missing or the request fails, it automatically falls back to Tier 2 using DuckDuckGo.
  3. For highly complex research or as a final fallback, it triggers Tier 3 by automating a browser session on claude.ai to perform analysis and search.
  4. All retrieved data is processed and automatically saved to a persistent research directory for later use.

Web-Claude Unified Search Setup

To deploy this skill within your Openclaw Skills setup, follow these steps:

  1. Configure your Brave API key in your environment to enable Tier 1 search.
  2. Ensure your OpenClaw browser profile is running on port 18800 for Tier 3 automation.
  3. Install the required Python dependencies for the fallback search:
pip install duckduckgo-search

Web-Claude Unified Search Data Schema & Taxonomy

This skill automatically organizes research data within the Openclaw Skills directory structure for easy retrieval:

Field Description
Directory memory/research/
Filename search-YYYY-MM-DD-HH-MM-[keyword].md
Metadata Timestamps, search method used, and the original query
Content Markdown formatted list of results, source links, and AI-generated insights

Web-Claude Unified Search Advanced Features

  • Time-based freshness parameters (24h, weekly, monthly) for focused news gathering.
  • Regional search support with specific language and country parameters for localized research.
  • Seamless cross-skill integration allowing search results to feed directly into content planning or competitor watch tasks.
  • Automatic caching system that prevents redundant searches and preserves data within the Openclaw Skills ecosystem.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*