ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified productivity Safety 4/5

web-claude

Unified web search skill. Fallback order — web_search(Brave) → duckduckgo → claude.ai. Auto-cache search results (saved to memory/research/)

Why use this skill?

Enhance OpenClaw with web-claude, a 3-tier automated search skill. Features Brave, DuckDuckGo, and browser-based fallback with instant markdown research archiving.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/mupengi-bot/mupeng-web-claude
Or

What This Skill Does

The web-claude skill is a comprehensive, resilient web search solution for the OpenClaw AI agent. It implements a sophisticated 3-tier fallback architecture to ensure users never face a dead-end during information gathering. It automatically iterates from high-speed API services (Brave) to privacy-focused alternatives (DuckDuckGo), and finally to a direct browser-based analysis (claude.ai) if necessary. Furthermore, it manages an automated research memory system that archives all findings into organized markdown files within your memory/research/ directory, facilitating long-term context retention.

Installation

To integrate this skill into your OpenClaw environment, execute the following command in your terminal:

clawhub install openclaw/skills/skills/mupengi-bot/mupeng-web-claude

Ensure your system meets the requirements for browser automation if you intend to use the third-tier fallback method, specifically the openclaw browser profile on port 18800.

Use Cases

This skill is perfect for research-heavy tasks. Use it when you need to perform deep market analysis, verify real-time news updates, or consolidate information from multiple web sources into a clean markdown format. It is particularly effective for developers researching libraries with shifting documentation and analysts tracking daily market trends.

Example Prompts

  1. "Perform a research query on the latest advancements in small language models for the year 2026 and save the findings to memory."
  2. "Find the current market sentiment regarding decentralized AI infrastructure and summarize the top three sources."
  3. "Search for the latest documentation on integrating OpenClaw with local vector databases and compile a summary."

Tips & Limitations

To optimize performance, ensure you have a valid Brave API key configured to avoid the overhead of the slower DuckDuckGo and browser-based tiers. The browser-based fallback (Tier 3) is a powerful 'last resort' but is subject to claude.ai rate limits and longer execution times. Avoid running massive batch searches to prevent potential rate-limiting from external providers. Always check the memory/research/ directory to review cached markdown files for future reference or project documentation.

Metadata

Stars1335
Views1
Updated2026-02-23
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-mupengi-bot-mupeng-web-claude": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#search#automation#research#web-scraping#memory
Safety Score: 4/5

Flags: network-access, file-write, file-read, external-api, code-execution