local-web-search
Free local web search via DuckDuckGo HTML scraping with no API key. Use when web_search tool is unavailable or missing API keys, and you need fast query results with source trust scoring, retry/backoff handling, and JSON output suitable for pipelines.
Why use this skill?
Perform fast, free web searches without API keys. Integrates DuckDuckGo scraping with trust-scoring for reliable AI agents.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/mes28io/local-web-search-skillWhat This Skill Does
The local-web-search skill provides a lightweight, dependency-free mechanism for querying the web directly from your OpenClaw environment. By utilizing HTML scraping of DuckDuckGo's results, it bypasses the need for costly commercial search APIs like Google Custom Search or Bing. It is designed for high-throughput automated tasks where reliability is prioritized over massive metadata sets, providing structured JSON output that integrates seamlessly into downstream AI pipelines.
Installation
To install this skill, use the ClawHub CLI tool integrated with your environment. Run the following command in your terminal:
clawhub install openclaw/skills/skills/mes28io/local-web-search-skill
Ensure that your environment has Python 3.x installed, as the script executes via local Python runtime without external network tokens.
Use Cases
- Automated Research Agents: Populate context for LLM prompts when specific primary documentation is missing.
- Trend Aggregation: Periodically track specific topics across reputable domains.
- Fallback Retrieval: Use this as a secondary retrieval mechanism when primary enterprise search APIs are rate-limited or unavailable.
- Pipeline Feeding: Automatically gather search snippets to be summarized or categorized by local models (e.g., Llama 3 or Mistral).
Example Prompts
- "Perform a local web search for 'latest advancements in quantum computing' and filter for high-trust sources only."
- "Search for the documentation on setting up an OpenClaw server and provide the top 5 results with trust scores."
- "Find current news on Rust programming updates and format the output for a briefing document."
Tips & Limitations
Trust Scoring: The skill implements a heuristic scoring system. 'High' trust tiers are reserved for .gov, .edu, and academic domains. 'Medium' captures established industry news, while 'Low' indicates user-generated content like blog posts. Always treat 'Low' results as unverified.
Reliability: The script utilizes exponential backoff with jitter to handle network hiccups. However, because it relies on scraping DuckDuckGo's UI, changes to their HTML structure may break the parser. If you encounter issues, check for updates in the source repository. Avoid overloading the search endpoint with rapid-fire requests to prevent IP-based rate limiting on the network level.
Metadata
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 skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-mes28io-local-web-search-skill": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access