search

Search DuckDuckGo via ddgr and return JSON results with title, url, and abstract.

1|1|Updated Aug 3, 2020
One-click install
npx skills add https://github.com/lolwierd/dotfiles --skill search-lolwierd
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: search
Source: https://github.com/lolwierd/dotfiles/tree/main/ai/dot-agents/skills/search
Command: npx skills add https://github.com/lolwierd/dotfiles --skill search-lolwierd

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill enables quick, structured web searches to gather information, sources, and answers from the internet via a fast DuckDuckGo interface.

Core Features & Use Cases

  • Json-friendly results: returns search results in JSON for easy parsing.
  • Non-interactive: suitable for automated workflows and AI-assisted research.
  • Use Case: when you need to answer a question with cited sources, run a search and pass the results to your note-taking or analysis pipeline.

Quick Start

Run a DuckDuckGo search using ddgr to fetch up to five results in JSON for your query.

Frequently Asked Questions about search

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I get DuckDuckGo web search results in JSON format?

You need the ddgr command-line tool installed in your environment to fetch DuckDuckGo web search results. Once the dependency is set up, the interface runs non-interactively to return structured JSON data for your queries.

Can I limit the number of web search results returned by ddgr?

Yes, you can configure the result limit for web searches using the -n flag in ddgr. This allows you to fetch a specific number of results, such as up to five JSON entries, tailored to your research needs.

How do I run non-interactive web searches for automated workflows?

Non-interactive web searches run via ddgr return structured JSON results without requiring user input during execution. This makes the process suitable for automated pipelines where you need to gather sources and pass them directly to analysis tools.

What is the best way to gather cited web sources for research tasks?

DuckDuckGo web search via ddgr is suited for research tasks and quick fact-finding but does not perform deep site crawling or full-text article extraction. It returns concise abstracts and URLs, so you may need separate tools for full content retrieval.