Agent skill · Documentation

ddgs-search

Web search via the DDGS metasearch library. Use for searching for unknown documentation, facts, or any web content. Lightweight, no browser required.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill ddgs-search-rebelpotato-agent-config-1410d7a0 --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 3 KB
Bundled scripts: none
Path: skills/analysis/ddgs-search-rebelpotato-agent-config-1410d7a0/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# DDGS search Web search and content extraction using the DDGS library. No browser required. ## Usage Run from any directory: ```bash uv run {baseDir}/search.py "python programming" # Basic search (5 results) uv run {baseDir}/search.py "python programming" --proxy http://proxy.example.com:8080 # Use proxy uv run {baseDir}/search.py "russia filetype:pdf" # Search with advanced query uv run {baseDir}/search.py "python programming" -n 20 # More results uv run {baseDir}/search.py "python programming" -r uk-en # UK English results uv run {baseDir}/search.py "python programming" -s off # Disable safesearch uv run {baseDir}/search.py "python programming" -t w2 # Results from the last two weeks uv run {baseDir}/search.py "python programming" -p 2 # Page 2 of results uv run {baseDir}/search.py "python programming" -b "bing,google" # Use specific backends uv run {baseDir}/search.py "python programming" --brief # Show only snippets (no full text extraction) ``` ### Options - `-n, --max-results <num>` - Maximum number of results (default: 5) - `-r, --region <code>` - Region/language code: us-en, uk-en, ru-ru, etc. (default: us-en) - `-s, --safesearch <level>` - Safesearch level: on, moderate,

What's inside
Steps it walks through
  1. Usage
  2. Options
  3. Output Format
  4. When to Use
  5. Next Steps
  6. Useful commands
Ships with 1 file
  • metadata.json
Commands it runs
uv run {baseDir}/search.py "python programming"                     # Basic search (5 results)
uv run {baseDir}/search.py "python programming" --proxy http://proxy.example.com:8080  # Use proxy
uv run {baseDir}/search.py "russia filetype:pdf"                    # Search with advanced query
uv run {baseDir}/search.py "python programming" -n 20               # More results
uv run {baseDir}/search.py "python programming" -r uk-en            # UK English results
uv run {baseDir}/search.py "python programming" -s off              # Disable safesearch
uv run {baseDir}/search.py "python programming" -t w2               # Results from the last two weeks
uv run {baseDir}/search.py "python programming" -p 2                # Page 2 of results
uv run {baseDir}/search.py "python programming" -b "bing,google"    # Use specific backends
uv run {baseDir}/search.py "python programming" --brief             # Show only snippets (no full text extraction)
More from claude-skill-registry
All skills →
About this skill
What does the ddgs-search skill do?

Web search via the DDGS metasearch library. Use for searching for unknown documentation, facts, or any web content. Lightweight, no browser required.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill ddgs-search-rebelpotato-agent-config-1410d7a0 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going