Web search

Web search and content extraction using ddgs (multi-engine metasearch). No API keys required. Use when: searching documentation, facts, current information, news, fetching web content. Triggers: search the web, look up, find information, web search, news search, fetch page.From its SKILL.md

Install

npx -y skills add marcfargas/skills --skill web-search

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
runs commandsInstructs the agent to run 5 commands, including `uv tool install ddgs` and 4 more.

SKILL.md

3.0 KB, 725 tokens by cl100k_base, as published. Nobody here has run it

Web Search

Web search and content extraction using ddgs — a multi-engine metasearch CLI. No API keys, no signup, no browser required.

Setup

Install ddgs (run once):

uv tool install ddgs

Install Node.js dependencies for content extraction (run once):

cd {baseDir}
npm install

Search

{baseDir}/search.js "query"                         # Basic search (5 results)
{baseDir}/search.js "query" -n 10                   # More results
{baseDir}/search.js "query" --content               # Include page content as markdown
{baseDir}/search.js "query" -t w                    # Results from last week
{baseDir}/search.js "query" -t m                    # Results from last month
{baseDir}/search.js "query" -r es-es                # Results in Spanish
{baseDir}/search.js "query" -b google               # Use Google backend
{baseDir}/search.js "query" -n 3 --content          # Combined options

Options

-n <num> — Number of results (default: 5)
--content — Fetch and include page content as markdown
-r <region> — Region code: us-en, es-es, de-de, fr-fr, etc. (default: none)
-t <timelimit> — Filter by time: d (day), w (week), m (month), y (year)
-b <backend> — Search backend: auto, all, bing, brave, duckduckgo, google, mojeek, yandex, yahoo, wikipedia (default: auto)

News Search

{baseDir}/search.js --news "query"                  # News search
{baseDir}/search.js --news "query" -n 10 -t w       # News from last week
{baseDir}/search.js --news "query" --content         # News with full article content

News backends: auto, all, bing, duckduckgo, yahoo

Extract Page Content

{baseDir}/content.js https://example.com/article

Fetches a URL and extracts readable content as markdown.

Output Format

Text search

--- Result 1 ---
Title: Page Title
Link: https://example.com/page
Snippet: Description from search results
Content: (if --content flag used)
  Markdown content extracted from the page...

--- Result 2 ---
...

News search

--- Result 1 ---
Title: Article Title
Link: https://news.example.com/article
Date: 2026-02-08T10:18:00+00:00
Source: Reuters
Snippet: Article summary...
Content: (if --content flag used)
  Full article as markdown...

--- Result 2 ---
...

When to Use

Searching for documentation or API references
Looking up facts or current information
News search for recent events
Fetching content from specific URLs
Any task requiring web search without interactive browsing
When no API key is available (unlike Brave Search)

What ships with it: 4 files

8.7 KB alongside SKILL.md, 2 of them executable

content.jsruns2.5 KB
.gitignore14 B
package.json296 B
search.jsruns5.9 KB