agentleFS
Sign inStart free
KerberosClawKerberosClaw/kc_ai_skills/searxng/SKILL.md

searxng

Skill79 starsChanged 29 days agoMITView on GitHub

Use when the user wants privacy-respecting web, image, news, or video search through a configured local SearXNG instance instead of external search APIs. Calls the bundled script against SEARXNG_URL, supports result limits/categories/language/time range, and can return human-readable or JSON output. NOT for searches when no SearXNG instance is configured or when authenticated/private data retrieval is required.

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Search the web using your local SearXNG instance - a privacy-respecting metasearch engine.

    line 20
  2. Very specific:

    Do not use if SEARXNG_URL is missing and no local/default instance is reachable.

    line 24
  3. Distinctive:

    Do not scrape authenticated pages or private user accounts.

    line 25
  4. Distinctive:

    Do not treat search snippets as verified facts.

    line 26
  5. Very specific:

    Default (if not set): http://localhost:8080

    line 67

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

SearXNG Search

You are a privacy-preserving search operator. You route search requests through the user's configured SearXNG instance and report results without introducing third-party API dependencies.

Search the web using your local SearXNG instance - a privacy-respecting metasearch engine.

Not For

  • Do not use if SEARXNG_URL is missing and no local/default instance is reachable.
  • Do not scrape authenticated pages or private user accounts.
  • Do not treat search snippets as verified facts; cite uncertainty and follow sources when needed.

Commands

Web Search

uv run {baseDir}/scripts/searxng.py search "query"              # Top 10 results
uv run {baseDir}/scripts/searxng.py search "query" -n 20        # Top 20 results
uv run {baseDir}/scripts/searxng.py search "query" --format json # JSON output

Category Search

uv run {baseDir}/scripts/searxng.py search "query" --category images
uv run {baseDir}/scripts/searxng.py search "query" --category news
uv run {baseDir}/scripts/searxng.py search "query" --category videos

Advanced Options

uv run {baseDir}/scripts/searxng.py search "query" --language en
uv run {baseDir}/scripts/searxng.py search "query" --time-range day

Configuration

Required: Set the SEARXNG_URL environment variable to your SearXNG instance:

export SEARXNG_URL=https://your-searxng-instance.com

Or configure in your Clawdbot config:

{
  "env": {
    "SEARXNG_URL": "https://your-searxng-instance.com"
  }
}

Default (if not set): http://localhost:8080

Features

  • Privacy-focused (uses your local instance)
  • Multi-engine aggregation
  • Multiple search categories
  • Rich formatted output
  • Fast JSON mode for programmatic use

API

Uses your local SearXNG JSON API endpoint (no authentication required by default).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free