agentleFS
Sign inStart free
ryanmacleanryanmaclean/skills/searxng/SKILL.md

searxng

Skill1 starsChanged 51 days agoMITView on GitHub

Use the local SearXNG instance (searxng.local) for web searches when WebSearch is rate-limited, geo-blocked, or returns no results — also for fleet-internal search via JSON API.

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

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

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use the local SearXNG instance when WebSearch is rate-limited, geo-blocked, or returns no results.

    line 8
  2. Distinctive:

    Not accessible from cloud/remote contexts.

    line 18

“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 — Local Search Fallback

Use the local SearXNG instance when WebSearch is rate-limited, geo-blocked, or returns no results.

Instance

http://10.0.3.202:8080/

Network note: LAN-only. Reachable when connected to the studio network. Not accessible from cloud/remote contexts. If ECONNREFUSED, you are off-network — fall back to WebSearch.

Usage

JSON API (preferred for parsing)

WebFetch url="http://10.0.3.202:8080/search?q=<query>&format=json"
prompt="extract: titles, urls, snippets from results array"

URL-encode the query

Spaces → + or %20. Special chars → percent-encoded.

Examples:

http://10.0.3.202:8080/search?q=rust+genai+crate+2026&format=json
http://10.0.3.202:8080/search?q=kunal732+MLX+Swift&format=json
http://10.0.3.202:8080/search?q=fastembed+rs+qdrant&format=json

Filter by category

http://10.0.3.202:8080/search?q=<query>&categories=general&format=json
http://10.0.3.202:8080/search?q=<query>&categories=it&format=json
http://10.0.3.202:8080/search?q=<query>&categories=science&format=json

JSON response structure

{
  "query": "...",
  "results": [
    {
      "title": "...",
      "url": "...",
      "content": "...",
      "engine": "...",
      "score": 0.0
    }
  ],
  "answers": [],
  "suggestions": []
}

When to use

  • WebSearch returns 429 (rate limit)
  • WebSearch returns no results for technical queries
  • Need fresh results without Google/Bing geo-filtering
  • Researching local network resources

When NOT to use

  • WebSearch is working fine — prefer it (returns structured search results natively)
  • Query requires real-time data (SearXNG caches may lag)

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