← Skillful-Alhazen

Web Search

Skills: Web Search

General-purpose web search via SearXNG — a self-hosted metasearch engine that aggregates results from Google, DuckDuckGo, Bing, and others. No API key required.

Purpose

Use this skill whenever you need to search the web during a research or curation session. It’s the primary discovery mechanism for finding external sources — used by both the agent during foraging and by specialized skills like tech-recon and scientific-literature.

Prerequisites

  • SearXNG running (started automatically in Docker deployments)
  • For local Claude Code sessions: docker compose up -d searxng or use the public fallback

Usage

The agent calls SearXNG directly via HTTP:

curl -s "${SEARXNG_URL:-http://localhost:8888}/search?q=QUERY&format=json" | python3 -c "
import sys, json
r = json.load(sys.stdin)
results = r.get('results', [])[:5]
print(f'{len(results)} results:\n')
for x in results:
    print(x.get('title',''))
    print(x.get('url',''))
    print(x.get('content','')[:300])
    print()
"

Replace QUERY with URL-encoded search terms (spaces as +, e.g. TypeDB+knowledge+graph).

Tips:

  • Use [:10] instead of [:5] for more results
  • Add site:github.com for GitHub-only results
  • SEARXNG_URL is set automatically per environment (localhost:8888 on Mac Mini, searxng:8080 on VPS)

When Other Skills Use It

  • tech-recon — discovery phase (finding candidate systems)
  • scientific-literature — supplemental web search alongside Europe PMC and PubMed
  • they-said-whaaa — finding news articles about public figures
  • Agent (general) — any time background web research is needed

See Also