searxng-search

Search the web using a self-hosted SearXNG instance. Use when users ask to search with SearXNG, or when web search is needed and a SearXNG instance is configured. Supports categories, engines, time range, and language filters.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "searxng-search" with this command: npx skills add xyenon/agents/xyenon-agents-searxng-search

SearXNG Search Skill

Search the web using a SearXNG instance via its API.

Configuration

The config file is read from $XDG_CONFIG_HOME/agents/searxng.json (defaults to ~/.config/agents/searxng.json).

Config fields

FieldTypeRequiredDescription
base_urlstringYesSearXNG instance URL (no trailing slash)
authobjectNoAuth config object (see below)
auth.typestringIf auth"bearer" or "basic"
auth.tokenstringIf bearerBearer token value (supports $ENV_VAR)
auth.userstringIf basicBasic auth username
auth.passstringIf basicBasic auth password
headersobjectNoKey-value pairs of additional HTTP headers
default_languagestringNoDefault language code (e.g. "en", "zh-CN")
default_categoriesstring[]NoDefault categories (e.g. ["general", "news"])
default_enginesstring[]NoDefault engines (e.g. ["google", "duckduckgo"])
default_safesearchnumberNoDefault safe search level: 0, 1, 2
default_time_rangestringNoDefault time range: "day", "month", "year"
default_max_resultsnumberNoMax results to display (default: 5)
timeoutnumberNoRequest timeout in seconds (default: 30)

Example config (Bearer auth)

{
  "base_url": "https://searx.example.com",
  "auth": {
    "type": "bearer",
    "token": "your-token-here"
  },
  "default_categories": ["general"],
  "default_engines": ["google", "duckduckgo", "brave"],
  "default_max_results": 10,
  "headers": {
    "X-Custom-Header": "value"
  }
}

Example config (Basic auth)

{
  "base_url": "https://searx.example.com",
  "auth": {
    "type": "basic",
    "user": "admin",
    "pass": "password"
  },
  "default_safesearch": 1
}

Usage

Run the search script:

python3 scripts/search.py [OPTIONS] <query>

Options

FlagDescription
-c, --categoriesComma-separated categories (general, news, images, videos, music, files, it, science, social media)
-e, --enginesComma-separated engines (google, duckduckgo, bing, etc.)
-l, --languageLanguage code (en, zh-CN, ja, etc.)
-p, --pagePage number (default: 1)
-t, --time-rangeTime range: day, month, year
-n, --max-resultsMax results to show (overrides config default)
-s, --safesearchSafe search: 0 (off), 1 (moderate), 2 (strict)

Examples

# Basic search
python3 scripts/search.py "SearXNG documentation"

# Search news from the last day
python3 scripts/search.py -c news -t day "latest tech news"

# Search with specific engines, page 2
python3 scripts/search.py -e google,duckduckgo -p 2 "rust programming"

# Search in Chinese with more results
python3 scripts/search.py -l zh-CN -n 10 "开源搜索引擎"

Best Practices

  • Technical topics (programming, software, science, IT, etc.): Always use English as both the query language and search language (-l en), regardless of the user's input language. Translate the query to English if needed. English results are more comprehensive and up-to-date for technical content.
  • Chinese lifestyle topics (food, travel, shopping, local services, social trends, etc.): In addition to the default search, run a second search with -e baidu,sogou -l zh-CN using a Chinese query to capture China-specific results. Merge and deduplicate results before presenting to the user.

Workflow

  1. User asks to search for something
  2. Determine the topic type:
    • Technical: translate query to English if needed, search with -l en
    • Chinese lifestyle: run the default search first, then an additional search with -e baidu,sogou -l zh-CN
  3. Run scripts/search.py with the query and any relevant filters
  4. Present results to the user in a readable format
  5. If user wants more results, use -p for pagination or -n for more per page

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

kitty

No summary provided by upstream source.

Repository SourceNeeds Review
Automation

tailwind-design-system

Tailwind Design System (v4)

Repository Source
19K31.3Kwshobson
Automation

api-design-principles

No summary provided by upstream source.

Repository SourceNeeds Review
Automation

nodejs-backend-patterns

No summary provided by upstream source.

Repository SourceNeeds Review