# Send Advanced Searxng Search Skill to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - Download the package from Yavira. - Extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the extracted folder. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "searxng-search-skill", "name": "Advanced Searxng Search Skill", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/elmaslouhymouaad/searxng-search-skill", "canonicalUrl": "https://clawhub.ai/elmaslouhymouaad/searxng-search-skill", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/searxng-search-skill", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=searxng-search-skill", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "README.md", "SKILL.md", "pyproject.toml", "requirements.txt", "searxng_skill/__init__.py", "searxng_skill/config.py" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-23T16:43:11.935Z", "expiresAt": "2026-04-30T16:43:11.935Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/searxng-search-skill" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/searxng-search-skill", "downloadUrl": "https://openagent3.xyz/downloads/searxng-search-skill", "agentUrl": "https://openagent3.xyz/skills/searxng-search-skill/agent", "manifestUrl": "https://openagent3.xyz/skills/searxng-search-skill/agent.json", "briefUrl": "https://openagent3.xyz/skills/searxng-search-skill/agent.md" } } ``` ## Documentation ### SearXNG Advanced Search Skill --- name: searxng-skill description: Advanced Python library for SearXNG metasearch with retry logic, timeout handling, and comprehensive search patterns. homepage: https://github.com/yourusername/searxng-skill metadata: {"clawdbot":{"emoji":"🔍","requires":{"python":">=3.8","packages":["requests","urllib3","python-dotenv"]},"install":[{"id":"pip","kind":"pip","package":"searxng-skill","label":"Install searxng-skill (pip)"},{"id":"local","kind":"local","command":"pip install -e .","label":"Install from source"}]}} --- # searxng-skill Use \`searxng-skill\` for privacy-focused metasearch with local/remote SearXNG instances. Supports retry logic, timeout handling, and advanced search patterns. ## Setup (once) **Environment variables (recommended)** \`\`\`bash # Create .env file cat > .env << EOF SEARXNG_URL=http://localhost:8080 SEARXNG_TIMEOUT=10 SEARXNG_MAX_RETRIES=3 SEARXNG_RETRY_DELAY=1.0 SEARXNG_BACKOFF_FACTOR=2.0 SEARXNG_VERIFY_SSL=true SEARXNG_LANGUAGE=en EOF Or configuration file # Create config.json cat > config.json << EOF { "instance_url": "http://localhost:8080", "default_timeout": 10, "max_retries": 3, "retry_delay": 1.0, "backoff_factor": 2.0, "verify_ssl": true, "default_language": "en" } EOF Initialize in code from searxng_skill import SearXNGSkill, SearXNGConfig # From environment config = SearXNGConfig.from_env() skill = SearXNGSkill(config=config) # From file config = SearXNGConfig.from_file("config.json") skill = SearXNGSkill(config=config) # Direct skill = SearXNGSkill(instance_url="http://localhost:8080") ### Common Commands Basic search from searxng_skill import SearXNGSkill skill = SearXNGSkill(instance_url="http://localhost:8080") results = skill.search("Python programming") # Access results for result in results["results"][:10]: print(f"{result['title']} - {result['url']}") Category search from searxng_skill import SearchCategory # Single category results = skill.search("AI", categories=[SearchCategory.NEWS]) # Multiple categories results = skill.search( "climate change", categories=[SearchCategory.NEWS, SearchCategory.SCIENCE] ) Time-filtered search from searxng_skill import TimeRange # Recent news (last 24 hours) news = skill.news_search("AI breakthrough", time_range=TimeRange.DAY) # Last week results = skill.search("Python", time_range=TimeRange.WEEK) Image search from searxng_skill import SafeSearch images = skill.image_search( "nature photography", safesearch=SafeSearch.STRICT ) for img in images[:10]: print(f"{img['title']}: {img.get('img_src', 'N/A')}") Video search videos = skill.video_search("Python tutorial") for video in videos[:5]: print(f"{video['title']} ({video.get('duration', 'N/A')})") Advanced search with operators results = skill.advanced_search( query="machine learning", exact_phrase="deep learning", exclude_words=["tutorial", "beginner"], site="github.com", filetype="pdf" ) Engine-specific search results = skill.search( "quantum computing", engines=["google", "duckduckgo", "wikipedia"] ) Structured search response = skill.search_structured("artificial intelligence") print(f"Query: {response.query}") print(f"Total: {response.number_of_results}") for result in response.results[:5]: print(f"{result.title} [{result.engine}]") print(f" {result.url}") print(f" Score: {result.score}\\n") Autocomplete suggestions = skill.autocomplete("artificial int") # ['artificial intelligence', 'artificial intelligence news', ...] Multi-category search categorized = skill.multi_category_search( "climate change", categories=[ SearchCategory.GENERAL, SearchCategory.NEWS, SearchCategory.SCIENCE ] ) for category, results in categorized.items(): print(f"{category}: {len(results)} results") Parallel searches queries = ["Python", "JavaScript", "Go", "Rust"] results = skill.parallel_search(queries, categories=[SearchCategory.IT]) for query, result_data in results.items(): print(f"{query}: {len(result_data.get('results', []))} results") Paginated search # Get multiple pages all_results = [] for page in range(1, 4): results = skill.search("AI", page=page) all_results.extend(results["results"]) print(f"Total results: {len(all_results)}") Health check if skill.health_check(): print("✓ SearXNG instance is healthy") else: print("✗ Instance unavailable") Get engine info engines = skill.get_engines_info() for engine in engines[:10]: print(f"{engine.name} - {', '.join(engine.categories)}") print(f" Enabled: {engine.enabled}") Export results from searxng_skill.utils import export_results_json, export_results_csv results = skill.search("machine learning") # Export to JSON export_results_json(results, "results.json") # Export to CSV export_results_csv(results["results"], "results.csv") ### Quick Reference Search Categories SearchCategory.GENERAL # General web search SearchCategory.IMAGES # Image search SearchCategory.VIDEOS # Video search SearchCategory.NEWS # News articles SearchCategory.MAP # Maps SearchCategory.MUSIC # Music SearchCategory.IT # IT/Tech SearchCategory.SCIENCE # Scientific papers SearchCategory.FILES # File search SearchCategory.SOCIAL_MEDIA # Social media Time Ranges TimeRange.DAY # Last 24 hours TimeRange.WEEK # Last 7 days TimeRange.MONTH # Last 30 days TimeRange.YEAR # Last year TimeRange.ALL # All time Safe Search Levels SafeSearch.NONE # No filtering (0) SafeSearch.MODERATE # Moderate filtering (1) SafeSearch.STRICT # Strict filtering (2) ### Notes Environment variable shortcuts Set SEARXNG_URL=http://localhost:8080 to avoid repeating instance URL Set SEARXNG_LANGUAGE=en for default language Set SEARXNG_MAX_RETRIES=5 for custom retry behavior For scripting Use format=OutputFormat.JSON for structured output (default) Set verify_ssl=False for local development only Implement rate limiting with time.sleep() between requests Use health_check() before batch operations Performance tips Reuse SearXNGSkill instance for multiple searches Use parallel_search() for independent queries Cache results with functools.lru_cache for repeated queries Set appropriate timeouts: fast queries (5s), complex queries (30s) Retry behavior Automatic retry with exponential backoff on timeout/connection errors Default: 3 retries, 1s initial delay, 2x backoff factor Customize: max_retries, retry_delay, backoff_factor No retry on HTTP 4xx/5xx errors Error handling from searxng_skill.exceptions import TimeoutException, ConnectionException try: results = skill.search("query", timeout=5) except TimeoutException: print("Request timed out - try increasing timeout") except ConnectionException: print("Cannot connect to instance - check URL and network") Fallback instance try: skill = SearXNGSkill(instance_url="http://localhost:8080") results = skill.search("query") except ConnectionException: # Fallback to public instance skill = SearXNGSkill(instance_url="https://searx.be") results = skill.search("query") Local instance setup # Docker docker run -d -p 8080:8080 searxng/searxng # Verify curl http://localhost:8080/healthz Confirm before operations Always validate query is not empty: if query.strip(): ... Check results exist: if "results" in results: ... Validate URLs before requests: validate_url(url) ### Advanced Usage Custom retry strategy from searxng_skill.retry import RetryStrategy strategy = RetryStrategy( max_retries=5, initial_delay=2.0, backoff_factor=1.5, max_delay=60.0, jitter=True ) skill = SearXNGSkill( instance_url="http://localhost:8080", max_retries=5, retry_delay=2.0, backoff_factor=1.5 ) Batch processing import time queries = ["Python", "Java", "Go", "Rust"] for query in queries: results = skill.search(query) print(f"{query}: {len(results['results'])} results") time.sleep(1) # Rate limiting Result deduplication from searxng_skill.utils import deduplicate_results results = skill.search("AI") unique = deduplicate_results(results["results"], key="url") Merge multiple searches from searxng_skill.utils import merge_search_results r1 = skill.search("Python", engines=["google"]) r2 = skill.search("Python", engines=["duckduckgo"]) merged = merge_search_results([r1, r2]) Logging import logging logging.basicConfig(level=logging.INFO) logger = logging.getLogger(__name__) logger.info("Searching for: Python") results = skill.search("Python") logger.info(f"Found {len(results['results'])} results") ### API Methods MethodPurposeReturnssearch()Basic searchDict[str, Any]search_structured()Structured searchSearchResponseautocomplete()Get suggestionsList[str]image_search()Image-specificList[Dict]news_search()News-specificList[Dict]video_search()Video-specificList[Dict]advanced_search()With operatorsDict[str, Any]multi_category_search()Multiple categoriesDict[str, List]parallel_search()Multiple queriesDict[str, Dict]health_check()Instance statusboolget_engines_info()Engine detailsList[EngineInfo] ### Troubleshooting Connection refused # Check instance is running curl http://localhost:8080/healthz # Or in Python if not skill.health_check(): print("Instance is down") SSL errors (local development) skill = SearXNGSkill( instance_url="http://localhost:8080", verify_ssl=False # Only for local dev! ) Timeout issues # Increase timeout skill = SearXNGSkill( instance_url="http://localhost:8080", default_timeout=30 ) # Or per-request results = skill.search("query", timeout=30) No results # Check enabled engines engines = skill.get_engines_info() enabled = [e for e in engines if e.enabled] print(f"Enabled: {len(enabled)} engines") # Try specific engines results = skill.search("query", engines=["duckduckgo"]) ## Trust - Source: tencent - Verification: Indexed source record - Publisher: elmaslouhymouaad - Version: 0.1.1 ## Source health - Status: healthy - Source download looks usable. - Yavira can redirect you to the upstream package for this source. - Health scope: source - Reason: direct_download_ok - Checked at: 2026-04-23T16:43:11.935Z - Expires at: 2026-04-30T16:43:11.935Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/searxng-search-skill) - [Send to Agent page](https://openagent3.xyz/skills/searxng-search-skill/agent) - [JSON manifest](https://openagent3.xyz/skills/searxng-search-skill/agent.json) - [Markdown brief](https://openagent3.xyz/skills/searxng-search-skill/agent.md) - [Download page](https://openagent3.xyz/downloads/searxng-search-skill)