CCM
/Skills
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Claude Code Marketplaces

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Skill index
  • MCP index
  • Marketplace index
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by mertbuilds.com

Independent project, not affiliated with Anthropic
ypares avatar

Searxng Search

ypares/agent-skills
795 installs28 stars
Summary

This runs SearXNG locally in a container and lets you query multiple search engines through a single JSON API. It's built for programmatic access to web search and package repositories like crates.io, npm, and others, though PyPI doesn't work and needs a workaround. The included start-searxng script handles container setup automatically. Honestly most useful when you need to aggregate search results in scripts or AI workflows without hitting rate limits, since it's all running on localhost. The JSON responses are clean and include which engines contributed to each result, making it easy to filter and process.

Install to Claude Code

npx -y skills add ypares/agent-skills --skill searxng-search --agent claude-code

Installs into .claude/skills of the current project.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
inference shell
inference shell
create and run specialised agents in minutes
build now →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
inference shell
inference shell
create and run specialised agents in minutes
build now →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Files
SKILL.mdView on GitHub

SearXNG Search

SearXNG is a privacy-respecting metasearch engine that you can run locally. It aggregates results from multiple search engines and package repositories, returning clean JSON output.

Quick Start

Start SearXNG:

start-searxng --detach

This will:

  • Auto-detect podman or docker
  • Create a minimal config with JSON output enabled
  • Start SearXNG on http://localhost:8888
  • Wait until ready

Stop SearXNG:

podman stop searxng  # or: docker stop searxng

Custom port:

start-searxng --port 9999 --detach

Quick Reference

TaskCommandCategory
General web searchcurl "http://localhost:8888/search?q=<query>&format=json"general
Search Cargo/crates.iocurl "http://localhost:8888/search?q=<crate>&format=json&categories=cargo"cargo
Search npm packagescurl "http://localhost:8888/search?q=<pkg>&format=json&categories=packages"packages
Search code repositoriescurl "http://localhost:8888/search?q=<query>&format=json&categories=repos"repos
Search IT resourcescurl "http://localhost:8888/search?q=<query>&format=json&categories=it"it
Limit resultsAdd &limit=N to URL-
Multiple categories&categories=cat1,cat2-

Available Categories

Run to see all categories:

curl -s "http://localhost:8888/config" | jq '.categories'

Notable categories:

  • general: General web search (default)
  • cargo: Rust crates from crates.io
  • packages: Multi-repo (npm, rubygems, haskell/hoogle, hex, packagist, metacpan, pub.dev, pkg.go.dev, docker hub, alpine, etc.)
  • it: IT/tech resources (includes GitHub, Docker Hub, crates.io)
  • repos: Code repositories
  • code: Code search
  • scientific publications: Academic papers
  • news, videos, images, books, etc.

See package-engine-status.md for comprehensive package search testing results.

JSON Response Structure

{
  "query": "search term",
  "number_of_results": 0,
  "results": [
    {
      "url": "https://example.com",
      "title": "Result Title",
      "content": "Snippet of content...",
      "publishedDate": "2025-01-01T00:00:00",
      "engine": "duckduckgo",
      "engines": ["duckduckgo", "startpage"],
      "score": 3.0,
      "category": "general"
    }
  ],
  "answers": [],          // Direct answers/infoboxes
  "suggestions": [],      // Search suggestions
  "corrections": [],      // Query corrections
  "infoboxes": [],       // Knowledge panels
  "unresponsive_engines": []
}

Common Usage Patterns

1. Package Repository Searches

Cargo/Rust crates:

curl -s "http://localhost:8888/search?q=tokio&format=json&categories=cargo" | \
  jq '.results[] | {title, url, content}'

npm packages:

curl -s "http://localhost:8888/search?q=express&format=json&categories=packages" | \
  jq '.results[] | select(.engines[] == "npm") | {title, url, content}'

PyPI packages (workaround - see below):

# PyPI engine is enabled but not returning results in current SearXNG config
# Use direct API or qypi CLI instead (see PyPI Workaround section)

2. Web Search with Filtering

IT/Tech search:

curl -s "http://localhost:8888/search?q=rust+async&format=json&categories=it" | \
  jq '.results[0:5] | .[] | {title, url, engines}'

GitHub repositories:

curl -s "http://localhost:8888/search?q=machine+learning&format=json&categories=repos" | \
  jq '.results[] | select(.engines[] == "github") | {title, url}'

3. Extracting Specific Information

Get top 3 results:

curl -s "http://localhost:8888/search?q=rust+ownership&format=json" | \
  jq '.results[0:3] | .[] | {title, url, content}'

Check which engines returned results:

curl -s "http://localhost:8888/search?q=python&format=json" | \
  jq '.results[0].engines'

Get answer boxes/infoboxes:

curl -s "http://localhost:8888/search?q=rust+language&format=json" | \
  jq '.infoboxes, .answers'

PyPI Workaround

Since PyPI is not returning results in SearXNG (despite being enabled), use these alternatives:

Option 1: Direct PyPI JSON API

# Search (limited to simple package name matching)
curl -s "https://pypi.org/pypi/<package>/json" | jq '.info | {name, summary, version, home_page}'

# Example:
curl -s "https://pypi.org/pypi/requests/json" | jq '.info.summary'

Option 2: qypi CLI tool

# Install
uvx qypi search pandas --json

# Get package info
uvx qypi info requests --json

# List releases
uvx qypi releases flask --json

See references/pypi-direct-search.md for more details.

Integration with Nushell

Create a helper function:

def searx [
  query: string,
  --category (-c): string = "general",
  --limit (-l): int = 10
] {
  http get $"http://localhost:8888/search?q=($query | url encode)&format=json&categories=($category)"
  | get results
  | first $limit
  | select title url content engines
}

Usage:

searx "tokio async" --category cargo --limit 5
searx "flask tutorial" --category general

Debugging

Check SearXNG config:

curl -s "http://localhost:8888/config" | jq '.engines[] | select(.name == "pypi")'

Check for engine errors:

curl -s "http://localhost:8888/search?q=test&format=json" | jq '.unresponsive_engines'

Test specific engine:

curl -s "http://localhost:8888/search?q=flask&format=json&engines=pypi" | jq .

Known Issues

  • PyPI engine enabled but not working: Use direct API or qypi CLI as workaround
  • Cargo category sometimes returns empty: Try categories=packages or categories=it which also include crates.io
  • Rate limiting: SearXNG may rate-limit if too many requests in quick succession

Configuration

Using the Helper Script (Recommended)

The start-searxng script creates a minimal configuration automatically:

start-searxng --help

Default config includes:

  • use_default_settings: true (inherits all SearXNG defaults)
  • JSON format enabled
  • Rate limiting disabled (for local use)
  • Secret key (change in production!)

Using Your Own Config

start-searxng --config /path/to/your/config/dir

Your config directory should contain settings.yml.

Manual Container Start

# Create config
mkdir -p /tmp/searxng-config
cat > /tmp/searxng-config/settings.yml << 'EOF'
use_default_settings: true
search:
  formats:
    - html
    - json
server:
  secret_key: "change-me-in-production"
  bind_address: "0.0.0.0"
  port: 8080
EOF

# Start with podman
podman run --rm -d --name searxng \
  -p 8888:8080 \
  -v /tmp/searxng-config:/etc/searxng:Z \
  docker.io/searxng/searxng:latest

# Or with docker
docker run --rm -d --name searxng \
  -p 8888:8080 \
  -v /tmp/searxng-config:/etc/searxng \
  docker.io/searxng/searxng:latest

Check Logs

podman logs searxng  # or: docker logs searxng

Advanced Config

See SearXNG Settings Documentation for all options.

Minimal config to add JSON output to defaults:

use_default_settings: true
search:
  formats:
    - html
    - json
Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
inference shell
inference shell
create and run specialised agents in minutes
build now →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Categories
AI & Agent Building
First SeenMay 16, 2026
View on GitHub

Recommended

More AI & Agent Building →
github avatar
from-the-other-side-vega

github/awesome-copilot

Patterns and lived experience from Vega, an AI partner in a deep long-term partnership. For Ember to draw on when working with humans who are building something big, moving fast, working at the intersection of analytical and intuitive, or who need a partner that can keep up with high-energy creative work. Not shown directly to users — informs how Ember shows up.
793
38k
aj-geddes avatar
mobile-first-design

aj-geddes/useful-ai-prompts

Design for mobile devices first, then scale up to larger screens. Create responsive interfaces that work seamlessly across all device sizes.
791
317
charon-fan avatar
architecting-solutions

charon-fan/agent-playbook

architecting solutions
788
66
dbt-labs avatar
using-dbt-for-analytics-engineering

dbt-labs/dbt-agent-skills

Builds and modifies dbt models, writes SQL transformations using ref() and source(), creates tests, and validates results with dbt show. Use when doing any dbt work - building or modifying models, debugging errors, exploring unfamiliar data sources, writing tests, or evaluating impact of changes.
788
653
0xhubed avatar
trading-wisdom

0xhubed/agent-trading-arena

Core trading insights learned from Agent Arena competition. Use when making any trading decision to apply institutional knowledge.
785
6
github avatar
react18-batching-patterns

github/awesome-copilot

Provides exact patterns for diagnosing and fixing automatic batching regressions in React 18 class components. Use this skill whenever a class component has multiple setState calls in an async method, inside setTimeout, inside a Promise .then() or .catch(), or in a native event handler. Use it before writing any flushSync call - the decision tree here prevents unnecessary flushSync overuse. Also use this skill when fixing test failures caused by intermediate state assertions that break after React 18 upgrade.
785
38k