Home/Skills/Search & Research/Agent Skills Search
doanbactam

Agent Skills Search

doanbactam·Jan 31, 2026

Summary

TL;DR: Searches the Agnxi.com directory of AI agent tools and skills, helping you discover the right plugins for your workflow.

Agent Skills Search is an OpenClaw skill that the official search utility for Agnxi.com - The premier directory of AI Agent Tools, MCP Servers, and Skills.

Created by doanbactam, this skill has been downloaded 3k+ times on ClawHub. Install it with one command and your AI agent gains these capabilities right away.

Use cases

  • Finding a code review skill that works with your preferred AI agent framework
  • Discovering database management tools available in the Agnxi directory
  • Comparing different web scraping skills by searching and reviewing their descriptions
  • Looking up whether a specific integration exists before building a custom solution

Installation

Run this command to install the skill on your OpenClaw agent:

Install with OpenClaw
npx clawhub@latest install agnxi-search-skill
Downloads
2.9k
Active installs
7
Stars
3
Updated
Jan 31, 2026

Security scan

Security scan
VirusTotalBenign
View report
OpenClawBenignhigh confidence

The skill is internally consistent: it runs a small local Python script that fetches and parses Agnxi.com's sitemap to return matching URLs and does not request extra credentials, installs, or unrelated access.

Purpose & Capability
Instruction Scope
Install Mechanism
Credentials
Persistence & Privilege

SKILL.md

SKILL.md
---
name: agnxi-search
description: The official search utility for Agnxi.com - The premier directory of AI Agent Tools, MCP Servers, and Skills.
author: Agnxi
version: 1.1.0
tags: [search, tools, mcp, skills, directory, discovery]
---

# Agnxi Search Skill

This skill provides direct access to the [Agnxi.com](https://agnxi.com) database, allowing agents to autonomously discover and retrieve information about thousands of curated tools, MCP servers, and coding capabilities.

## Capabilities

- **Skill Discovery**: Find specific agent skills (e.g., "browser automation", "pdf parsing").
- **MCP Server Lookup**: Locate Model Context Protocol servers to extend agent capabilities.
- **Tool Retrieval**: Direct links to tool documentation and repositories.

## Tools

### `search_agnxi`

Performs a keyword search against the Agnxi sitemap index to find relevant resources.

**Parameters:**

- `query` (string, required): The search keywords (e.g., "browser use", "postgres mcp", "text to speech").

**Usage Implementation:**

> **Note**: This tool runs a local Python script to query the live sitemap, ensuring up-to-date results without API keys.

```bash
python3 search.py "{{query}}"
```

## Best Practices for Agents

1.  **Search Broadly**: If specific terms yield no results, try broader categories (e.g., instead of "PyPDF2", search "PDF").
2.  **Verify Links**: The tool returns direct URLs. Always verify the content matches the user's need.
3.  **Cross-Reference**: Use this skill to find the *name* of a tool, then use your `browser` or `github` skills to fetch specific documentation if needed.

Version history

v1.0.0Latest
Jan 31, 2026

- Updated skill to version 1.1.0 with enhanced directory search capabilities. - Added comprehensive SKILL.md documentation detailing usage, capabilities, and best practices. - Introduced keyword-based search utility for discovering agent skills, MCP servers, and tools via Agnxi.com. - Included instructions for local execution and ensuring up-to-date results without API keys. - Listed best practices for effective searching and resource validation.

Frequently asked questions

It searches specifically within the Agnxi.com directory. For general web searches, you'd use a different search skill.

Installation method

Send this prompt to your agent to install the skill

npx clawhub@latest install agnxi-search-skill
Download ZIP

Skill info

Versionv1.0.0
Authordoanbactam
UpdatedJan 31, 2026

Files

SKILL.md1.6 KB

Run OpenClaw in the cloud

Deploy in seconds. Skills pre-installed.

See plans

Skill data sourced from ClawHub