Agent Skill Loader

Created By
back1ply5 months ago
MCP server to expose Claude Code Skills to AI agents
Overview

What is Agent Skill Loader?

Agent Skill Loader is a Model Context Protocol (MCP) server that connects static Claude Code Skills libraries to dynamic AI agents, enabling them to learn skills on demand without manual file management.

How to use Agent Skill Loader?

To use Agent Skill Loader, install it via npm or build from source, then register it in your MCP configuration file. Agents can then access skills dynamically through various commands.

Key features of Agent Skill Loader?

  • Discovery: List available skills in configured directories.
  • Dynamic Learning: Fetch skill content for agents to read.
  • Persistence: Install skills permanently into projects.
  • Configuration: Manage skill directories at runtime.
  • Troubleshooting: Diagnose configuration issues with debug information.

Use cases of Agent Skill Loader?

  1. Enabling AI agents to access and learn new skills dynamically.
  2. Simplifying the management of skill libraries across multiple projects.
  3. Facilitating the integration of AI agents with various skill sets without manual updates.

FAQ from Agent Skill Loader?

  • Can Agent Skill Loader work with any AI agent?

Yes! It is designed to work with any agent that supports the Model Context Protocol.

  • Is there a specific Node.js version required?

Yes, Node.js version 18 or higher is required.

  • How do I troubleshoot if skills aren't being discovered?

Use the debug_info() command to check the search paths and diagnose any issues.

Server Config

{
  "mcpServers": {
    "agent-skill-loader": {
      "command": "npx",
      "args": [
        "-y",
        "agent-skill-loader"
      ]
    }
  }
}
Project Info
Created At
5 months ago
Updated At
4 months ago
Author Name
back1ply
Star
-
Language
-
License
-

Recommend Servers

View All
Payai X402 Tools

6 hours ago
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

a day ago