Updated March 2026

Install Skill Seekers

Pick your client, copy the command, done.

Local setup required. This server has to be cloned and prepared on your machine before you register it in Claude Code.

Run this once to clone and prepare the server before adding it to Claude Code.

Run in terminal

pip install skill-seekers

After the local setup is done, run this command to point Claude Code at the built server.

Run in terminal

claude mcp add skill-seekers -- node "<FULL_PATH_TO_SKILL_SEEKERS>/dist/index.js"

Replace <FULL_PATH_TO_SKILL_SEEKERS>/dist/index.js with the actual folder you prepared in step 1.

Available Tools (2)

Once configured, Skill Seekers gives your AI agent access to:

create_skillTransform a source (URL, repo, or local path) into a structured knowledge asset.

sourcetarget

package_skillPackage processed knowledge for specific AI targets like Claude, LangChain, or Cursor.

pathtarget

After setup, try these prompts with your AI agent:

→Create a new AI skill from the React documentation at https://docs.react.dev/

→Package the processed knowledge in output/react for use with Claude Code.

→Convert my local project folder into a RAG-ready knowledge asset for LlamaIndex.

→Generate a .cursorrules file from the documentation in my current repository.

Prerequisites & system requirements

An MCP-compatible client (Claude Code, Cursor, Windsurf, Claude Desktop, or Codex)
Python 3.8+ with pip installed

Save the docs, env vars, and workflow around Skill Seekers in Conare so Claude Code, Codex, and Cursor remember it next time.