Install SkillNet MCP

Pick your client, copy the command, done.

Manual setup required. The maintainer's config contains paths only you know - edit the placeholders below before adding it to Claude Code.

Run this once before adding it to Claude Code.

pip install skillnet-ai
npm install

claude mcp add skillnet-mcp -- node /absolute/path/to/skillnet-mcp/index.js

Replace any placeholder paths in the command with the real path on your machine.

Environment Variables

Set these before running SkillNet MCP.

VariableDescriptionRequired

API_KEYRequired for create_skill, evaluate_skill, and analyze_skills to communicate with LLM endpoints.No

GITHUB_TOKENOptional token to accelerate cloning and prevent rate-limits during skill creation.No

Once configured, SkillNet MCP gives your AI agent access to:

search_skillsSearch for available agent skills in the SkillNet library.

query

download_skillDownload a specific skill from the SkillNet library.

skill_id

create_skillCreate a new agent skill.

skill_namedescription

evaluate_skillEvaluate the performance or capabilities of a skill.

skill_id

analyze_skillsAnalyze existing skills for best practices or improvements.

skill_ids

After setup, try these prompts with your AI agent:

→Search for skills related to Kubernetes architecture best practices.

→Download the latest skill for automated Python unit testing.

→Analyze my current project structure and suggest relevant skills from SkillNet.

→Evaluate the performance of the skill with ID 'devops-security-001'.

Prerequisites & system requirements

An MCP-compatible client (Claude Code, Cursor, Windsurf, Claude Desktop, or Codex)
Node.js 18+ with npm/npx installed
Python 3.8+ with pip installed

Conare · memory for coding agents

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