harbor

harbor-framework/harbor

Harbor is a framework for running agent evaluations and creating and using RL environments.

2,254 stars

1,097 forks

Python

25 views

View on GitHub Add to Favorites

Installation

Option 1: Use slash command in Claude Code

/install-skill https://github.com/harbor-framework/harbor

Option 2: Clone to skills directory

# Global (all projects)

git clone https://github.com/harbor-framework/harbor ~/.claude/skills/harbor

# Project-specific

git clone https://github.com/harbor-framework/harbor .claude/skills/harbor

Add MCP server to .cursor/mcp.json:

{
  "mcpServers": {
    "skillz": {
      "command": "npx",
      "args": ["-y", "skillz-mcp", "https://github.com/harbor-framework/harbor"]
    }
  }
}

Restart Cursor after adding the configuration.

Option 1: Use Gemini CLI command

gemini extensions install https://github.com/harbor-framework/harbor

Option 2: Clone to extensions directory

git clone https://github.com/harbor-framework/harbor ~/.gemini/extensions/harbor

Topics

evals rl-environments terminal-bench

Related Skills

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

skill-writer

Tensors and Dynamic neural networks in Python with strong GPU acceleration