prompt-benchmark

manutej/categorical-meta-prompting

Systematic prompt evaluation framework with MATH, GSM8K, and Game of 24 benchmarks. Use when evaluating prompt effectiveness on standard benchmarks, comparing meta-prompting strategies quantitatively, measuring prompt quality improvements, or validating categorical prompt optimizations against ground truth datasets.

3 stars

1 forks

29 views

View on GitHub Add to Favorites

Installation

Option 1: Use slash command in Claude Code

/install-skill https://github.com/manutej/categorical-meta-prompting/tree/master/.claude/skills/prompt-benchmark

Option 2: Clone to skills directory

# Global (all projects)

git clone https://github.com/manutej/categorical-meta-prompting/tree/master/.claude/skills/prompt-benchmark ~/.claude/skills/categorical-meta-prompting

# Project-specific

git clone https://github.com/manutej/categorical-meta-prompting/tree/master/.claude/skills/prompt-benchmark .claude/skills/categorical-meta-prompting

Add MCP server to .cursor/mcp.json:

{
  "mcpServers": {
    "skillz": {
      "command": "npx",
      "args": ["-y", "skillz-mcp", "https://github.com/manutej/categorical-meta-prompting/tree/master/.claude/skills/prompt-benchmark"]
    }
  }
}

Restart Cursor after adding the configuration.

Option 1: Use Gemini CLI command

gemini extensions install https://github.com/manutej/categorical-meta-prompting/tree/master/.claude/skills/prompt-benchmark

Option 2: Clone to extensions directory

git clone https://github.com/manutej/categorical-meta-prompting/tree/master/.claude/skills/prompt-benchmark ~/.gemini/extensions/categorical-meta-prompting

Related Skills

camsnap

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

clawdis-canvas

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

sonoscli

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

clawdis-nodes

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞