Use Case
benchmark is a powerful AI agent skill that extends your assistant with new capabilities. Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics This guide walks you through installing benchmark, configuring it for your setup, and running your first commands β so you can start getting value in minutes.
Install benchmark: npx clawhub@latest --dir ~/.claude/skills install benchmark
Restart your AI client (Claude Code, Cursor, Gemini CLI, or OpenClaw)
Type a natural language request related to ai agent to trigger benchmark
Review the output and refine your prompt for better results
Combine benchmark with other skills to build multi-step workflows
Copy these prompts and use them with your AI agent after installing benchmark
Help me get started with benchmark
What can benchmark do for my ai agent workflow?
Show me an example of using benchmark
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install benchmarkOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install benchmarkβ οΈ Requires Node.js 18+. No Node? Use Option 2 below to download the ZIP instead. Install Node.js β
Option 2: Manual install (no Node required)
Download the ZIP, extract it, and place the folder at the path below. Restart your agent to activate.
Install path
~/.claude/skills/benchmark/π‘Extract and place the folder at the path above, then restart your agent.