Use Case
Inference Optimizer is a powerful AI agent skill that extends your assistant with new capabilities. Audit OpenClaw runtime health first, then optimize inference speed and token usage with approval. Use /audit for analyze-only and /optimize for analyze + act... This guide walks you through installing Inference Optimizer, configuring it for your setup, and running your first commands β so you can start getting value in minutes.
Install Inference Optimizer: npx clawhub@latest --dir ~/.claude/skills install inference-optimizer
Restart your AI client (Claude Code, Cursor, Gemini CLI, or OpenClaw)
Type a natural language request related to ai agent & automation to trigger Inference Optimizer
Review the output and refine your prompt for better results
Combine Inference Optimizer with other skills to build multi-step workflows
Copy these prompts and use them with your AI agent after installing Inference Optimizer
Help me get started with Inference Optimizer
What can Inference Optimizer do for my ai agent & automation workflow?
Show me an example of using Inference Optimizer
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install inference-optimizerOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install inference-optimizerβ 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/inference-optimizer/π‘Extract and place the folder at the path above, then restart your agent.