Use Case
StartClaw-Optimizer is a powerful AI agent skill that extends your assistant with new capabilities. Master optimization system - APPLIES TO EVERY RESPONSE. Before responding, classify task complexity (simple question vs analysis vs coding). Use Haiku for simple/navigation/extraction/status. Use Sonnet ONLY for writing/analysis/planning/debugging. Monitor context size - if >50k tokens, recommend /compact. For automations, use scheduler wrapper. Never load full conversation history for simple tasks. Heartbeats always Haiku, single-line only. Never use Opus. This skill MUST run before every response to prevent 100k+ token bloat. This guide walks you through installing StartClaw-Optimizer, configuring it for your setup, and running your first commands β so you can start getting value in minutes.
Install StartClaw-Optimizer: npx clawhub@latest --dir ~/.claude/skills install startclaw-optimizer
Restart your AI client (Claude Code, Cursor, Gemini CLI, or OpenClaw)
Type a natural language request related to developer & devops to trigger StartClaw-Optimizer
Review the output and refine your prompt for better results
Combine StartClaw-Optimizer with other skills to build multi-step workflows
Copy these prompts and use them with your AI agent after installing StartClaw-Optimizer
Help me get started with StartClaw-Optimizer
What can StartClaw-Optimizer do for my developer & devops workflow?
Show me an example of using StartClaw-Optimizer
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install startclaw-optimizerOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install startclaw-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/startclaw-optimizer/π‘Extract and place the folder at the path above, then restart your agent.