Use Case
Execution Loop is a powerful AI agent skill that extends your assistant with new capabilities. Agent performs loop control. Used when the agent stops early, deviates from the task, or needs to perform control in headless mode. Does not apply to tool retries (with tool-governance). See context-memory (stage boundary handoff), quality-verification (post-edit check). This guide walks you through installing Execution Loop, configuring it for your setup, and running your first commands β so you can start getting value in minutes.
Install Execution Loop: npx clawhub@latest --dir ~/.claude/skills install execution-loop
Restart your AI client (Claude Code, Cursor, Gemini CLI, or OpenClaw)
Type a natural language request related to documents & notes to trigger Execution Loop
Review the output and refine your prompt for better results
Combine Execution Loop with other skills to build multi-step workflows
Copy these prompts and use them with your AI agent after installing Execution Loop
Help me get started with Execution Loop
What can Execution Loop do for my documents & notes workflow?
Show me an example of using Execution Loop
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install execution-loopOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install execution-loopβ 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/execution-loop/π‘Extract and place the folder at the path above, then restart your agent.