auto

Manage autonomous coding loops with task selection, quality checks, and commits.

Updated Feb 17, 2026
One-click install
npx skills add https://github.com/cuemby/cloud-marketplace --skill auto-cuemby
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: auto
Source: https://github.com/cuemby/cloud-marketplace/tree/main/.claude/skills/auto
Command: npx skills add https://github.com/cuemby/cloud-marketplace --skill auto-cuemby

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill enables AI agents to work autonomously, independently selecting and completing tasks from a structured list without constant human supervision, facilitating "away from keyboard" development.

Core Features & Use Cases

  • Autonomous Task Execution: AI agents can independently pick, implement, and commit tasks based on priority and dependencies.
  • State Persistence: Project progress, learnings, and task status are maintained through files like prd.json and progress.md, not conversation history.
  • Use Case: Kick off a complex feature development, and let the AI handle the iterative coding, testing, and committing process overnight or while you focus on other priorities.

Quick Start

Start the autonomous development loop for the project defined in .claude/tasks/0001-prd-feature.md.

Frequently Asked Questions about auto

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I set up an autonomous AI coding loop for unattended development?

To start an autonomous AI coding loop, define a structured task list in a `prd.json` file and initiate the loop. The AI agent manages task selection, implementation, quality checks, and commits independently across multiple context windows.

How does state persistence work across multiple context windows in AFK development?

State persistence in AFK development relies on persistent files like `progress.md` and `CLAUDE.md` instead of conversation history. This maintains project progress, learnings, and task status across different context windows.

Do I need a defined PRD to start autonomous task execution?

Yes, a defined PRD and task breakdown are required for execution. The autonomous AI agent uses this structured task list to independently pick, implement, and commit tasks based on priority and dependencies.

What is the best way to manage task selection and commits with an AI agent?

The best way to manage task selection and commits is using a structured `prd.json` file. The AI agent autonomously selects tasks, implements code, runs quality checks, and handles commit processes without human supervision.

Can I run workflow automation for coding overnight without constant supervision?

Yes, you can run workflow automation for coding overnight. The AI agent works autonomously, independently selecting and completing tasks from a structured list without constant human supervision, enabling away from keyboard development.

Why does the AI agent use persistent files instead of conversation history?

The AI agent uses persistent files like `progress.md` and `CLAUDE.md` instead of conversation history to maintain state. This ensures project progress and task status are preserved across multiple context windows during unattended development.