lfg

Orchestrate autonomous engineering workflows from planning through shipping.

Updated Aug 27, 2026

Search Tags:#automation #planning #execution #engineering #code-review #feature-development #autonomous-workflow

Ready to run

npx skills add https://github.com/mattjefferson/open-compound-engineering --skill lfg

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: lfg
Source: https://github.com/mattjefferson/open-compound-engineering/tree/main/skills/lfg
Command: npx skills add https://github.com/mattjefferson/open-compound-engineering --skill lfg

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Full autonomous engineering workflow that eliminates manual handoffs by orchestrating planning, deepening, execution, review, and shipping of features.

Core Features & Use Cases

End-to-end workflow chaining: plan, deepen plan, execute work, review changes, and ship the feature.
Optional persistence loop: attempts to clean up slash commands if ralph-wiggum is available, otherwise continues automatically.
Guardrails and testing: includes browser tests and optional video walkthroughs for verification.

Quick Start

Provide a feature description to begin the end-to-end autonomous workflow from planning to shipping.

Frequently Asked Questions about lfg

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

FAQPage Schema

How do I automate end-to-end feature delivery from planning to shipping?▼

Autonomous feature delivery automates the workflow from planning through shipping by orchestrating planning, deepening, execution, review, and release stages continuously. You provide a feature description, and the system drives the entire engineering process without manual handoffs.

Can I use an autonomous engineering workflow for bug fixes and improvements?▼

Yes, an autonomous engineering workflow applies to bug fixes and improvements in software projects. It coordinates the same end-to-end process—planning, execution, review, and shipping—ensuring continuous execution across various types of code changes.

What is the best way to orchestrate code review and feature development without manual handoffs?▼

Orchestrating code review and feature development without manual handoffs is achieved by chaining the workflow stages: plan, deepen plan, execute work, review changes, and ship. This eliminates manual intervention by applying guardrails and optional validation at each stage.

Does autonomous workflow execution include guardrails and error handling?▼

Yes, autonomous workflow execution includes guardrails and error handling to satisfy orchestration requirements. It features optional persistence and validation at each stage, and attempts to clean up slash commands if the persistence module is available, otherwise continuing automatically.

How do I verify changes during an autonomous feature delivery workflow?▼

You verify changes during autonomous feature delivery using built-in guardrails and testing. The workflow includes browser tests and optional video walkthroughs for verification, allowing you to validate execution results before the final shipping stage.

Do I need any dependencies to start an autonomous engineering workflow?▼

No dependencies are required to start an autonomous engineering workflow. The core orchestration runs independently, though it can optionally leverage a persistence module to clean up slash commands if available, otherwise it continues automatically without it.