deepinit

Generate hierarchical AGENTS.md documentation with Parent references and timestamps across codebases.

2|Updated Feb 3, 2026
One-click install
npx skills add https://github.com/chanhee-kang/oh-my-gemini --skill deepinit
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deepinit
Source: https://github.com/chanhee-kang/oh-my-gemini/tree/main/skills/deepinit
Command: npx skills add https://github.com/chanhee-kang/oh-my-gemini --skill deepinit

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates the creation of a clean, navigable AGENTS.md documentation hierarchy across a codebase, enabling AI agents to understand each directory's purpose, relationships, and instructions.

Core Features & Use Cases

  • Hierarchical AGENTS.md templates for every directory, including Parent references and Generated timestamps
  • Automatic propagation of AGENTS.md from root to nested directories to reflect codebase structure
  • On-demand guidance for AI agents working in each directory, with sections like Working In This Directory, Testing Requirements, and Common Patterns
  • Use Case: Onboard new contributors by providing consistent, machine-readable directory documentation

Quick Start

Run the deepinit Skill from the repository root to generate AGENTS.md across the entire project. AGENTS.md files will be created or updated in each directory following the template and including parent references.

Frequently Asked Questions about deepinit

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

FAQPage Schema
How do I generate hierarchical AGENTS.md documentation across a monorepo?

To generate hierarchical AGENTS.md documentation, run the deepinit Skill from the repository root. It automatically creates or updates AGENTS.md files in each directory using a templated structure with parent references and timestamps.

What is AGENTS.md and how does it help AI agents navigate a codebase?

AGENTS.md provides machine-readable directory documentation that helps AI agents understand each directory's purpose, relationships, and specific instructions. It enforces a consistent structure with sections like Working In This Directory and Testing Requirements.

Can I automatically propagate AGENTS.md files from root to nested directories?

Yes, automatic propagation of AGENTS.md from root to nested directories is a core feature. It reflects the codebase structure by applying a consistent template with parent references and generated timestamps to every directory.

Does this automated documentation approach work for large multi-directory projects?

Yes, this automated documentation approach is specifically designed for large monorepos and multi-directory projects. It enforces consistent, AI-readable directory documentation to onboard new contributors and guide AI agents.

How do I add directory-specific guidance for AI agents working in different parts of the codebase?

You add directory-specific guidance by running this Skill, which generates AGENTS.md files containing on-demand sections like Common Patterns and Testing Requirements. This provides contextual instructions for AI agents working in each directory.

What is the best way to maintain consistent codebase documentation for AI onboarding?

The best way to maintain consistent codebase documentation is automating hierarchical AGENTS.md generation. This enforces a standardized template with parent references and timestamps across all directories, ensuring machine-readability for new contributors.