📚
AI EngineeringTypeScript

Deep Init

by Yeachan-Heo

Deep Init is an AI Engineering skill for Claude Code, published by Yeachan-Heo in oh-my-claudecode.

38.5K stars3.5K forkson Yeachan-Heo/oh-my-claudecodeAdded 2026/08/13Repository updated 2026/08/13
agentic-codingai-agentsautomationclaudeclaude-codemulti-agent-systemsoh-my-opencodeopencodeparallel-executionvibe-coding
Install in seconds
Install Deep Init
Copy Deep Init into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/Yeachan-Heo/oh-my-claudecode/tree/main/skills/deepinit ~/.claude/skills/deepinit

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/Yeachan-Heo/oh-my-claudecode.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
skills/deepinit/SKILL.md in Yeachan-Heo/oh-my-claudecode
Installs to
~/.claude/skills/deepinit
Collection
One of 25 skills cataloged from this repository
Category
AI Engineering2451 skills

What Deep Init does

Deep Init creates comprehensive, hierarchical AGENTS.md documentation across a codebase to help AI agents understand directory purpose, relationships, and conventions.

Deep Init is cataloged under AI Engineering on DirSkills. Deep Init comes from a repository tagged agentic-coding, ai-agents, automation, claude and claude-code.

Documentation

README

Deep Init Skill

Creates comprehensive, hierarchical AGENTS.md documentation across the entire codebase.

Core Concept

AGENTS.md files serve as AI-readable documentation that helps agents understand:

  • What each directory contains
  • How components relate to each other
  • Special instructions for working in that area
  • Dependencies and relationships

Hierarchical Tagging System

Every AGENTS.md (except root) includes a parent reference tag:

<!-- Parent: ../AGENTS.md -->

This is the opening of the README. Read the full README on GitHub.

Commands Deep Init provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

  • /src
  • /docs
  • /tests

Frequently asked about Deep Init

  • What else does Yeachan-Heo publish alongside Deep Init?

    Deep Init is one of 25 skills that DirSkills catalogs from Yeachan-Heo/oh-my-claudecode, the repository it ships in. Its siblings there include AI Slop Cleaner, Ask and Autopilot. Each one is a separate skill with its own page in this directory, installs the same way Deep Init does, and is maintained by Yeachan-Heo in that same repository. The rest of the collection is listed on the Yeachan-Heo/oh-my-claudecode page.

  • How does Deep Init compare to other AI Engineering skills?

    Deep Init ranks #138 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Deep Init against them. Open each page to compare what they document and how they install.

More from Yeachan-Heo/oh-my-claudecode

Deep Init is one of 25 skills cataloged on DirSkills from Yeachan-Heo/oh-my-claudecode.

See all 25 skills
🧹
3w ago

AI Slop Cleaner

AI Slop Cleaner removes code bloat, duplication, dead code, and needless abstraction from AI-generated code using a deletion-first, regression-safe workflow. It supports a reviewer-only mode to separate cleanup writing from review.
Quality
38.5K3.5K
🧭
3w ago

Ask

Ask routes a prompt through the local Claude, Codex, Gemini, Antigravity, Grok, or Cursor CLI via `omc ask` and persists the result as an ask artifact. Use it when you want to ask a local AI model a question or task and save the response.
AI Engineering
38.5K3.5K
🤖
3w ago

Autopilot

Autopilot turns a brief product idea into working code by autonomously handling requirements analysis, technical design, planning, parallel implementation, QA cycling, and multi-perspective validation. Use it when you want hands-off execution from a 2-3 line description to verified, working software.
AI Engineering
38.5K3.5K
🔁
3w ago

Autoresearch

Autoresearch runs one mission through bounded, evaluator-driven iterations and records each decision in durable logs. Use it when you have an existing mission and want persistent improvement until an explicit stop condition or max runtime is reached.
AI Engineering
38.5K3.5K
🧠
3w ago

CCG

CCG routes tasks through Codex and Antigravity/Gemini CLIs, then Claude synthesizes both outputs into one answer. Use it to get parallel external perspectives on architecture, code review, and UI without tmux team workers.
AI Engineering
38.5K3.5K
⏹️
3w ago

Cancel OMC Mode

Cancel OMC Mode detects and cancels the active Oh My Claude Code mode such as autopilot, ralph, ultrawork, or swarm. Use it to cleanly exit a workflow, release tasks, and clear state files.
AI Engineering
38.5K3.5K