deepinit

Generates hierarchical AI-CONTEXT.md documentation files by indexing codebase directory structures.

Updated Feb 26, 2026
One-click install
npx skills add https://github.com/VelkaressiaBlutkrone/spring-python-llm-exam-mng --skill deepinit-velkaressiablutkrone
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: deepinit
Source: https://github.com/VelkaressiaBlutkrone/spring-python-llm-exam-mng/tree/main/.claude/skills/deep-init
Command: npx skills add https://github.com/VelkaressiaBlutkrone/spring-python-llm-exam-mng --skill deepinit-velkaressiablutkrone

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Large or unfamiliar codebases are hard for AI agents to navigate without structured documentation. This Skill indexes a project and produces hierarchical AI-CONTEXT.md files so AI assistants can quickly understand each directory's purpose, files, and conventions. ## Core Features & Use Cases - Hierarchical Documentation: Creates an AI-CONTEXT.md in each directory with parent references, forming a traversable documentation tree. - Structured Templates: Each file includes purpose, key files, subdirectories, AI work guidelines, test instructions, and dependencies. - Incremental Updates: Compares existing AI-CONTEXT.md files and updates them while preserving sections marked with <!-- MANUAL --> tags. - Use Case: When onboarding an AI agent to a large Spring Boot or multi-module project, run this Skill once so every directory has an up-to-date guide the agent can consult during code changes. ## Quick Start Ask the AI to run /deepinit to document this codebase and generate AI-CONTEXT.md files for every directory.

Frequently Asked Questions about deepinit

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

FAQPage Schema
How do I generate AI documentation for an entire codebase?▼

Run the deepinit Skill, which maps the full directory structure, then creates an AI-CONTEXT.md in each directory describing its purpose, key files, subdirectories, and AI work guidelines. Directories are processed parent-first, with same-level directories handled in parallel.

What is an AI-CONTEXT.md file used for?▼

An AI-CONTEXT.md file gives AI agents a structured summary of a directory, including its purpose, important files, dependencies, testing instructions, and work conventions. Parent references link files into a traversable documentation tree.

Does regenerating documentation overwrite my manual edits?▼

No. Sections wrapped in <!-- MANUAL --> tags are preserved when AI-CONTEXT.md files are updated. The Skill compares existing files against the current codebase and only refreshes the generated portions.

Which directories are skipped during codebase indexing?▼

Empty directories are skipped unless they contain subdirectories, and ignorable folders such as node_modules, .git, and build outputs are identified and excluded before documentation generation begins.

When should I not use hierarchical codebase documentation?▼

For very small projects with only a few files, a single README is usually sufficient and per-directory context files add unnecessary overhead. The Skill is most valuable for large or growing codebases that AI agents must navigate repeatedly.