One-click install
npx skills add https://github.com/roerohan/skills --skill index-knowledge-roerohan
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: index-knowledge
Source: https://github.com/roerohan/skills/tree/main/index-knowledge
Command: npx skills add https://github.com/roerohan/skills --skill index-knowledge-roerohan

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Codebases often lack structured, hierarchical knowledge documentation, forcing AI agents and developers to sift through irrelevant context or miss critical project-specific conventions, anti-patterns, and architectural details when working on specific modules.

Core Features & Use Cases

  • Hierarchical AGENTS.md Generation: Creates root-level and subdirectory-level AGENTS.md files tailored to each part of the codebase, avoiding redundant generic content.
  • Complexity-Scoped Documentation: Uses a scoring matrix to only document high-complexity or distinct-domain directories, so low-complexity areas are covered by parent docs without bloat.
  • Use Case: For a large monorepo with 10+ modules, this skill automatically generates a root knowledge base plus per-module docs, letting agents instantly access relevant context for any task without loading the entire codebase context every time.

Quick Start

Use the index-knowledge skill to generate a complete hierarchical AGENTS.md knowledge base for your current codebase.

Frequently Asked Questions about index-knowledge

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

FAQPage Schema
How do I generate an AGENTS.md knowledge base for my codebase?

To generate an AGENTS.md knowledge base, use a skill that produces hierarchical, scoped documentation for AI agents and developers. It creates root-level and subdirectory-level files covering project structure, conventions, anti-patterns, and code maps without redundant generic content.

What is the best way to document a monorepo with multiple modules for AI agents?

Documenting a monorepo for AI agents requires hierarchical knowledge bases that provide scoped context for specific modules. This approach generates a root knowledge base plus per-module docs, letting agents instantly access relevant context without loading the entire codebase context every time.

How does complexity-scoped codebase documentation avoid content bloat?

Complexity-scoped codebase documentation uses a scoring matrix to only document high-complexity or distinct-domain directories. Low-complexity areas are covered by parent docs, ensuring the generated AGENTS.md files contain no generic or irrelevant content and preventing documentation bloat.

Can I auto-generate codebase onboarding documentation for nested directories?

Yes, you can auto-generate codebase onboarding documentation for nested directories. The process analyzes the repository structure and produces non-redundant AGENTS.md files at the root and high-complexity subdirectories, capturing project-specific conventions and architectural details.

Why do AI agents need scoped context from hierarchical codebase documentation?

AI agents need scoped context because codebases often lack structured knowledge documentation, forcing agents to sift through irrelevant context or miss critical project-specific conventions. Hierarchical AGENTS.md files provide structured, scoped context for any task within specific modules.