ck:llms

Generate llms.txt and llms-full.txt indexes from documentation directories.

Updated May 10, 2026
One-click install
npx skills add https://github.com/dthuy62/kollet-app --skill ck-llms-dthuy62
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ck:llms
Source: https://github.com/dthuy62/kollet-app/tree/main/.opencode/skills/llms
Command: npx skills add https://github.com/dthuy62/kollet-app --skill ck-llms-dthuy62

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill turns a documentation folder or codebase into a concise, LLM-friendly index so people and agents can find the right docs without scanning everything manually.

Core Features & Use Cases

  • Curated Documentation Indexes: Builds llms.txt files with categorized links and brief descriptions.
  • Expanded Context Output: Can also generate llms-full.txt with inline content for deeper context.
  • Use Case: Use it when you are publishing docs, preparing AI context for a project, or organizing a large markdown knowledge base into a smarter table of contents.

Quick Start

Ask the skill to scan your docs directory and generate llms.txt, and include llms-full.txt if you want the expanded inline version.

Frequently Asked Questions about ck:llms

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

FAQPage Schema
How do I generate an llms.txt index for my markdown documentation directory?

To generate an llms.txt index, the Skill scans your markdown docs directory to extract titles and descriptions, then groups them into categorized link lists using deterministic Python scripts. It outputs a concise navigation summary optimized for LLM reading.

What is the difference between llms.txt and llms-full.txt for AI context preparation?

The llms.txt file provides a concise documentation index with categorized links and brief descriptions, while llms-full.txt exports expanded inline content for deeper context. Both files help agents find the right docs without scanning everything manually.

How do I build a categorized site map of my codebase docs for AI agents?

You can build a categorized site map by running the Skill's codebase scanning script over your documentation folder. It parses markdown files, extracts titles, groups links by category, and applies base URL building to produce a structured navigation summary.

Can I use this to prepare publishing workflows that need deterministic documentation outputs?

Yes, the Skill is designed for publishing workflows that need deterministic documentation outputs. It executes Python scripts to parse markdown and generate structured indexes, ensuring consistent and reproducible llms.txt and llms-full.txt files.

What is the best way to organize a large markdown knowledge base for LLM navigation?

The best way to organize a large markdown knowledge base is generating a curated documentation index. The Skill extracts titles and descriptions, groups them by category, and builds links with base URLs, creating a smarter table of contents for agents and users.

Do I need any external dependencies to run the llms.txt generation scripts?

No external dependencies are required to run the llms.txt generation scripts. The Skill uses deterministic Python-script execution built into its components, allowing it to parse markdown and extract content without installing additional packages.