skills.rest
CaptainCrouton89
CaptainCrouton89COMMUNITY
Explore all skills by this author →
Website𝕏@SilasRhyneer1GitHub

Writing Documentation for LLMs

Write documentation for LLMs with progressive disclosure and consistent terminology.

497|68|Updated Sep 7, 2025
Search Tags:#documentation#technical writing#LLM#content structure#API documentation#AI-friendly
One-click install
npx skills add https://github.com/CaptainCrouton89/.claude --skill writing-documentation-for-llms
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Writing Documentation for LLMs
Source: https://github.com/CaptainCrouton89/.claude/tree/main/.claude/skills/llm-documentation
Command: npx skills add https://github.com/CaptainCrouton89/.claude --skill writing-documentation-for-llms

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill teaches you how to write documentation that Large Language Models (LLMs) can effectively discover, understand, and utilize. It addresses the challenge of creating AI-friendly reference materials, API docs, and feature specifications, ensuring your LLM-powered workflows are efficient and accurate.

Core Features & Use Cases

  • LLM-Optimized Structure: Learn progressive disclosure and consistent terminology for better AI comprehension.
  • Content Patterns: Master "what + when" descriptions, examples over explanations, and clear workflows.
  • Use Case: When documenting a new API, a complex feature, or creating a knowledge base, this Skill guides you to structure content so Claude can autonomously find and apply the information, reducing repetitive prompting.

Quick Start

Good description for LLM discovery

---

description: Extract text and tables from PDF files, fill forms, merge documents.

Use when working with PDF files or when the user mentions PDFs, forms, or extraction.

---

Bad description (too vague)

---

description: Helps with documents

---

Frequently Asked Questions about Writing Documentation for LLMs

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

FAQPage Schema
How do I structure documentation so LLMs can understand and use it effectively?▼

Structure documentation with progressive disclosure, consistent terminology, and concrete examples before explanations. This organization helps LLMs discover and apply information autonomously, reducing repetitive prompting and improving accuracy in AI-powered workflows.

What makes API documentation AI-friendly?▼

AI-friendly API documentation uses "what + when" descriptions that specify the function's purpose and context for use. Include concrete usage examples upfront, clear workflows, and consistent naming conventions so LLMs can reliably locate and apply the correct API calls.

Can I use this approach for knowledge bases and feature specifications?▼

Yes. This documentation method applies to code, APIs, features, and knowledge bases. The same principles—progressive disclosure, terminology consistency, examples-first content patterns, and validator-driven quality checks—improve LLM comprehension across all documentation types.

How do I evaluate whether my documentation is LLM-ready?▼

Apply validator-driven quality checks based on the core requirements: consistent terminology throughout, progressive disclosure of complexity, concrete examples before abstract explanations, and clear "what + when" descriptions. These checks ensure your documentation meets LLM comprehension standards.

Why does vague documentation hurt LLM performance?▼

Vague descriptions lack the specificity LLMs need to distinguish use cases and locate relevant information. Generic language like "helps with documents" provides no context for discovery. Precise, task-focused descriptions enable LLMs to autonomously select the right information for user queries.

Related Skills

Explore More Software Engineering Skills→
viktorbezdekviktorbezdek
10

consistency-standards

Audit codebases and documentation for naming, terminology, and reuse inconsistencies.

Community
Intermediate
yusufcmgyusufcmg
1

rag-implementation

Implement Retrieval-Augmented Generation systems with vector databases and semantic search.

Community
Advanced
d0whc3rd0whc3r

llm-prompt-optimizer

Diagnose and rewrite LLM prompts using RSCIT, Chain-of-Thought, and Few-Shot patterns.

Community
Advanced
liuaibin001liuaibin001

writing-skills

Create SKILL.md files with YAML frontmatter and reference file organization.

Community
Intermediate