What is the llms.txt standard?

The llms.txt standard is a convention for websites to host Markdown-based documentation specifically optimized for Large Language Models, making ingestion faster and more accurate than scraping HTML.

What happens if a website doesn't have an llms.txt file?

The skill includes a Recovery Protocol that diagnoses the failure and suggests falling back to traditional web scraping or manual documentation ingestion.

How does this skill handle different documentation sizes?

It checks for three variants in order: llms-full.txt (complete), llms.txt (standard), and llms-small.txt (condensed), allowing the AI to choose the version that best fits the current context window.

Can this skill be used with other scraping tools?

Yes, it is designed to integrate with tools like doc-scraper or skill-seekers, using llms.txt as a structured base that can be augmented by traditional scraping if necessary.

LLM Documentation Intelligence

Name: LLM Documentation Intelligence
Author: jmagly

byjmagly

•

102

•

学习与文档

Automates the detection and ingestion of llms.txt files to provide Claude with high-fidelity, LLM-optimized documentation.

This skill empowers Claude Code to bypass inefficient web scraping by identifying and utilizing the llms.txt standard for documentation delivery. By probing for hierarchical documentation levels—including full, standard, and condensed variants—it ensures that the AI receives the most relevant technical context without exceeding token limits or introducing scraping noise. It features robust error handling, automated content validation, and a recovery protocol that seamlessly bridges the gap between structured llms.txt files and traditional documentation extraction methods.

主要功能

01102 GitHub stars

02Integrated recovery protocol for falling back to traditional scraping

03Automated content validation to filter out error pages and redirects

04Smart variant selection based on context window availability

05Hierarchical detection of llms-full.txt, llms.txt, and llms-small.txt variants

06Pre-configured grounding checks to ensure documentation accuracy

使用场景

01Rapidly onboarding new frameworks or libraries that support LLM-friendly documentation

02Maintaining high-fidelity local documentation caches for agentic coding workflows

03Reducing token usage by ingesting condensed documentation variants

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add jmagly/aiwg llms-txt-support

For use in Claude.ai and ChatGPT