llms.txt Documentation Extraction Guide

SkillWeb & browsing

Guide to llm.energy — extract llms.txt and install.md documentation from any website for AI agents, LLMs, and automation workflows. Features MCP server, REST API, batch processing, and multiple export formats. The documentation extraction standard for AI-ready content.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the llms.txt Documentation Extraction Guide skill

What this skill tells your AI

The instructions your AI receives, as published by nirholas/three.ws in data/skills/development/llms-txt-extraction-guide/SKILL.md and read by ahel’s review.

llm.energy extracts documentation from websites implementing the llms.txt and install.md standards. It transforms raw documentation into structured, agent-ready formats optimized for LLMs.

Standards

StandardPurposeSpecification
llms.txtMachine-readable documentationllmstxt.org
install.mdLLM-executable installation instructionsinstallmd.org

What It Does

Input: https://docs.chat.sperax.io
    │
    ▼
Auto-detects:
  ├── /llms.txt (summary)
  ├── /llms-full.txt (full docs)
  └── /install.md (setup instructions)
    │
    ▼
Output:
  ├── Individual markdown files per section
  ├── Single concatenated document
  ├── JSON structured output
  └── MCP-compatible tool responses

Quick Start

Web Interface

Visit llm.energy, paste a URL, and extract.

CLI

npx @llm-energy/cli extract https://docs.chat.sperax.io

MCP Server

{
  "mcpServers": {
    "llm-energy": {
      "command": "npx",
      "args": ["@llm-energy/mcp-server"]
    }
  }
}

MCP Tools

ToolDescription
extractDocsExtract llms.txt from a URL
extractFullExtract llms-full.txt (complete documentation)
extractInstallExtract install.md (setup instructions)
detectStandardsCheck which standards a site supports
batchExtractExtract from multiple URLs at once

REST API

# Extract documentation
curl https://llm.energy/api/extract?url=https://docs.chat.sperax.io

# Detect standards support
curl https://llm.energy/api/detect?url=https://docs.chat.sperax.io

# Batch extract
curl -X POST https://llm.energy/api/batch \
  -d '{"urls": ["https://docs.chat.sperax.io", "https://docs.aave.com"]}'

Export Formats

FormatBest For
MarkdownHuman reading, GitHub, documentation sites
JSONProgrammatic consumption, databases
Plain textLLM context windows, RAG pipelines
Split filesIndividual section storage

Use Cases

Build a Knowledge Base

Extract docs from multiple DeFi protocols to create a comprehensive AI knowledge base:

llm-energy batch \
  https://docs.chat.sperax.io \
  https://docs.aave.com \
  https://docs.uniswap.org \
  --output ./defi-knowledge/

Agent Documentation

Give AI agents up-to-date documentation for any tool or protocol they need to use.

SperaxOS Integration

llm.energy powers the documentation extraction in SperaxOS's knowledge base tool, enabling agents to ingest any protocol's docs on-demand.

Adding llms.txt to Your Site

To make your site AI-friendly, add these files:

/llms.txt (Summary)

# My Protocol

> One-line description

## Docs
- [Getting Started](https://docs.example.com/start)
- [API Reference](https://docs.example.com/api)

/llms-full.txt (Full Content)

Concatenation of all documentation pages in a single markdown file.

/install.md (Setup)

Step-by-step installation instructions that an LLM can execute.

Links

Signals

GitHub stars
114
Forks
29
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
llms-txt-extraction-guide
Source
github.com/nirholas/three.ws