agentsclimarketplace

Llms txt

Skill marcelo-earth/llms-txt-generator/skills/llms-txt

Generate an llms.txt file for any project or website following the llmstxt.org specification. Use when asked to create llms.txt, generate LLM-friendly documentation, make a project AI-readable, or prepare documentation for language models.From its SKILL.md

Install
npx -y skills add marcelo-earth/llms-txt-generator --skill llms-txt

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.3 KB, 675 tokens by cl100k_base, as published. Nobody here has run it

llms.txt Generator

Generate a well-structured /llms.txt file following the llmstxt.org specification proposed by Jeremy Howard.

What is llms.txt?

A markdown file that helps LLMs understand and use a project/website efficiently. It provides:

  • Concise project overview
  • Links to key documentation with descriptions
  • Organized sections for different resource types

Generation Process

  1. Analyze the project structure using Glob to find:

    • README files
    • Documentation directories (docs/, documentation/, wiki/)
    • API documentation
    • Example files and tutorials
    • Configuration files that explain the project
    • Source code entry points
  2. Identify key information:

    • Project name and purpose
    • Main features and capabilities
    • Important caveats or limitations
    • Dependencies and requirements
  3. Generate the llms.txt following this exact format:

# Project Name

> Brief description of the project in 1-2 sentences. Include the most critical information needed to understand what this project does.

Key notes (if any important caveats exist):
- Important limitation or compatibility note
- Another critical detail

## Docs

- [Doc Title](url): Brief description of what this doc covers

## Examples

- [Example Title](url): What this example demonstrates

## API

- [API Reference](url): Description of API coverage

## Optional

- [Secondary Resource](url): Less critical but potentially useful

Format Rules

  1. H1 (Required): Project/site name - this is the ONLY required section
  2. Blockquote: Short summary with key context (highly recommended)
  3. Body text: Important notes, caveats, or guidance (optional)
  4. H2 Sections: Categorized lists of resources with URLs and descriptions
  5. Optional Section: Resources that can be skipped for shorter context

Best Practices

  • Be concise: LLMs have limited context windows
  • Prioritize: Put most important resources first
  • Describe well: Each link should have a brief, informative description
  • Use "Optional" wisely: Secondary resources that aren't always needed
  • Avoid jargon: Explain terms that aren't universally known
  • Include external links: Reference external docs if helpful (e.g., framework docs)

URL Handling

  • For websites: Use absolute URLs (https://example.com/docs/api.md)
  • For repositories: Use relative paths or raw GitHub URLs
  • Suggest creating .md versions of HTML pages at same URL + .md extension

Output

Write the generated llms.txt to:

  • $ARGUMENTS if provided
  • Otherwise, project root as llms.txt

After generating, briefly explain what was included and why.

Reference Examples

For examples of well-crafted llms.txt files, see references/examples.md.


Note: This skill does not require external scripts. The analysis and generation is performed directly using available tools (Glob, Grep, Read) to understand the project structure and generate appropriate content.

What ships with it: 1 file

5.3 KB alongside SKILL.md

references/

Keep looking

Skills are one crate of 326,835. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.