โšก OMNISKILL v3.0 Documentation

llms.txt

What is llms.txt?

llms.txt is an emerging convention that provides a machine-readable index of a project's documentation. It lets Large Language Models (and any tool that works with them) instantly understand a project's purpose, structure, and capabilities โ€” without crawling dozens of files.

OMNISKILL generates two files:

File Purpose Size
llms.txt Concise index โ€” skill names, agent roles, pipeline chains, bundle contents ~10โ€“15 KB
llms-full.txt Complete dump โ€” every SKILL.md, AGENT.md, SYNAPSE.md, pipeline YAML, bundle YAML, and docs page ~500 KB โ€“ 3 MB

What OMNISKILL's llms.txt Contains

Concise Index (llms.txt)

Full Dump (llms-full.txt)

Contains the complete text content of every component file in the framework:

Each section is preceded by a separator (---), an H2 heading, and a > Source: line showing the file path.

How to Generate

# Generate both files (default)
omniskill generate llms-txt

# Generate only the concise index
omniskill generate llms-txt --concise

# Generate only the full dump
omniskill generate llms-txt --full

# Write to a custom directory
omniskill generate llms-txt --output ./dist/

# JSON output (for scripting)
omniskill --json generate llms-txt

# Verbose output (shows each component being processed)
omniskill --verbose generate llms-txt

Standalone Script

Works without the omniskill package installed โ€” only requires Python 3.10+ and PyYAML:

# Generate both files
python scripts/generate-llms-txt.py

# Concise only
python scripts/generate-llms-txt.py --concise

# Full only
python scripts/generate-llms-txt.py --full

# Custom output directory
python scripts/generate-llms-txt.py --output ./dist/

Where It's Deployed

When you push to the master branch, GitHub Actions automatically:

  1. Sets up Python 3.12
  2. Installs PyYAML
  3. Runs python scripts/generate-llms-txt.py
  4. Deploys both files to the docs site

After deployment, the files are available at:

Validation

You can check whether your local llms.txt files are up to date:

# Via CLI
omniskill validate --check-llms-txt

# Via standalone script
python scripts/validate.py --check-llms-txt

The validator regenerates the files in memory and compares them to the on-disk versions. It reports:

The staleness check is warning-only โ€” it never causes validation failures (exit code 2).