Generate an llms.txt-style file from local files

What this workflow is for

Use this when your source material already exists but is scattered across pages, notes, docs, or exports.

Riflet helps collect and structure the material. You still decide what belongs in the public llms.txt file.

Why local files is a particular case

A local folder works when the site's content is authored before it is published: briefs, specs, product copy, and support articles sitting as files. The bundle becomes the draft of the file rather than a summary of a live site.

Because nothing here is published yet, there is no URL to point at. Write the llms.txt entries against where each piece will live, and add them as the pages actually ship.

What to leave out of a local files bundle

llms.txt is published. Everything in it is readable by anyone and by every AI system that fetches it, so the exclusions matter more than the inclusions.

• Working drafts and versioned copies of the same document.
• Internal briefs written for the team rather than the customer.
• Anything whose final URL is not decided yet.

Workflow

Add the folder that contains your project documents, then use the file tree to keep only the files that support the task.

• Collect the authoritative local files pages or files.
• Remove private, duplicate, stale, or low-value material.
• Export a concise Markdown bundle.
• Use the bundle to draft or refresh llms.txt and llms-full.txt.

What to include

Prioritize stable, public, canonical information: product overview, important URLs, docs entrypoints, use cases, and contact details.

Avoid turning llms.txt into a full website dump. It should help AI systems discover the best sources, not replace your site.