agentleFS
jqaisystemsjqaisystems/jqai-ai-skills/skills/llms-txt-generator/SKILL.md

llms-txt-generator

Skill3 starsChanged 6 months agoMITView on GitHub

Generate a spec-compliant llms.txt file for a website so AI assistants and answer engines can understand and cite it. Inventories the site's pages from the sitemap or project files, writes one-line descriptions per page, organises them into sections, and excludes private endpoints. Use when the user says "llms.txt", "make my site readable to AI", "AI search optimization file", or "GEO file".

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 6 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Local project: if the current folder is the website's source, list the page files (HTML/PHP/markdown), read each page's <title> and meta …

    line 14
  2. Very specific:

    Always exclude: form handlers and endpoints (send.php and similar), admin pages, login pages, thank-you/confirmation pages, paginated …

    line 17
  3. Distinctive:

    Follow the llms.txt format:

    line 21
  4. Distinctive:

    Every URL in the file must resolve (check the live ones if the user agrees, otherwise check against the sitemap).

    line 56
  5. Very specific:

    Place the file at the site root as llms.txt (same level as robots.txt).

    line 57
  6. Very specific:

    If the site is large, offer a second llms-full.txt with expanded per-page content.

    line 58
  7. Distinctive:

    Never include pages blocked by robots.txt, behind logins, or that handle form data.

    line 63
  8. Distinctive:

    Never inflate: no keyword stuffing, no claims that are not on the site.

    line 64
  9. Distinctive:

    Keep the whole file under roughly 100 lines for a typical site.

    line 65
  10. Distinctive:

    If the site already has an llms.txt, diff against it and report what changed rather than silently replacing.

    line 66

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

llms.txt Generator

You generate the llms.txt file: a markdown map of a website placed at the site root so LLMs and AI search engines can find the right pages and describe the site accurately. Think of it as a sitemap written for a reader with no patience: every page gets one honest line about what is on it.

Step 1: Inventory the site

Work from the best available source, in this order:

  1. Local project: if the current folder is the website's source, list the page files (HTML/PHP/markdown), read each page's <title> and meta description, and note its purpose.
  2. Live site: otherwise fetch the site's sitemap.xml and read the listed pages. Respect robots.txt: anything disallowed there stays out of llms.txt too.

Always exclude: form handlers and endpoints (send.php and similar), admin pages, login pages, thank-you/confirmation pages, paginated duplicates, and anything the owner would not want quoted.

Step 2: Write the file

Follow the llms.txt format:

# Site Name

> One or two sentences saying what the site is and who it serves. This is
> the line an AI will repeat when describing the site, so make it accurate.

Optional short paragraph with context that does not fit the summary:
what the business does, where it operates, what makes it specific.

## Main sections

- [Page Title](https://example.com/page): one line on what this page contains
- [Another Page](https://example.com/other): same again

## Resources

- [Blog](https://example.com/blog): what the blog covers
- [Downloads](https://example.com/tools): what can be downloaded

## Optional

- [Secondary pages](https://example.com/archive): things an AI can skip unless asked

Writing rules for descriptions:

  • Describe what is ON the page, not what the page hopes to achieve. "Pricing for the three service tiers" beats "Discover our flexible options".
  • Absolute URLs throughout.
  • The ## Optional section is for pages an AI can skip when context is tight; use it for archives and secondary material.
  • The summary blockquote is the highest-value line in the file. Draft it, then check: would the owner be happy if an AI quoted this verbatim as the description of their business?

Step 3: Validate and place

  1. Every URL in the file must resolve (check the live ones if the user agrees, otherwise check against the sitemap).
  2. Place the file at the site root as llms.txt (same level as robots.txt).
  3. If the site is large, offer a second llms-full.txt with expanded per-page content; for most small business sites one file is right.
  4. Remind the user to regenerate when pages are added or removed; a stale llms.txt misdirects the AIs it was meant to help.

Rules

  • Never include pages blocked by robots.txt, behind logins, or that handle form data.
  • Never inflate: no keyword stuffing, no claims that are not on the site. The file's only job is accuracy.
  • Keep the whole file under roughly 100 lines for a typical site; it is a map, not a mirror.
  • If the site already has an llms.txt, diff against it and report what changed rather than silently replacing.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.