markdown-twin
Skill8 starsChanged 2 days agoMITView on GitHub
Use this when adding a clean markdown twin for one HTML page: a .md copy at the same path, a rel=alternate type=text/markdown link, and one line for it in /llms.txt.
- Installs packages
In this repository28 other files it gives its agents.
- whetstone-signalSkill
- design-a-grok-botSkill
- make-bot-uiSkill
- overheard-setupSkill
- overheardSkill
- routine-healthcheckSkill
- transcript-healthcheckSkill
- design-taste-frontendSkill
- diagram-designSkill
- motion-pickerSkill
- redesign-existing-projectsSkill
- engineering-playbookSkill
- show-meSkill
- chatgpt-images-browser-playbookSkill
- aeo-geo-siteSkill
- ai-citation-sourcesSkill
- ai-search-gap-loopSkill
- exact-match-intent-seoSkill
- shorts-reframeSkill
- coachSkill
- draftSkill
- no-ai-slopSkill
- outlineSkill
- social-copywritingSkill
- source-checkSkill
- top-editSkill
- x-articleSkill
- youtube-niche-reportSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Write a clean .md copy at the same path as the page, using one of the forms from the llms.txt v2 spec: append .md (page.html.md) or replace …
- Very specific: line 21
Add one line for that twin in /llms.txt (create the file if the site does not have one yet), in the spec's file-list form: a markdown link, …
- Distinctive: line 23
Do this for the one page you were asked to cover.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Markdown twin
For one HTML page, publish a clean markdown copy that an agent can read instead of scraping the rendered page. The twin must carry the same facts as the HTML. Do not cloak.
Three steps
- Write a clean
.mdcopy at the same path as the page, using one of the forms from the llms.txt v2 spec: append.md(page.html.md) or replace the extension (page.md). For a URL with no filename, useindex.html.mdorindex.md. Advertise the twin from the HTML page:
<link rel="alternate" type="text/markdown" href="/docs/install.md">- Add one line for that twin in
/llms.txt(create the file if the site does not have one yet), in the spec's file-list form: a markdown link, optionally a colon, and a short note.
Do this for the one page you were asked to cover. Do not invent a site-wide crawl, a Worker router, or content negotiation unless that work is already in scope.
Example
HTML page at /docs/install/ (or /docs/install.html). Twin at /docs/install.md (or /docs/install/index.md).
<!doctype html>
<html lang="en">
<head>
<link rel="alternate" type="text/markdown" href="/docs/install.md">
<title>Install</title>
</head>
<body>
<h1>Install</h1>
<p>Run <code>npm install example</code>, then start the app with <code>npm start</code>.</p>
</body>
</html>/docs/install.md:
# Install
Run `npm install example`, then start the app with `npm start`.One new line in /llms.txt:
# Example
> Product docs for agents.
## Docs
- [Install](/docs/install.md): How to install the productThe markdown has the same facts as the HTML, without navigation or other chrome. Point the llms.txt link at the twin, not the HTML page.
Inspired by
Inspired by Jeremy Howard's /llms.txt v2 proposal (clean markdown at the same URL with .md or index.md, and rel="alternate" type="text/markdown"). The spec defines the file forms, the link relation, and the /llms.txt format, but it is not a one-page recipe that does all three together. This skill adds that per-page sequence and a tiny worked example.
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
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.

