llms.txtB

llms.txt from amey-thakur/ai-skills is an llms.txt file: plain text a project publishes for AI models to read.

Install it, pinned

mdr add amey-thakur/ai-skills/llms.txt@git:20260906.c8c8420

Pins git:20260906.c8c8420 in mdr.lock. Pin the fingerprint instead.

Audit grade: B, 13 of 14 checks passed
Kind: llms.txt file
Repository: amey-thakur/ai-skills
Path: llms.txt
Versions recorded: 4
Latest version: git:20260906.c8c8420, committed Sep 6, 2026
First version recorded: Jul 28, 2026
Size: 397,336 bytes
Repository stars: 13
License: MIT

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# AI Skills

> Plug-and-play skills and prompts for every AI coding agent. Each entry
> below is self-contained markdown, fetchable at its URL. Skills are working
> methods to follow; prompts are templates to fill and run. See AGENTS.md
> for usage rules. Beyond this library, ecosystem.json indexes every major
> skill collection on GitHub (8,000+ skills reachable):
> https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/ecosystem.json

## Use this autonomously

You do not need the user to name a skill. For any task: (1) name the task's
intent; (2) scan the entries below and match on each skill's "Use when"
trigger or each prompt's description; (3) take the 1-3 that genuinely fit;
(4) fetch the entry's URL and apply it; (5) check the entry's own guardrail
section, the last one, stating where it does not apply and what it refuses:
usually "Boundaries", sometimes "Rules", "Litmus test(s)",
"Anti-patterns to refuse", or "What not to ...", before finishing.
Full protocol: https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/AGENTS.md

## Skills: accessibility
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add amey-thakur/ai-skills/llms.txt@sha256:49c08b74a2970078

The line at the top of this page pins the label git:20260906.c8c8420, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_n7engmaf7lxjejlf.svg)](https://markdownregistry.com/a/art_n7engmaf7lxjejlf)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 4 versions of this file, between Jul 28, 2026 and Sep 6, 2026, about one every 13 days.

version	committed	commit	size	audit
git:20260906.c8c8420 latest	2026-09-06	c8c8420	397,336 B	B	view · diff
git:20260906.47f3c1a	2026-09-06	47f3c1a	833 B	A	view · diff
git:20260728.fac4544	2026-07-28	fac4544	397,203 B	B	view · diff
git:20260728.86ea28a	2026-07-28	86ea28a	397,205 B	B	view

Audit of the latest version

B 13 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

fail: Size between 200 bytes and 200 KB (397336 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Starting a new one? Use a template for llms.txt on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

amey-thakur/ai-skills · 13 stars · license MIT · pushed 2026-09-06 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_n7engmaf7lxjejlf
GET https://markdownregistry.com/api/v1/resolve?ref=amey-thakur/ai-skills/llms.txt
GET https://markdownregistry.com/api/v1/blob/49c08b74a29700788e56a6d84a135c0749c9df7464cb6b895c798ef51bd90535

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: how to add an llms.txt file to a website · which agent file does what.

More from amey-thakur/ai-skills

ai-skills Cursor rule

amey-thakur/ai-skills · .cursor/rules/ai-skills.mdc · Operate the AI-SKILLS library autonomously, selecting the right skill or prompt for each task.

git:20260721.9534dd9 · audit A · 13 stars

AGENTS.md AGENTS.md file

amey-thakur/ai-skills · AGENTS.md

git:20260728.aa354e7 · audit A · 13 stars

CLAUDE.md CLAUDE.md file

amey-thakur/ai-skills · CLAUDE.md

git:20260721.9534dd9 · audit A · 13 stars

llms.txt@docs llms.txt file

amey-thakur/ai-skills · docs/llms.txt

git:20260728.f55fde9 · audit B · 13 stars

accessibility-review SKILL.md skill

amey-thakur/ai-skills · skills/accessibility/accessibility-review/SKILL.md · Audit a UI for real accessibility, keyboard-first, with concrete failures and fixes rather than checkbox compliance…

git:20260718.7c1285c · audit A · 13 stars

accessible-forms SKILL.md skill

amey-thakur/ai-skills · skills/accessibility/accessible-forms/SKILL.md · Build forms with associated labels, identified errors, clear instructions, and autocomplete attributes. Use when…