PatkanPatkan

For ChatGPT

A ChatGPT prompt generator that lives inside ChatGPT

ChatGPT answers best when a prompt is split into labeled markdown sections — role, context, task, constraints, output format. Writing that by hand every time is tedious. Patkan does it for you: type your rough thought on chatgpt.com, end it with //, and it becomes a structured ChatGPT prompt in the blink of an eye.

Try the playground

Before → After

Same thought. Surgically crafted for ChatGPT.

YOU TYPE

help me write a cold email to a founder about my analytics tool //

CHATGPT RECEIVES

## Role
Senior B2B copywriter who writes concise, founder-to-founder cold email.

## Context
The sender is reaching out about an analytics product. The recipient is a startup founder with limited time.

## Task
Write a cold outreach email introducing the analytics tool.

## Output format
Subject line, then body. No sign-off placeholders.

## Constraints
- Under 120 words
- No buzzwords or hype
- One clear call to action

## Before answering
Check that no fact, number or name has been invented, and that the output matches the requested format exactly.

How it works

  1. 01

    Type what you want

    Open chatgpt.com and describe your task in plain, messy words. No structure needed.

  2. 02

    End it with //

    Two slashes at the end of your sentence trigger Patkan. Nothing happens until then.

  3. 03

    Watch it become markdown

    Your thought is replaced in place by a structured ChatGPT prompt — role, context, task, constraints, and output format under clean markdown headings that ChatGPT follows best.

Nothing leaves the page until //

Patkan takes no action until you deliberately end a sentence with two slashes.

Markdown for ChatGPT, its native tongue

ChatGPT gets markdown headings. Claude gets XML. Each model receives the structure it respects.

Open and auditable

Installed unpacked as plain JavaScript — open the folder and inspect every line before you load it.

Questions

ChatGPT + Patkan, answered

Why does markdown work better for ChatGPT?+

ChatGPT parses markdown natively — its answers come back as headings, bullets, and bold text. When a prompt is split into clearly labeled markdown sections (Role, Context, Task, Constraints, Output format), ChatGPT treats each block as an instruction with a boundary, which means fewer misunderstandings and better first answers. Patkan applies that structure for you automatically.

Do I have to leave chatgpt.com to use it?+

No. Patkan is a browser extension that runs inside the ChatGPT tab. You type, you finish with //, and your text is transformed right in the input box — no copy-pasting, no switching tabs.

What does Patkan actually do to my text?+

It compiles your rough thought into a structured prompt: it picks an expert persona, adds the context and constraints ChatGPT needs, and puts each section under a markdown heading. You can review and edit the result before sending it.

Does it work with other AI tools too?+

Yes. The same extension works inside Claude, Gemini, Microsoft Copilot, Perplexity, and more — with the output format adapted to each model. Claude gets XML tags; ChatGPT gets markdown headings. There's a separate page for the Claude dialect.

Start prompting ChatGPT patkan.

10 transforms a day in ghost mode. No sign-up to start.