Nothing leaves the page until //
Patkan takes no action until you deliberately end a sentence with two slashes.
For Google Gemini
Gemini answers best when a prompt has clear, unmistakable boundaries — role, context, task, constraints, output format. Writing that by hand every time is tedious. Patkan does it for you: type your rough thought on gemini.google.com, end it with //, and it becomes a structured Gemini prompt in the blink of an eye.
Before → After
YOU TYPE
help me write a cold email to a founder about my analytics tool //
GEMINI 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 answer matches the requested format exactly.
Open gemini.google.com and describe your task in plain, messy words. No structure needed.
Two slashes at the end of your sentence trigger Patkan. Nothing happens until then.
Your thought is replaced in place by a structured Gemini prompt — role, context, task, output format and constraints, each under its own clear heading.
Patkan takes no action until you deliberately end a sentence with two slashes.
Gemini gets sections. Claude gets XML. ChatGPT gets markdown. Each model receives the structure it respects.
Patkan is open source under AGPL-3.0. Every line is on GitHub, there for anyone to read.
Questions
Gemini reads a prompt as one block of text. When the role, the task, the limits and the format are not separated, it fills the gaps itself — padding the answer with chatter, assuming details that were never given, or drifting away from what you asked. Plain uppercase section headings draw those lines for it. Patkan writes them for you.
No. Patkan is a browser extension that runs inside the Gemini tab. You type, you finish with //, and your text is rewritten right in the input box — no copying, no switching tabs.
Yes. Patkan runs on both gemini.google.com and aistudio.google.com, and applies the same sectioned structure in each.
It compiles your rough thought into a structured prompt: it picks an expert role, adds the context and limits Gemini needs, and states the format you want back. You can read and edit the result before you send it.
Yes. The same extension works inside ChatGPT, Claude, Microsoft Copilot, Perplexity and more, with the structure adapted to each one. This page is about the Gemini dialect.
10 transforms a day in ghost mode. No sign-up to start.