Fake data finder
Give it a live page. Get a report of which numbers are real, mocked, hardcoded or broken.
Fake data finder is a free AI skill for the job "Test and fix code". Give the instructions to an AI assistant that supports the required files and tools, then review its output.
Free · No account · CC BY 4.0 licence · Made by sickn33
Made by sickn33. See the original on GitHub; we copied it as it is, with its licence.
What it does
A page audit that tells you which numbers on screen come from a real source and which are made up. It matters before you show an app built with AI to a customer or investor. You give a live URL. A browser walks the page, takes a full screenshot, and lists every heading, button, card, stat and table cell. With your approval it clicks tabs and safe buttons, and watches network calls and console errors. Each value is labelled real, mocked, hardcoded, generated or broken. Warning signs include round numbers, clustered timestamps and values that never change. You confirm ownership and which actions are allowed before it starts.
You give it
- The live page URL
- Login details for a test account, if needed
- Which actions are safe to click
- Your suspicions about the page (optional)
You get
- A value-by-value report: real, mocked, hardcoded or broken
- Screenshots of the page
- Notes on network and console problems
- A short fix list
Use it when
- You built a dashboard with an AI tool and are unsure what is connected.
- A contractor delivered an app and you need a check before you pay.
- A page looks too tidy, with every metric a round number.
- You are about to demo an early product and want no surprises.
How to use it
- Add it to your AI once: download it and add the folder to Claude, ChatGPT or Codex as a skill.
- Ask for the job in your own words. Your AI opens the skill when it fits.
- It works best when your AI can run code and open a browser.