How-to
Recreate a website animation with Claude or ChatGPT
Give Claude or ChatGPT the real timings instead of a vague description. What is in the Capture Motion LLM prompt, how to use it, and how to check the result.
Ask a model to "make a card that slides in smoothly, like the one on that site I saw" and you will get a card that slides in. It will use ease-in-out, a round 300 ms, and nothing else. The result is fine and forgettable, because the model is guessing at exactly the parts that made the original feel good: the duration, the delays between parts, and the easing curve.
The fix is to stop describing the animation and give the model the data. This guide shows how to use the Capture Motion LLM prompt with Claude or ChatGPT, what goes into it, how to steer the result, and how to check that the timings survived.
Where the prompt comes from
There are two places to get it, depending on your source.
- From the gallery. On the home page gallery, open a card with View, then choose Copy > LLM prompt (for ChatGPT or Claude). You can copy it or download it.
- From any website. Capture the animation with the Chrome extension, then click Copy for LLM in the popup. If you have not captured before, start with how to copy an animation from any website.
Copying needs a free account. Capturing and previewing in the extension do not.
What is in the prompt
It helps to know what the model is reading, because that tells you what it can and cannot get right.
| Part | What it gives the model |
|---|---|
| A ready-made instruction | Tells the model what to build and to use the captured values |
| The capture JSON | Each animated property, with its keyframes, durations, delays and easing |
| Reference markup (gallery cards) | The card's own markup, as a visual reference for structure and look |
The JSON is the motion. The reference markup is the look. A capture from the extension carries the motion data, so the model rebuilds the movement faithfully but has to invent the visual design around it. A gallery card prompt carries both, so the model can rebuild it closely.
If you customized a gallery card first, your choices carry into the prompt: colour re-tints, text swaps, speed and background. Set those before you copy and you skip a round of follow-ups.
Step by step
- Get the cleanest source you can. For a capture, pick the smallest container that holds the whole motion and close any banners first. Stray tracks in the JSON become stray animations in the code.
- Copy the prompt. Use Copy > LLM prompt on a gallery card, or Copy for LLM in the extension.
- Paste it into Claude or ChatGPT as the first message of a new chat. Do not trim it; the instruction and the data belong together.
- Add one line about your stack before you send, if it matters. For example: "Build this as a React component with Tailwind."
- Run what comes back. The model returns a self-contained HTML file, or a component if you asked for one. Save the HTML and open it in a browser, or drop the component into your project.
- Check the timings against the JSON (see below) before you start changing anything.
- Then make it yours. Ask for your own content and colours in a follow-up.
Good follow-up prompts
The first answer is a starting point. These follow-ups tend to work well, and each one keeps the motion intact while changing something else.
- Change the stack: "Convert this to a React component using Tailwind. Keep every duration, delay and easing value exactly as in the JSON."
- Swap the content: "Replace the text with my own: [your copy]. Do not change the animation."
- Swap the colours: "Use my brand colours: primary #…, background #…. Keep the timings as given."
- Pull the values out: "Move the durations, delays and easing curves into CSS custom properties at the top so I can tune them."
- Add reduced motion: "Add a prefers-reduced-motion version that fades in without movement."
- Explain it: "List each animated element with its property, duration, delay and easing as a table." This doubles as a timing check.
Notice the repeated phrase "keep the timings as given". Models like to tidy numbers. A 520 ms duration becomes 500 ms, and a precise cubic-bezier() becomes ease-out. Saying it every time costs nothing.
Check the timings
This is the step most people skip, and it is the one that decides whether the result feels like the original. It takes two minutes.
- Open the JSON you pasted next to the model's code.
- Match each track. For every animated element, find its duration, delay and easing in the code and compare.
- Look hardest at the easing. A
cubic-bezier()orlinear()value should come through unchanged. If the model swapped it for a keyword, the motion will feel flatter. Our guide on finding the easing curve of an animation explains why the curve matters so much. - Check the delays. Staggers are easy to break. If ten items should start 40 ms apart, count them.
- Watch it side by side. Play the original (the gallery card, or the extension preview) next to the new file. Differences in feel usually point straight to a changed number.
- Correct in one message. List what differs and ask the model to use the given values exactly.
A small table makes the check quick:
| Track | In the JSON | In the code | OK? |
|---|---|---|---|
| Card opacity | 400 ms, 0 ms delay | 400 ms, 0 ms delay | Yes |
| Card translateY | 520 ms, cubic-bezier(.22, 1, .36, 1) | 500 ms, ease-out | No |
The values above are an example of the format, not taken from a real capture.
Common problems
- It looks right but feels wrong. Almost always the easing or a rounded duration. Run the check above.
- It does not look like the original. If you started from a site capture, the model only had the motion data and invented the visuals. Describe the look in a follow-up, or start from a gallery card, which includes reference markup.
- Extra things are moving. The capture probably picked up a banner or a neighbour. Capture a smaller container and start again.
- The model added a library. If you want plain CSS, say so: "No libraries, CSS only."
Where to go next
If React is your target, gallery animation to React component goes further. If a designer also needs the motion, the Figma plugin guide uses the same capture. And to keep prompts you want to reuse, save the capture in My Gallery.
Questions
What does the LLM prompt contain?
The capture JSON, with each animated property, its keyframes, durations, delays and easing. From a gallery card it also includes the card's own markup as a visual reference, so the model can rebuild it closely.
Where do I get the prompt?
From a gallery card, open View and use Copy > LLM prompt. From the Chrome extension, use Copy for LLM after a capture. Copying needs a free account.
Does it work with ChatGPT as well as Claude?
Yes. The prompt is plain text with a ready-made instruction, so you can paste it into either. The model returns a self-contained HTML file, or a component if you ask for one.
How do I know the model kept the timings?
Compare the durations, delays and easing in its code with the values in the JSON you pasted. If anything differs, ask it to use the given values exactly.
