# Vibe coding with PoseTracker

## Build faster with AI coding assistants

If you use **Cursor**, **Claude**, **Copilot**, **ChatGPT**, or similar tools, use this repo to integrate PoseTracker faster.

It provides **ready-to-use prompts, examples, and quick fixes** for Cursor / Claude / Copilot / ChatGPT.

Repo:

{% embed url="<https://github.com/Movelytics/posetracker-llm-prompts>" %}

{% hint style="info" %}
This repo is **not** a replacement for the official PoseTracker docs.

Use the docs as the source of truth for endpoints, parameters, and message payloads. Use the repo as a developer acceleration layer on top.
{% endhint %}

***

### What the repo contains

* Prompts for **real-time tracking** (camera / webcam)
* Prompts for **upload tracking** (video / image)
* Prompts for **reference movement comparison**
* Use-case-driven prompt templates (goal-oriented)
* Quick fixes for **React Native**, **WebView**, and mobile integration issues
* LLM query files and capability summaries

***

### Recommended use cases

* Count squat reps in **React Native**
* Build an AI workout coach (real-time feedback + summaries)
* Retrieve real-time pose keypoints in a mobile app
* Compare a user movement to a reference movement
* Analyze an uploaded workout video in **Flutter**

***

### How to use it (simple workflow)

1. Pick the closest prompt to your target stack and use case.
2. Paste it into your AI coding tool.
3. Replace placeholders (token, reference UUID, exercise key, etc.).
4. Validate against the official docs before shipping.

Keep your final integration aligned with:

* the Tracking endpoint URL format
* the Upload Tracking endpoint URL format
* the emitted WebView / postMessage events


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://posetracker.gitbook.io/posetracker-api/use-posetracker-on-real-time-camera-webcam/integration-tutorials/vibe-coding-with-posetracker.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.