Vibe coding with PoseTracker

Build faster with AI coding assistants using ready-to-use prompts and templates.

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:

GitHub - Movelytics/posetracker-llm-prompts: Ready-to-use prompts, examples, and schemas to help AI coding agents integrate PoseTracker API for real-time motion tracking, pose estimation, and reference movement comparison in web and mobile apps.GitHub

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.

---

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