add-exercise
Add a new exercise to vibereps. Use when the user wants to create a new exercise type with pose detection. Handles creating the JSON config file and detection logic.
Best use case
add-exercise is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Add a new exercise to vibereps. Use when the user wants to create a new exercise type with pose detection. Handles creating the JSON config file and detection logic.
Teams using add-exercise should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/add-exercise/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How add-exercise Compares
| Feature / Agent | add-exercise | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Add a new exercise to vibereps. Use when the user wants to create a new exercise type with pose detection. Handles creating the JSON config file and detection logic.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Add New Exercise
## Instructions
When adding a new exercise to vibereps:
1. **Read the template** at `exercises/_template.json` for the JSON structure
2. **Choose a detection type** based on the exercise motion:
- `angle` - Joint angle changes (squats, pushups)
- `height_baseline` - Vertical movement from baseline (calf raises)
- `height_relative` - Position relative to reference point (jumping jacks)
- `tilt` - Torso lean (side stretches)
- `distance` - Body parts approaching each other (standing crunches)
- `width_ratio` - Shoulder/hip width ratio (torso twists)
- `quadrant_tracking` - Circular arm motion (arm circles)
3. **Create the JSON config** in `exercises/{exercise_name}.json`
4. **Test detection** by running the tracker
## MediaPipe Landmark IDs
Key landmarks for detection:
- Shoulders: 11 (left), 12 (right)
- Elbows: 13 (left), 14 (right)
- Wrists: 15 (left), 16 (right)
- Hips: 23 (left), 24 (right)
- Knees: 25 (left), 26 (right)
- Ankles: 27 (left), 28 (right)
## Example: Angle-based exercise
```json
{
"id": "squats",
"name": "Squats",
"description": "Strengthens legs",
"category": "strength",
"reps": { "normal": 10, "quick": 5 },
"detection": {
"type": "angle",
"landmarks": {
"joint": [23, 25, 27],
"joint_alt": [24, 26, 28]
},
"thresholds": { "down": 120, "up": 150 }
},
"instructions": {
"ready": "Squat down below {down}°",
"down": "Good! Now stand up"
}
}
```
## Testing
Run the tracker to test:
```bash
./exercise_tracker.py user_prompt_submit '{}'
```Related Skills
add-exercises
Add new exercises to the workout tracker database. Use when asked to add exercises, expand the exercise library, or check what exercises exist. Triggers include "add exercise", "new exercise", "exercise database", "what exercises", "missing exercises", "expand exercises".
ontopo
An AI agent skill to search for Israeli restaurants, check table availability, view menus, and retrieve booking links via the Ontopo platform, acting as an unofficial interface to its data.
grail-miner
This skill assists in setting up, managing, and optimizing Grail miners on Bittensor Subnet 81, handling tasks like environment configuration, R2 storage, model checkpoint management, and performance tuning.
ux
This AI agent skill provides comprehensive guidance for creating professional and insightful User Experience (UX) designs, covering user research, information architecture, interaction design, visual guidance, and usability evaluation. It aims to produce actionable, user-centered solutions that avoid generic AI aesthetics.
thor-skills
An entry point and router for AI agents to manage various THOR-related cybersecurity tasks, including running scans, analyzing logs, troubleshooting, and maintenance.
modal-deployment
Run Python code in the cloud with serverless containers, GPUs, and autoscaling using Modal. This skill enables agents to generate code for deploying ML models, running batch jobs, serving APIs, and scaling compute-intensive workloads.
lets-go-rss
A lightweight, full-platform RSS subscription manager that aggregates content from YouTube, Vimeo, Behance, Twitter/X, and Chinese platforms like Bilibili, Weibo, and Douyin, featuring deduplication and AI smart classification.
astro
This skill provides essential Astro framework patterns, focusing on server-side rendering (SSR), static site generation (SSG), middleware, and TypeScript best practices. It helps AI agents implement secure authentication, manage API routes, and debug rendering behaviors within Astro projects.
chrome-debug
This skill empowers AI agents to debug web applications and inspect browser behavior using the Chrome DevTools Protocol (CDP), offering both collaborative (headful) and automated (headless) modes.
vly-money
Generate crypto payment links for supported tokens and networks, manage access to X402 payment-protected content, and provide direct access to the vly.money wallet interface.
whisper-transcribe
Transcribes audio and video files to text using OpenAI's Whisper CLI, enhanced with contextual grounding from local markdown files for improved accuracy.
tech-blog
Generates comprehensive technical blog posts, offering detailed explanations of system internals, architecture, and implementation, either through source code analysis or document-driven research.