handtracking
Real-time hand detection in egocentric videos using victordibia/handtracking. Outputs bounding boxes for hands, specifically trained on EgoHands dataset. Supports video input/output with labeled hand boxes. Lightweight and fast for egocentric view applications.
npx skills add BioTender-max/awesome-bio-agent-skills --skill handtracking --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# HandTracking - Real-time Hand Detection ## Overview Real-time hand detection system designed specifically for egocentric (first-person) video views. Trained on the EgoHands dataset, this lightweight model detects hand bounding boxes in video streams and can output labeled videos with hand annotations. Ideal for quick prototyping of hand-based interaction systems in AR/VR and wearable computing applications. **Companion JavaScript library**: Handtrack.js is available for browser-based applications (https://github.com/victordibia/handtrack.js). ## When to Use This Skill This skill should be used when: - Analyzing egocentric video footage from wearable cameras or smart glasses - Detecting hand presence and location in first-person perspective videos - Building hand gesture interfaces or interaction systems - Annotating training data for hand detection models - Processing egocentric videos for human-computer interaction research - Creating labeled video outputs with hand bounding box overlays - Implementing real-time hand detection in web applications (using Handtrack.js) - Quick prototyping of hand-based AR/VR interfaces **Choose this when**: You need fast, lightweight hand detectio
- Overview
- When to Use This Skill
- Core Capabilities
- 1. Hand Detection in Egocentric Views
- 2. Video Processing and Annotation
- 3. Real-time Webcam Detection
- 4. Browser-based Detection (Handtrack.js)
- Installation and Setup
- Option 1: Python Installation
- Option 2: JavaScript Installation (Handtrack.js)
- Usage Examples
- Example 1: Process Video with Output
- Example 2: Extract Hand Regions
- Example 3: Real-time Detection Statistics
Clone repository git clone https://github.com/victordibia/handtracking.git cd handtracking Install dependencies (TensorFlow 1.x compatible) pip install tensorflow==1.15.0 opencv-python numpy Run hand detection on video python run.py \ Create virtual environment python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate
What does the handtracking skill do?
Real-time hand detection in egocentric videos using victordibia/handtracking. Outputs bounding boxes for hands, specifically trained on EgoHands dataset. Supports video input/output with labeled hand boxes. Lightweight and fast for egocentric view applications.
How do I install it?
Run `npx skills add BioTender-max/awesome-bio-agent-skills --skill handtracking --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From BioTender-max/awesome-bio-agent-skills, a repository with 135 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.