AI coding agents are smart generalists but lack the deep procedural knowledge senior engineers carry. TechSkills bridges that gap — an open-source library of loadable SKILL.md files that give any AI agent structured workflows, design checklists, and production-ready patterns.
Skills use progressive loading — no context window waste. Agent-agnostic, framework-neutral, eval-driven.
Currently: frontend-engineer & backend-engineer skills. Early stage, community-driven. More skills coming.
Built a gesture-controlled calculator a while back using MediaPipe. Extracted the detection logic into a standalone library so anyone can add gesture recognition to their project without touching CV code.
from mp_gesture_lib import GestureDetector
detector = GestureDetector() # bundled model, zero config
result = detector.detect(frame) # pass any BGR webcam frame
print(result.gesture, result.confidence)
An open-source Python library that wraps MediaPipe gesture recognition into an ultra-simple API. Detect hand gestures from webcam frames in just 3 lines of code! Supports finger counting (1-10), arithmetic gestures (plus, minus, multiply, divide, equal, clear), and custom ML models. Comes with a bundled gesture model out of the box with zero external setup. Fully compatible with all MediaPipe versions, from legacy to the latest 0.10.35+ release.
