MaixPy Skill

MaixPy Development Skill

[](LICENSE) [](https://github.com/sipeed/MaixPy) [](https://claude.ai/code)

**[English](README.md)** | **[简体中文](README_CN.md)**

A comprehensive Claude Code skill for developing Python applications on Sipeed MaixCAM, MaixCAM-Pro, and MaixCAM2 edge AI devices using MaixPy v4.

Features

• AI Vision: YOLO detection, segmentation, pose estimation, classification, face recognition, OCR
• Image Processing: Blob detection, edge detection, QR/barcode scanning, line tracking
• Object Tracking: ByteTracker, counting, trajectory visualization
• Peripherals: Camera, display, UART, I2C, SPI, GPIO, PWM, ADC, USB HID
• Network: WiFi, HTTP streaming, MQTT, WebSocket, RTSP/RTMP
• Audio: Playback, recording, TTS, ASR
• LLM/VLM: Qwen, DeepSeek, InternVL (MaixCAM2 only)
• Advanced: OpenCV integration, video encoding/decoding, self-learning classifier

Installation

Method 1: Direct Download

Download `maixpy-dev.skill` and place it in your Claude Code skills directory:

~/.claude/skills/

Method 2: Clone Repository

git clone https://github.com/StanleyChanH/MaixPy-skill.git

Quick Start

from maix import camera, display, image, nn, app

detector = nn.YOLOv8(model="/root/models/yolov8n.mud", dual_buff=True)
cam = camera.Camera(detector.input_width(), detector.input_height(), detector.input_format())
disp = display.Display()

while not app.need_exit():
    img = cam.read()
    objs = detector.detect(img, conf_th=0.5, iou_th=0.45)
    for obj in objs:
        img.draw_rect(obj.x, obj.y, obj.w, obj.h, color=image.COLOR_RED)
    disp.show(img)

Documentation Structure

| File | Content | |-