Loading...
Loading...
Found 8 Skills
Build a multi-board dashboard for XIAO ESP32S3: each board joins WiFi (STA mode), publishes its touch sensor value over MQTT, and accepts LED on/off commands, while a browser dashboard shows every board live and lets you toggle each LED. Use this skill whenever the user wants several ESP32S3 boards reporting to one web page, an MQTT-based sensor dashboard, "여러 esp32s3 대시보드", "MQTT로 여러 보드 연결", or mentions Mosquitto/Eclipse MQTT with an ESP32S3. For a single board with no broker, use the `xiao-esp32s3` skill's own SoftAP + web server example instead.
Operate a Seeed XIAO ESP32S3 board with arduino-cli on Windows: install the core, compile, upload, read serial output, and run verified examples (blink, serial, touch, ADC, PWM, WiFi scan/AP, BLE, deep sleep). Use this skill WHENEVER the task involves an ESP32S3 / XIAO board, arduino-cli, flashing a sketch, reading the serial monitor, COM ports, or any embedded/Arduino work — even for a "simple" LED change. It contains verified commands and known pitfalls (DTR reset, deep-sleep USB drop, PSRAM flag) that prevent wasted debugging time.
Bring up I2C sensors on a XIAO ESP32S3 and stream their values to serial: BH1750 ambient light, BME280 temperature/pressure/humidity, and BNO055 9-DOF fused orientation, individually as unit tests or all three together on one bus. Use this skill WHENEVER the task involves I2C sensors on an ESP32S3 — wiring one up, "센서 값 읽어줘", a sensor that answers the scan but reads zeros, unit-testing a module before trusting it, deciding whether a 0x76 part is a BME280 or a BMP280, or a BNO055 whose orientation stays at 0. It carries hardware-verified sketches and the address/clock traps that make a healthy-looking sensor return nothing.
Build and flash the XIAO ESP32S3 Sense camera web apps in STA (router) mode: a Teachable-Machine-style dataset collector page and a live inference viewer page, reachable at http://<name>.local while every device KEEPS its internet connection. Use this skill whenever the user wants the camera web app on their normal WiFi network — home/office development, "인터넷 안 끊기게", "공유기로", "mDNS", or says "STA 모드". For router-less classroom hotspot deployments use the xiao-webcam-ap skill instead.
Serial monitoring for a XIAO ESP32S3 (or any Arduino board) on Windows, in both modes that matter: a bounded read the agent can run to debug its own changes, and a persistent terminal monitor handed to the user with clear instructions for checking output later. Auto-detects the COM port by USB vendor ID, survives the port dropping on every reset and re-upload, and adds one-word `mon` / `flash` shortcuts to the PowerShell profile. Use this skill WHENEVER serial output is involved: reading what a board is printing, asking to "open the serial monitor", wanting it available "every time" or as a shortcut, a monitor that keeps disconnecting, needing Ctrl+C before every upload, the wrong COM port being picked, or whenever you are about to tell the user how to watch the board themselves.
Build and flash the XIAO ESP32S3 Sense camera web apps in STANDALONE AP (hotspot) mode: a Teachable-Machine-style dataset collector page and a live inference viewer page served by the board itself at http://192.168.4.1. Use this skill whenever the user wants the camera web app WITHOUT a router — classroom/education deployments, demos with no WiFi, per-student boards, or says "AP 모드", "핫스팟", "공유기 없이". For router (STA) mode use the xiao-webcam-sta skill instead.
Train and deploy a TinyML model for the XIAO ESP32S3 (Sense) using the Edge Impulse REST API only — no edge-impulse-cli needed (its serialport dep fails to build on modern Node/Windows). Covers: dataset upload, impulse creation (audio MFCC / vision transfer-learning), training jobs, downloading the Arduino library, and the on-device fixes required to actually run it on the ESP32-S3. Use this skill whenever the user wants to train/retrain a model ("재훈련", "edge impulse", "TinyML 훈련", "모델 배포"), upload a dataset to Edge Impulse, or gets EI Arduino-library build/runtime errors (mel filterbank, objs.a, tensor arena, EI_MAX_OVERFLOW_BUFFER_COUNT).
Motion sensing on a XIAO ESP32S3 with an MPU-6050 / MPU-6500 6-axis IMU: accelerometer and gyroscope over I2C, startup calibration, and a moving/still decision driven to the onboard LED. Use this skill WHENEVER the task involves an MPU-60x0 module on an ESP32S3 — "움직임 감지해줘", wiring one up, an Adafruit_MPU6050 sketch whose begin() returns "MPU6050 not found" even though the scan shows 0x68, a gyro that drifts hundreds of degrees per minute, an accelerometer whose magnitude sits well off 9.8 m/s² at rest, or deciding whether a module labelled MPU-6050 is actually an MPU-6500. Carries a hardware-verified library-free driver and the identity trap that makes a perfectly healthy module look broken.