agentleFS
wedsamuel1230wedsamuel1230/embedded-engineering-skills/skills/arduino-project-builder/SKILL.md

arduino-project-builder

Skill28 starsChanged 30 days agoMITView on GitHub

Build complete Arduino and embedded projects across Arduino IDE, Arduino CLI, PlatformIO, and vendor-specific toolchains. Use when users request an application combining firmware, sensors, actuators, networking, power, or deployment rather than a code snippet. The bundled scaffold targets UNO, ESP32, and Raspberry Pi Pico; use the board profile and document limitations for other targets.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before assembling a project, read the shared contract and fill the board profile.

    line 31
  2. Distinctive:

    Use the shared Arduino skill contract: state assumptions, required tools and versions, implementation steps, tests/evidence by proof stage, …

    line 100

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Arduino Project Builder

Assemble complete, working Arduino projects from requirements. This skill combines multiple patterns (sensors, actuators, state machines, logging, communication) into cohesive systems.

Quick Start

List available project types:

uv run --no-project scripts/scaffold_project.py --list

Create a complete project:

uv run --no-project scripts/scaffold_project.py --type environmental --board esp32 --name "WeatherStation"
uv run --no-project scripts/scaffold_project.py --type robot --board uno --output ./my-robot

Interactive mode:

uv run --no-project scripts/scaffold_project.py --interactive

Intake And Evidence Boundary

Before assembling a project, read the shared contract and fill the board profile. Record the exact board, framework, toolchain, versions, pins, memory, power, protocols, and recovery path. Keep build, upload, hardware, system, and deployment proof separate; a generated scaffold is not hardware validation.

The scaffold script emits its supported board targets and PlatformIO structure. For another board or vendor framework, reuse the requirements and architecture workflow, then provide a toolchain-specific implementation rather than changing the script's claimed support.

Resources

  • examples/ - Complete project examples (environmental monitor, robot controller, IoT device)
  • scripts/scaffold_project.py - CLI tool for project scaffolding (config.h, main.ino, platformio.ini, README)
  • assets/workflow.mmd - Mermaid diagram of project assembly workflow

Supported Project Types

Environmental Monitors

Multi-sensor data loggers (temperature, humidity, light, air quality)

See Environmental Monitor Example

Robot Controllers

Motor control, sensor fusion, obstacle avoidance, state machines

See Robot Controller Example

IoT Devices

WiFi/MQTT data transmission, cloud integration, remote monitoring

See IoT Device Example

Home Automation

Relay control, scheduled tasks, sensor-triggered actions

Data Acquisition Systems

High-frequency sampling, SD card logging, real-time visualization

Project Assembly Workflow

  • Requirements Gathering - Analyze user request and gather project specifications
  • Architecture Design - Design component connections, data flow, and state machines
  • Code Assembly - Combine patterns and customize for user hardware
  • Testing & Validation - Verify compilation, memory usage, and functionality
  • Documentation - Create wiring diagrams, usage instructions, and troubleshooting guides

Quality Standards & Rules

  • Quality Standards - Hardware abstraction, non-blocking code, error handling, and memory safety requirements
  • Integration Checklist - Pre-delivery verification for sensor validation, timing, and reliability
  • Board Considerations - UNO, ESP32, and RP2040 specific optimizations and constraints

Project Output Template

  • Output Template - Standardized format for delivering complete Arduino projects

Resources

  • examples/ - Complete project examples with full implementations
  • scripts/scaffold_project.py - CLI tool for project scaffolding with config.h, main.ino, platformio.ini, README
  • assets/workflow.mmd - Mermaid diagram of project assembly workflow
  • workflow/ - Step-by-step project assembly process
  • rules/ - Quality standards and board-specific optimizations
  • templates/ - Project output templates and documentation standards

Shared Output Contract

Use the shared Arduino skill contract: state assumptions, required tools and versions, implementation steps, tests/evidence by proof stage, known limitations, and recovery/security notes.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.