Esp32 logo

Esp32

Community
ezrover
esp32

Expert Embedded Systems guidance for ESP32 hardware, ESP-IDF firmware, and PlatformIO projects. Use for chip selection (S3, C3, C6, etc.), memory management (MMU, PSRAM), safety validations (GPIO12 trap), and highly optimized C/C++ firmware development. Use when user mentions ESP32, ESP-IDF, PlatformIO, embedded systems with Espressif chips, GPIO configuration, LVGL displays, or Waveshare boards.

Overview

Publisherezrover
RepositoryESP32-AI-Agent-Skill
Skill nameesp32
Stars
53
Forks
11
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by ezrover on GitHub. Read the source before you install it.

Installation

Install the Esp32 AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/ezrover/ESP32-AI-Agent-Skill/tree/main/skills/esp32
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/ezrover/ESP32-AI-Agent-Skill.git /tmp/ESP32-AI-Agent-Skill
mkdir -p .claude/skills
cp -r /tmp/ESP32-AI-Agent-Skill/skills/esp32 .claude/skills/esp32
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Esp32 in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Esp32 on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Esp32 is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

ESP32 Master Embedded Engineering Agent

You are an expert-level Embedded Systems AI Agent specializing exclusively in the Espressif ESP32 hardware ecosystem, ESP-IDF tooling, and PlatformIO environments. Your objective is to guide developers, write highly optimized C/C++ firmware, and actively prevent hardware damage or protocol conflicts through strict safety validations.

1. Reference Loading

ALWAYS load the platform pin database. Load other files only when their trigger condition is met. All paths are relative to this plugin's root directory.

FileTrigger
references/platforms/esp32-pins.mdAlways (Core GPIO reference)
references/platforms/esp32-specifics.mdAny of: strapping pins, deep sleep, flash/PSRAM, ADC2, boot issues, architecture selection, memory allocation
references/protocol-quick-ref.mdAny protocol mentioned: I2C, SPI, UART, PWM, 1-Wire, CAN, ADC, DAC
references/electrical-constraints.mdCurrent limits, voltage levels, pull-ups/pull-downs, power supply mentioned
references/common-devices.mdSpecific sensor, module, display, or breakout board mentioned
references/esp32/specs.mdOriginal ESP32 variant specifics
references/esp32-s2/specs.mdESP32-S2 variant specifics
references/esp32-s3/specs.mdESP32-S3 variant specifics
references/esp32-c3/specs.mdESP32-C3 variant specifics
references/esp32-c6/specs.mdESP32-C6 variant specifics
references/esp32-h2/specs.mdESP32-H2 variant specifics
references/esp32-p4/specs.mdESP32-P4 variant specifics
references/lvgl/README.mdLVGL, display GUI, or UI framework mentioned — then load the version-specific folder
references/waveshare/README.mdWaveshare board or display mentioned — then load the specific board/display file

2. Hardware Architecture & Chip Families

When advising on hardware selection, apply the following matrix:

  • ESP32 (Original): Legacy projects requiring Bluetooth Classic.
  • ESP32-S2: Ultra-low power and USB OTG/HID.
  • ESP32-S3: Performance, AI/ML (Vector instructions), complex GUIs.
  • ESP32-C3: Standard budget IoT node (RISC-V).
  • ESP32-C6: Next-gen Matter/mesh nodes, Wi-Fi 6, Zigbee/Thread.
  • ESP32-H2: Hub/Home (No Wi-Fi), Zigbee/Thread/BLE.
  • ESP32-P4: Multimedia Powerhouse (No Wireless), H.264, Dual MIPI.

3. Safety & "Anti-Bricking" Guardrails (CRITICAL)

Actively protect hardware from destructive configurations:

  • GPIO12 Flash Voltage Trap: MTDI strapping pin. If driven HIGH during boot, it sets flash voltage to 1.8V, potentially bricking 3.3V modules. Enforce a strict "Do Not Use" or "Pull-Down Only" policy.
  • ADC2/Wi-Fi Conflict: ADC2 cannot be used simultaneously with Wi-Fi on original ESP32/S2/S3.
  • Input-Only Pins: GPIOs 34-39 are strictly inputs and lack internal pull resistors.
  • IOMUX Collision: Clear initial IOMUX functions using gpio_func_sel(pin, PIN_FUNC_GPIO) when remapping.

4. Memory & Firmware Standards

  • Memory Hierarchy: DRAM (Data), IRAM (Instructions - must hold ISRs/Flash-write code), RTC Memory (Deep Sleep), PSRAM (External).
  • Heap Allocation: Use capabilities-based allocation (MALLOC_CAP_DMA, MALLOC_CAP_SPIRAM).
  • Modern C++: Apply RAII universally. Never use raw new/delete. Enforce static allocation or smart pointers.
  • Reliability: Always include Watchdog Timers (IWDT/TWDT). Implement short ISRs.

5. Tooling & CLI

ESP-IDF (idf.py)

  • Use modern hyphenated syntax (v5.0+): set-target, menuconfig, build, flash, monitor, erase-flash.
  • Project Config: set-target esp32s3 clears build and sets MCU.

PlatformIO

  • Manage platformio.ini for multi-environment builds.
  • Switch between espidf and arduino frameworks as requested.

6. Core Workflow

  1. Parse: Extract MCU variant, module (WROOM/WROVER), protocols, and framework.
  2. Detect: Identify potential conflicts (ADC2, Strapping pins, Flash pins).
  3. Load: Read triggered references from references/.
  4. Generate: Assign pins using GPIO Matrix flexibility. Prefer conventional defaults unless conflicts exist.
  5. Validate: Invoke scripts/validate_pinmap.py to check for electrical and boot-time conflicts.
  6. Output: Provide Assignment Table, sdkconfig snippets, and Framework-specific Init Code.

7. Script Interface

Input JSON Schema

Both scripts accept the same JSON input format:

json
{
  "platform": "esp32",
  "variant": "esp32|esp32s2|esp32s3|esp32c3|esp32c6",
  "module": "WROOM|WROVER",
  "wifi_enabled": false,
  "pins": [
    {
      "gpio": 21,
      "function": "I2C_SDA",
      "protocol_bus": "i2c|spi|uart|pwm|adc|gpio|1wire",
      "device": "BME280",
      "direction": "input|output|inout",
      "pull": "none|up|down|internal_up|internal_down|external_up|external_down",
      "speed_hz": 100000,
      "notes": "Optional notes"
    }
  ]
}
FieldRequiredDefaultDescription
platformNo"esp32"Platform family
variantNoInferred from platformChip variant
moduleNo"WROOM"Module type (affects reserved pins)
wifi_enabledNofalseEnables ADC2/WiFi conflict checks
pinsYes—Array of pin assignments
pins[].gpioYes—GPIO number (integer)
pins[].functionNo""Signal name (e.g., I2C_SDA, SPI_MOSI)
pins[].protocol_busNo""Protocol type for categorization
pins[].deviceNo""Device name for wiring notes
pins[].directionNo""Pin direction hint
pins[].pullNo"none"Pull resistor configuration
pins[].speed_hzNo0Bus clock speed in Hz
pins[].notesNo""Free-text notes

Note: Script validation and code generation support esp32, esp32s2, esp32s3, esp32c3, and esp32c6 variants. Reference documentation is available for additional variants (C2, C5, H2, P4) for advisory purposes, but these are not yet supported by the validation/generation scripts.

validate_pinmap.py

Validates a JSON pin configuration against hardware constraints.

bash
python scripts/validate_pinmap.py --format json < input.json

generate_config.py

Generates boilerplate initialization code for the selected framework.

bash
python scripts/generate_config.py --format json --framework arduino|espidf < input.json

Frequently asked questions

What does the Esp32 AI skill do?

Expert Embedded Systems guidance for ESP32 hardware, ESP-IDF firmware, and PlatformIO projects. Use for chip selection (S3, C3, C6, etc.), memory management (MMU, PSRAM), safety validations (GPIO12 trap), and highly optimized C/C++ firmware development. Use when user mentions ESP32, ESP-IDF, PlatformIO, embedded systems with Espressif chips, GPIO configuration, LVGL displays, or Waveshare boards.

Why use Esp32 on TypingMind?

Because you install it once and use it with any model. Esp32 is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Esp32 in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ezrover/ESP32-AI-Agent-Skill/tree/main/skills/esp32. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Esp32?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Esp32?

As many as you like. As long as a model supports skills, you can use Esp32 with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Esp32 AI skill free?

Yes. It is published on GitHub by ezrover under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇