Esp32 Peripheral Bringup logo

Esp32 Peripheral Bringup

Community
agodianel
esp32-peripheral-bringup

Guides bring-up and debugging of ESP32 peripherals — I2C, SPI, UART, ADC and LEDC/PWM — using the ESP-IDF v5 driver APIs, chip-correct pin choices, and a step-by-step wiring → config → probe → speed-up procedure. Use when the user says "I2C sensor not responding", "i2c ESP_ERR_TIMEOUT", "no ACK", "I2C scan finds nothing", "SPI returns 0xFF", "SPI display blank", "UART garbage characters", "uart_read_bytes returns nothing", "ADC reads wrong value", "adc_oneshot", "analogRead with Wi-Fi", "PWM / LEDC not working", "set duty", "bring up a new sensor", or "connect a peripheral" on ESP32, ESP32-S3, ESP32-C3, ESP32-C6 or other Espressif chips.

Overview

Publisheragodianel
Repositoryesp32-claude-workbench
Skill nameesp32-peripheral-bringup
Stars
81
Forks
7
Bundled files
6
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.

  • 6 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Esp32 Peripheral Bringup 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/agodianel/esp32-claude-workbench/tree/main/skills/esp32-peripheral-bringup
  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/agodianel/esp32-claude-workbench.git /tmp/esp32-claude-workbench
mkdir -p .claude/skills
cp -r /tmp/esp32-claude-workbench/skills/esp32-peripheral-bringup .claude/skills/esp32-peripheral-bringup
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Esp32 Peripheral Bringup 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 Peripheral Bringup 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 Peripheral Bringup 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 Peripheral Bring-up

Bring a bus up in small, verifiable steps: pins → electrical → minimal config → probe → read known register → full speed → error handling.

Tools

If the esp32-workbench MCP server is connected, call its tools; otherwise run the CLI. If esp32wb is not on PATH, use uvx --from git+https://github.com/agodianel/esp32-claude-workbench esp32wb <args>. Add --json for machine-readable output.

NeedMCP toolCLI
Is this pin usable on this chip?chip_info, pin_auditesp32wb chip <target>, esp32wb pins .
Driver API / limits for the target (always before writing driver code)search_esp_docsesp32wb docs search "i2c master probe" --target T (index once: esp32wb docs index, needs pip install 'esp32-workbench[docs]')
Summarise error outputlog_summaryesp32wb logs monitor.log

Before writing driver code

  1. Target chip + ESP-IDF version (API generation differs: v5.x has new I2C master, esp_adc oneshot, etc.).
  2. Pin plan checked with esp32wb pins . — no flash/PSRAM/USB/console pins, strapping pins only with a reason, input-only pins only as inputs.
  3. Peripheral instance count for the chip (number of I2C/SPI/UART ports, LEDC channels, ADC units differs per target) — check docs, do not assume classic ESP32.
  4. Device datasheet: voltage levels (3.3 V I/O — never 5 V into a GPIO), address/mode, timing, power-up delay.
  5. An implementation contract exists for the change.

Per-peripheral quick guide

I2C

  • External pull-ups on SDA/SCL (typ. 2.2–4.7 kΩ to 3.3 V); internal pulls are too weak.
  • Start at 100 kHz; use i2c_master_probe() (new driver) to scan.
  • 7-bit addresses (datasheet 0xD0 8-bit write address = 0x68).
  • Don't mix the legacy driver/i2c.h and new driver/i2c_master.h APIs in one build unless the IDF version explicitly allows it.
  • Full procedure: I2C bring-up.

SPI

  • Mode (CPOL/CPHA) from the device datasheet — the #1 failure cause.
  • Start at 1 MHz; .length is in bits.
  • IOMUX pins allow the highest clock; GPIO-matrix routing lowers the max — check the SPI master timing section for your chip.
  • DMA buffers from MALLOC_CAP_DMA memory.
  • Full procedure: SPI bring-up.

UART

  • Match baud, data bits, parity, stop bits, and flow control on both ends; cross TX→RX.
  • Do not take UART0 console pins unless the console is moved.
  • RX buffer passed to uart_driver_install() must exceed the hardware FIFO.
  • Full procedure: UART bring-up.

ADC

  • Use esp_adc (adc_oneshot_* + adc_cali_*) on IDF v5; legacy driver/adc.h is deprecated.
  • ADC2 + Wi-Fi is chip-specific (classic ESP32: unusable with Wi-Fi; S2/S3: arbitrated, reads can fail; C3: ADC2 oneshot unsupported) → prefer ADC1.
  • Calibrate and report millivolts, not raw counts; attenuation sets the input range.
  • Full procedure: ADC bring-up.

LEDC (PWM)

  • LEDC_HIGH_SPEED_MODE exists only on classic ESP32; other chips use LEDC_LOW_SPEED_MODE.
  • Frequency × 2^resolution must be achievable from the timer clock source.
  • Full procedure: LEDC bring-up.

Bring-up procedure (all buses)

  1. Power and wiring: measure supply at the device, common ground, short wires.
  2. Minimal config at the slowest sensible speed, explicit pins (never rely on defaults).
  3. Probe: I2C probe / SPI read of a WHO_AM_I or ID register / UART loopback / ADC on a known voltage / LEDC on a scope or LED.
  4. Check every esp_err_t; log with esp_err_to_name().
  5. Scale up: target speed, DMA, interrupts, multiple devices.
  6. Harden: timeouts, retries, bus recovery, de-init path, mutex if the bus is shared between tasks.
  7. Evidence: serial log of probe + readings, logic-analyzer capture if available.

Report

markdown
# Bring-up — <device> on <bus> (target: <chip>, IDF <ver>)
| Signal | GPIO | Chip category (esp32wb) | Notes |
## Configuration (speed, mode, address, pulls)
## Results (probe / ID register / readings, with log excerpts)
## Issues found and fixes
## Not verified (e.g. no scope available)

Rules

  • Never hallucinate peripheral limits; search the docs for the target first.
  • Pin choices must pass esp32wb pins for the configured target.
  • Any code change goes through the mission/contract workflow.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Esp32 Peripheral Bringup AI skill do?

Guides bring-up and debugging of ESP32 peripherals — I2C, SPI, UART, ADC and LEDC/PWM — using the ESP-IDF v5 driver APIs, chip-correct pin choices, and a step-by-step wiring → config → probe → speed-up procedure. Use when the user says "I2C sensor not responding", "i2c ESP_ERR_TIMEOUT", "no ACK", "I2C scan finds nothing", "SPI returns 0xFF", "SPI display blank", "UART garbage characters", "uart_read_bytes returns nothing", "ADC reads wrong value", "adc_oneshot", "analogRead with Wi-Fi", "PWM / LEDC not working", "set duty", "bring up a new sensor", or "connect a peripheral" on ESP32, ESP32-...

Why use Esp32 Peripheral Bringup on TypingMind?

Because you install it once and use it with any model. Esp32 Peripheral Bringup 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 Peripheral Bringup in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/agodianel/esp32-claude-workbench/tree/main/skills/esp32-peripheral-bringup. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Esp32 Peripheral Bringup?

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 Peripheral Bringup?

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

Is the Esp32 Peripheral Bringup AI skill free?

Yes. It is published on GitHub by agodianel 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 👇