Esp32 Pin Audit logo

Esp32 Pin Audit

Community
agodianel
esp32-pin-audit

Audits GPIO assignments in ESP32-family firmware against the verified pin facts of the actual target chip and board, flagging flash/PSRAM pins, strapping pins, input-only pins, USB-Serial-JTAG and UART0 console pins, JTAG pins, ADC2/Wi-Fi conflicts, double assignments and pin-map drift. Use when the user asks "which pins can I use", "is GPIO 12 safe", "check my pinout", "pin conflict", "strapping pin", "board won't boot after wiring", "can't flash after connecting a sensor", "ADC2 with Wi-Fi", "input-only pin", "/pin-audit", or before adding any GPIO, I2C, SPI, UART, ADC or LEDC code on ESP32, ESP32-S2, ESP32-S3, ESP32-C2, ESP32-C3, ESP32-C5, ESP32-C6, ESP32-H2 or ESP32-P4.

Overview

Publisheragodianel
Repositoryesp32-claude-workbench
Skill nameesp32-pin-audit
Stars
81
Forks
7
Bundled files
5
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.

  • 5 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 Pin Audit 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-pin-audit
  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-pin-audit .claude/skills/esp32-pin-audit
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Esp32 Pin Audit 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 Pin Audit 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 Pin Audit 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 Pin Audit

Pin rules are chip-specific. GPIO 6–11 are flash pins on classic ESP32 but ordinary GPIOs on ESP32-S3; GPIO 34–39 are input-only on classic ESP32 but bidirectional on ESP32-S3. Never apply one chip's table to another.

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
Audit all GPIO usage (target auto-detected from CONFIG_IDF_TARGET)pin_auditesp32wb pins <path> [--target T]
Verified pin facts + Espressif source linkschip_infoesp32wb chip <target> (no arg lists targets)
Anything the chip table does not coversearch_esp_docsesp32wb docs search "<query>" --target T

Targets: esp32 esp32s2 esp32s3 esp32c2 esp32c3 esp32c5 esp32c6 esp32h2 esp32p4.

Steps

1. Establish target, module and board

  • Target from CONFIG_IDF_TARGET in sdkconfig / sdkconfig.defaults. If none is set, ESP-IDF defaults to esp32; state that assumption in the report.
  • Module/variant matters: flash and PSRAM type (quad vs octal, in-package vs external) change which pins are reserved. Check CONFIG_SPIRAM* and CONFIG_ESPTOOLPY_OCT_FLASH / octal PSRAM settings.
  • Board: if a profile exists (see References below), use it. Otherwise ask for the schematic. On-board peripherals (LEDs, buttons, displays, power-management chips) occupy pins even if the code never mentions them.

2. Run the audit tool

esp32wb pins . — it collects GPIO_NUM_*, #define *_PIN/_GPIO, Kconfig GPIO options and driver config structs, then checks them against the chip table. Include its findings verbatim; add your own analysis on top.

If the tool is unavailable, collect manually:

bash
grep -rnE "GPIO_NUM_[0-9]+|#define\s+\w*(GPIO|PIN|SDA|SCL|MOSI|MISO|SCLK|CLK|CS|TX|RX)\w*\s+[0-9]+" \
  --include=*.c --include=*.h --include=*.cpp .
grep -rn "CONFIG_.*\(GPIO\|PIN\)" sdkconfig sdkconfig.defaults* 2>/dev/null

and get the chip facts from esp32wb chip <target> or the Espressif datasheet.

3. Check every pin against the chip's categories

For each GPIO in use, look up the target's facts and classify:

CategorySeverityWhat to check
Not a GPIO on this chipERRORNumber missing from the chip's GPIO list (e.g. S3 has no GPIO22–25)
Flash SPI pinsERRORNever use. Set differs per chip
PSRAM pinsERROR if PSRAM enabledIncludes octal-mode extras on S3
Input-onlyERROR if used as output or with internal pullsClassic ESP32: 34–39 (no internal pulls). S2: GPIO46. S3/C-series: none
StrappingWARNExternal circuits must not force the wrong level at reset; note the boot function
USB D-/D+ (USB-Serial-JTAG / OTG)WARNReusing them disables USB console/JTAG/flashing over USB. Present on S2/S3/C3/C5/C6/H2/P4
UART0 console TX/RXWARNBreaks logs/flashing over UART unless the console is moved
JTAG pinsWARN if hardware debugging is used
ADC2 + Wi-Fisee below

4. ADC2 and Wi-Fi (chip-dependent)

  • Classic ESP32: ADC2 pins cannot be used while Wi-Fi is in use — ERROR. Move analog inputs to ADC1.
  • ESP32-S2 / ESP32-S3: ADC2 is shared with Wi-Fi and the driver arbitrates; adc_oneshot_read() can fail (returns an error) while Wi-Fi holds ADC2 — WARN, require retry/error handling or move to ADC1.
  • ESP32-C3: ADC2 (GPIO5) oneshot is no longer supported by current ESP-IDF due to a hardware erratum — flag any ADC2 use regardless of Wi-Fi.
  • Other chips: check esp32wb chip <target> (field "ADC2 + Wi-Fi" and notes) — several have no ADC2 at all.

5. Conflicts and electrical checks

  • Same GPIO assigned to two functions (including board-fixed functions).
  • Buses sharing pins unintentionally (I2C vs SPI vs UART).
  • I2C lines: external pull-ups required; internal pull-ups are too weak for reliable I2C. Flag configs relying only on *_pullup_en.
  • Floating inputs: buttons/sensors without external or internal pull.
  • Voltage domain: some pins run at the flash/PSRAM voltage on 1.8 V parts (e.g. ESP32-S3 GPIO47/48 on R8V/R16V variants) — check esp32wb chip.

6. Documentation drift

Compare code against pin_map.h, README pin tables, board profile and schematic. Every assignment must appear in one documented pin map (project rule).

Report

markdown
# Pin Audit — <project> (target: <chip>, board: <board>, module: <module>)
Evidence: `esp32wb pins` output + `esp32wb chip <target>` sources.

## Pin Allocation
| GPIO | Function | Defined in | Direction | Pull | Chip category |
## Errors (must fix)
## Warnings (strapping / USB / console / JTAG / ADC2)
## Conflicts
## Documentation drift
## Unknowns (facts not confirmed for this chip/board)

Use plain words (ERROR, WARN, OK) rather than emoji so the report renders in every agent and terminal.

References

Rules

  • Never hallucinate hardware constraints. If a fact is not in esp32wb chip output or a cited Espressif document, report it as unknown.
  • Label any classic-ESP32 fact as "classic ESP32" when you mention it.
  • Re-run the audit after every GPIO change and attach the output as test evidence.

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 Pin Audit AI skill do?

Audits GPIO assignments in ESP32-family firmware against the verified pin facts of the actual target chip and board, flagging flash/PSRAM pins, strapping pins, input-only pins, USB-Serial-JTAG and UART0 console pins, JTAG pins, ADC2/Wi-Fi conflicts, double assignments and pin-map drift. Use when the user asks "which pins can I use", "is GPIO 12 safe", "check my pinout", "pin conflict", "strapping pin", "board won't boot after wiring", "can't flash after connecting a sensor", "ADC2 with Wi-Fi", "input-only pin", "/pin-audit", or before adding any GPIO, I2C, SPI, UART, ADC or LEDC code on ESP...

Why use Esp32 Pin Audit on TypingMind?

Because you install it once and use it with any model. Esp32 Pin Audit 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 Pin Audit in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/agodianel/esp32-claude-workbench/tree/main/skills/esp32-pin-audit. 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 Pin Audit?

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 Pin Audit?

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

Is the Esp32 Pin Audit 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 👇