Esp32 Release Check

Community

agodianel

esp32-release-check

Runs a production-readiness review of ESP32 firmware — sdkconfig hardening, partition table and app-size headroom, OTA and rollback, secure boot, flash and NVS encryption, debug interfaces, logging and versioning — and returns a GO / NO-GO report with evidence. Use when the user asks "is this ready to ship", "release checklist", "production build", "prepare firmware release", "review sdkconfig", "check partition table", "OTA rollback", "secure boot", "flash encryption", "disable JTAG", "app partition too small", "/release-check", or before tagging a firmware release for ESP32, ESP32-S3, ESP32-C3, ESP32-C6 or other Espressif chips.

Overview

Publisher	agodianel
Repository	`esp32-claude-workbench`
Skill name	`esp32-release-check`
Stars	81
Forks	7
Bundled files	3
License	MIT
Links	Skill source Repository

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.
3 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 Release Check AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/agodianel/esp32-claude-workbench/tree/main/skills/esp32-release-check
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/agodianel/esp32-claude-workbench/tree/main/skills/esp32-release-check

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

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-release-check .claude/skills/esp32-release-check

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Esp32 Release Check 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 Release Check 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 Release Check 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 Release Check

A release gate. Read-only: produce findings; any change goes through a contract.

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 and attach the output as release evidence.

Need	MCP tool	CLI
Everything at once	`project_doctor`	`esp32wb doctor . [--target T]`
sdkconfig production review	`sdkconfig_review`	`esp32wb sdkconfig sdkconfig`
Partition table + app fit	`partition_check`	`esp32wb partitions partitions.csv --sdkconfig sdkconfig --bin build/<app>.bin [--flash-size 4M]`
Pins for the real target	`pin_audit`	`esp32wb pins .`
Stack sizes	`stack_check`	`esp32wb stacks .`
Security feature support per chip	`search_esp_docs`	`esp32wb docs search "secure boot v2" --target T`

Run against the release configuration (e.g. sdkconfig.defaults + sdkconfig.defaults.release / the CI release profile), not a developer's local sdkconfig.

Checklist

Mark each PASS, FAIL, N/A or UNKNOWN with evidence.

1. Build and configuration

CONFIG_IDF_TARGET matches production hardware; ESP-IDF version pinned.
Release config reproducible from committed sdkconfig.defaults*.
Clean build, no new warnings; app version set (PROJECT_VER / version.txt).
esp32wb sdkconfig shows no debug options left on (heap poisoning comprehensive, PANIC_PRINT_HALT, GDB stub, verbose log default, assertions policy as intended).
Bootloader/app log level appropriate for production.

2. Partitions and size

esp32wb partitions passes: no overlaps, aligned offsets, fits flash size.
App binary fits every app slot with headroom (team rule, e.g. ≥ 10–20 % free) to allow future OTA images.
NVS partition size adequate; nvs_keys partition present if NVS encryption is used.
Partition layout change vs the fielded version? Partition tables cannot be changed by a normal OTA — treat as HIGH risk.

3. OTA and rollback

otadata + at least two OTA app slots (ota_0, ota_1) if OTA is a requirement.
HTTPS with server certificate verification (bundle or pinned CA); no skip-verify.
CONFIG_BOOTLOADER_APP_ROLLBACK_ENABLE decision documented; if enabled, the new app calls esp_ota_mark_app_valid_cancel_rollback() only after self-test passes.
Anti-rollback (CONFIG_BOOTLOADER_APP_ANTI_ROLLBACK) secure version planned — it burns eFuses (irreversible).
Full cycle tested on hardware: download → reboot → validate → forced-failure rollback.
Details: OTA playbook.

4. Security

Secure boot and flash encryption decision recorded (enabled, or explicit risk acceptance). Availability and scheme (e.g. Secure Boot V2 RSA vs ECDSA) depend on chip and silicon revision — confirm in the ESP-IDF security guide for the target.
Flash encryption in Release mode for production (Development mode allows re-flashing plaintext).
NVS encryption enabled if secrets are stored in NVS.
JTAG / USB-Serial-JTAG debug and ROM download mode policy decided (secure download mode or disabled) — eFuse based, irreversible.
No credentials or private keys in source, logs, or sdkconfig.defaults.
Details: security checklist.

5. Robustness

Brownout detector enabled at an appropriate level.
Task WDT enabled; panic behaviour (CONFIG_ESP_SYSTEM_PANIC) set to reboot.
Core dump to flash enabled if field crash analysis is required (needs a coredump partition).
esp_reset_reason() logged/reported at boot.
Free heap / min free heap headroom measured under worst-case load.
esp32wb stacks . and esp32wb pins . clean.

6. Evidence and traceability

Mission marked complete; test plan results attached; known gaps listed.
Release notes: version, changes, migration notes (NVS schema, partition changes).
Artifacts archived: .bin, bootloader, partition table, ELF (needed to decode field crashes), sdkconfig.

Report

markdown
# Release Check — <project> <version> (target: <chip>, IDF <ver>)
## Verdict: GO | GO WITH ACCEPTED RISKS | NO-GO
## Tool evidence (doctor / sdkconfig / partitions JSON summaries)
## Blockers (FAIL items)
## Accepted risks (with owner)
## Unknowns (could not verify — e.g. eFuse state of production units)
## Checklist

Rules

NO-GO on: app does not fit an OTA slot, TLS verification disabled, debug-only config in release, missing rollback strategy for a fleet OTA product.
Never enable secure boot, flash encryption or burn eFuses as part of a review — recommend, and require explicit user approval and a contract.
Report chip-specific security support as UNKNOWN unless confirmed from Espressif docs for the exact chip revision.

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 Release Check AI skill do?

Why use Esp32 Release Check on TypingMind?

Because you install it once and use it with any model. Esp32 Release Check 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 Release Check in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/agodianel/esp32-claude-workbench/tree/main/skills/esp32-release-check. 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 Release Check?

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 Release Check?

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

Is the Esp32 Release Check 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

Security Triage

openclaw

OrganizationPopular

Triage OpenClaw security advisories, drafts, and GHSA reports with shipped-tag and trust-model proof.

Add Model Provider

Add and live-prove a model provider with non-interactive config one-liners, without exposing credentials.

Diagnose Gateway

Diagnose Gateway, config, secrets, channels, and port failures with read-only one-liners.

Apple Notes

Create, view, edit, delete, search, move, or export Apple Notes via the memo CLI on macOS.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

ESP32 Release Check

Tools

Checklist

1. Build and configuration

2. Partitions and size

3. OTA and rollback

4. Security

5. Robustness

6. Evidence and traceability

Report

Rules

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now