Esp32 Feature Contract

Community

agodianel

esp32-feature-contract

Creates a mission file and an implementation contract (scope, affected files, risks, tests, rollback) that must be accepted before any ESP32 firmware code is changed. Use when the user asks to "add a feature", "implement", "fix a bug", "refactor", "write a contract", "start a mission", "plan this change", "/contract", or "resume the mission" in an ESP-IDF, ESP32, ESP32-S3, ESP32-C3 or ESP32-C6 project, and before editing any firmware source.

Overview

Publisher	agodianel
Repository	`esp32-claude-workbench`
Skill name	`esp32-feature-contract`
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 Feature Contract 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-feature-contract
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-feature-contract

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-feature-contract .claude/skills/esp32-feature-contract

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

Use it in TypingMind

Enable Esp32 Feature Contract 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 Feature Contract 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 Feature Contract 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 Feature Contract

No firmware edit without an accepted contract. The workflow is:

mission → contract → test plan → implement → test evidence → PR

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>.

Need	MCP tool	CLI
New mission file in `missions/`	`create_mission`	`esp32wb mission new "<name>" -d "<desc>" --target T --board B`
Check a mission has all sections	`validate_mission`	`esp32wb mission validate missions/<file>.md [--json]`
Draft a contract	`generate_contract`	`esp32wb contract "<summary>" --files "path\|ACTION\|desc" --risks "..." --tests "..." --rollback "..." [-o file]`
Pin / peripheral risk facts	`pin_audit`, `chip_info`	`esp32wb pins .`, `esp32wb chip <target>`
Whole-project baseline	`project_doctor`	`esp32wb doctor .`

Templates if the tools are unavailable: mission template and contract template.

Steps

1. Open or create the mission

If missions/ has an active mission for this work, read it and resume from Current Status / Next Step.
Otherwise create one (tool above). Fill Board / Target from CONFIG_IDF_TARGET, not from assumption. If the target is unknown, ask.

2. Gather requirements

Requested change and expected behaviour after it.
Target chip, board, ESP-IDF version.
Hardware involved: which pins, buses, peripherals. Run esp32wb pins . and esp32wb chip <target> before proposing any GPIO; never quote pin limits from memory.
For peripheral, ADC, timer, Wi-Fi or BLE work, search the docs first (search_esp_docs / esp32wb docs search "<query>" --target T).

3. Write the contract

Size the contract to the change:

Change size	Contract
Tiny (typo, log text, constant tweak, one file, no API/pin/timing impact)	Brief: summary, files, one-line risk, test, rollback
Normal	Full template
Touches boot, partitions, OTA, flash encryption, eFuses, strapping pins	Full template + explicit Boot risk = HIGH + hardware test

Every contract contains:

Change summary — one paragraph.
Non-goals — what is explicitly out of scope.
Affected files — every file created/modified/deleted (path|ACTION|description).
APIs touched — public functions, Kconfig options, NVS keys, protocols.
Risk assessment (LOW/MED/HIGH with reasons):
- Concurrency — shared state, ISRs, task priorities, core affinity.
- Peripheral — pin conflicts, strapping/flash/PSRAM/USB pins for this chip, bus contention.
- Memory — heap, stack (bytes), DMA-capable / internal RAM, PSRAM.
- Boot — init order, strapping pins, partition table, bootloader config.
- Backward compatibility — API, wire protocol, NVS schema, OTA from older versions.
Test plan — new/updated tests, no-hardware vs hardware tests, evidence required. For anything non-trivial hand off to the esp32-test-plan skill.
Rollback — how to revert, and what persistent state (NVS, filesystem, OTA slot, eFuses — the last are irreversible) must be considered.
Acceptance criteria — measurable.

4. Get acceptance

Present the contract and stop. Do not edit firmware until the user accepts it. Record acceptance (date, who) in the mission History table.

5. During implementation

Stay inside the contracted file list. If scope grows, update the contract and get re-acceptance before continuing.
Update the mission Current Status and Next Step as you go.

6. After implementation

Record test commands and results (pass/fail with output) in the mission.
List what was not tested and why.
Run esp32wb mission validate on the mission file.
Prepare the PR with the esp32-pr-prepare skill, linking mission + contract.

Rules

Never skip the contract; a brief one is fine for tiny changes.
Never edit code before acceptance.
Never invent hardware constraints — cite esp32wb chip output or Espressif docs.
Changes that burn eFuses or enable secure boot / flash encryption require an explicit, separate confirmation from the user: they are irreversible.

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 Feature Contract AI skill do?

Why use Esp32 Feature Contract on TypingMind?

Because you install it once and use it with any model. Esp32 Feature Contract 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 Feature Contract in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/agodianel/esp32-claude-workbench/tree/main/skills/esp32-feature-contract. 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 Feature Contract?

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 Feature Contract?

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

Is the Esp32 Feature Contract 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

Apple Notes

openclaw

OrganizationPopular

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

Bear Notes

Create, search, and manage Bear notes via grizzly CLI.

Gog

Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.

Healthcheck

Audit/harden OpenClaw hosts: SSH, firewall, updates, exposure, backups, disk encryption, gateway security.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

ESP32 Feature Contract

Tools

Steps

1. Open or create the mission

2. Gather requirements

3. Write the contract

4. Get acceptance

5. During implementation

6. After implementation

Rules

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now