Esp32 Pr Prepare logo

Esp32 Pr Prepare

Community
agodianel
esp32-pr-prepare

Prepares a reviewable pull request for an ESP32 firmware change with summary, affected files, target chip, test evidence, static-check output, risk assessment, rollback plan and links to the mission and implementation contract. Use when the user says "prepare the PR", "write the PR description", "open a pull request", "ready for review", "/prcraft", "summarize my changes for review", or "mark the mission done" after implementing and testing an ESP-IDF change.

Overview

Publisheragodianel
Repositoryesp32-claude-workbench
Skill nameesp32-pr-prepare
Stars
81
Forks
7
Bundled files
1
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.

  • 1 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 Pr Prepare 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-pr-prepare
  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-pr-prepare .claude/skills/esp32-pr-prepare
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Esp32 Pr Prepare 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 Pr Prepare 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 Pr Prepare 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 PR Prepare

A PR is the audit record: what changed, why, how it was proven, what could go wrong.

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.

EvidenceMCP toolCLI
Static checks on the final treeproject_doctoresp32wb doctor . [--target T]
Pin audit (if GPIO changed)pin_auditesp32wb pins .
Partition / size (if app size or partitions changed)partition_checkesp32wb partitions partitions.csv --bin build/<app>.bin
Mission completenessvalidate_missionesp32wb mission validate missions/<file>.md

Steps

1. Collect artifacts

From the mission and contract: summary, motivation, non-goals, affected files, target chip(s), risks, rollback. If no contract exists, stop and say so — the workflow requires one (a brief one is fine for tiny changes).

2. Check scope

Compare the actual diff (git diff --stat <base>...HEAD) with the contract's file list. Unexpected files → explain them, update the contract, or split the PR.

3. Compile evidence

  • Exact test commands and their output (pass/fail counts).
  • esp32wb doctor summary; pin audit if GPIO changed.
  • Hardware results: chip + board + IDF version, serial log excerpts, measurements.
  • Skipped tests with reasons (e.g. hardware-only).
  • What was not tested and why.

Never claim a test passed without its output.

4. Write the description

markdown
## Summary
<what and why, one paragraph> — Mission: <link> · Contract: <link>

## Target
- Chip(s): <CONFIG_IDF_TARGET> · Board: <board> · ESP-IDF: <version>

## Changes
| File | Change | Description |
|------|--------|-------------|

### Architecture impact
- <tasks, memory, peripherals, new dependencies, Kconfig/NVS/partition changes>

## Testing
### Commands and results
```
<command>
<trimmed output>
```
- Passed: N · Failed: N · Skipped: N (reason)
### Static checks
<esp32wb doctor summary>
### Hardware validation
<board, steps, log excerpt> or "not performed — <reason>"
### Not tested
- <gap — reason>

## Risk assessment
| Risk | Level | Mitigation |
|------|-------|-----------|

## Rollback
<steps; NVS/OTA/partition implications>

## Checklist
- [ ] Contract accepted; scope matches diff
- [ ] Acceptance criteria met
- [ ] Tests added/updated; no regressions
- [ ] Pin audit clean for the target (if GPIO changed)
- [ ] Architecture review done (if structural change)
- [ ] Docs / pin map updated
- [ ] Mission updated to DONE with evidence

Use plain text markers (Passed/Failed/Skipped) rather than emoji so the description renders consistently everywhere.

5. Readiness check

  • CI would pass (same commands run locally).
  • No debug code, stray logs, or test-only sdkconfig changes.
  • No TODO/FIXME without an issue reference.
  • Commit messages descriptive.
  • Mission Current Status = REVIEW/DONE, History updated.

6. Hand-off

Output the PR description. Only run git/gh commands to create the PR if the user asks; follow the repository's branch and attribution conventions.

Rules

  1. No PR without test evidence (manual tests count if documented).
  2. Always include the risk assessment and rollback.
  3. Always link the mission and contract.
  4. Keep PRs focused; split when scope exceeded the contract.

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 Pr Prepare AI skill do?

Prepares a reviewable pull request for an ESP32 firmware change with summary, affected files, target chip, test evidence, static-check output, risk assessment, rollback plan and links to the mission and implementation contract. Use when the user says "prepare the PR", "write the PR description", "open a pull request", "ready for review", "/prcraft", "summarize my changes for review", or "mark the mission done" after implementing and testing an ESP-IDF change.

Why use Esp32 Pr Prepare on TypingMind?

Because you install it once and use it with any model. Esp32 Pr Prepare 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 Pr Prepare in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/agodianel/esp32-claude-workbench/tree/main/skills/esp32-pr-prepare. 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 Pr Prepare?

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 Pr Prepare?

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

Is the Esp32 Pr Prepare 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 👇