Setup logo

Setup

Community
Zane456
setup

First-run setup of a freshly cloned workspace — locale, toolchain, USER.md. Invoke ONLY when root `USER.md` is missing, or the user asks to set up / configure / 初始化 the workspace. A filled `USER.md` means setup is done: never invoke.

Overview

PublisherZane456
RepositoryPCB-Agent-Teams
Skill namesetup
Stars
79
Forks
20
Bundled files
1
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 Zane456 on GitHub. Read the source before you install it.

Installation

Install the Setup 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/Zane456/PCB-Agent-Teams/tree/main/.claude/skills/setup
  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/Zane456/PCB-Agent-Teams.git /tmp/PCB-Agent-Teams
mkdir -p .claude/skills
cp -r /tmp/PCB-Agent-Teams/.claude/skills/setup .claude/skills/setup
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Setup 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 Setup 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 Setup 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.

Setup — first run only

Preconditions (check all three before Step 1)

1. USER.md must be absent. If it exists, diff USER.md USER.md.example first. Identical, or §0 所属地 still [待填], means someone ran the manual cp and never filled it in — the gate reads "configured" while nothing is. Report that, then run this guide normally and overwrite the stub at Step 4 (no rm needed — it holds nothing). Never guess a country from it. A genuinely filled USER.md → stop, say so in one line, do nothing else.

2. Runtime is Claude Code. If you are any other agent (Codex, Copilot, Cursor, Gemini …), say so before Step 1: nothing here is wired for you — routing table and skill directory use Claude Code conventions, and the skills shell out to kicad-cli, a project venv and distributor APIs that other agents sandbox differently. Point at README.md → Using another agent and let them decide. Never proceed as if the runtime were supported.

3. Language. Step 1 is the only English message. Step 2 onward, reply in the user's language.

Step 1 — one question, nothing else

Which country are you in? (Reply in your own language.)

Alone. No preamble, no setup instructions — the user may not read English yet. One line buys both the locale (Phase 2 routing) and the language (whatever they answer in).

If their opening message already showed their language, that half is answered: ask the same country question in their language. Still one question, still nothing else.

Step 2 — locale verdict

Switch to their language. Lead with the constraint so this never reads as a limit on the whole workspace:

Locale binds exactly one phase — Phase 2, part selection, because it decides which distributor warehouse is actually reachable for you. Phases 0, 1, 2.5, 3, 3.5, 4, 4.5, 5 are locale-neutral.

AnswerSkillSay
Japancomponent-selecting-JPReady today. Needs one free DigiKey key (2 env vars); Mouser/element14 optional.
China mainlandcomponent-selecting-CNReady today. Zero API keys — LCSC public endpoints.
anything elsenoneNo skill for that country yet → the three options below.

Unimplemented locale — three honest options

Never silently reuse another locale's skill. Present all three, recommend by effort:

🅰 Hand-pick parts, skip the skill. Write the MPN list yourself, hand it to component-preparing. Zero setup; every other phase (schematic, ERC, SPICE, PCB, DRC, EMC, thermal, Gerber) runs untouched. Fastest, costs nothing.

🅱 Build component-selecting-<XX>. The engine is already locale-parameterised, so a port is a thin shell — but only if the region has a distributor with a public API (DigiKey / Mouser / LCSC are the only ones the engine speaks). No API distributor → say so, go 🅰. Only if they pick 🅱, read references/new_locale.md.

🅲 Use the nearest implemented locale, verify stock yourself. Cheap, but stock/price/lifecycle come from the wrong warehouse — feasibility passes only, never ordering.

Step 3 — toolchain check

Report a pass/fail checklist. Install nothing without asking.

bash
uname -s                                                  # Darwin expected
python3.12 --version                                      # 3.12 only; 3.13 / 3.14 unsupported
command -v kicad-cli || ls /Applications/KiCad/KiCad.app  # KiCad 10
command -v ngspice                                        # brew install ngspice
ls .venv/bin/python 2>/dev/null                           # venv already built?

OS — say it before they invest time. Developed and tested on macOS only. Linux untested but plausible (scripts probe PATH / Homebrew / Snap / Flatpak for kicad-cli). Windows will hit path assumptions; WSL is the realistic route.

Missing pieces → give the exact command from README.md → Prerequisites. Show these, do not run them (slow, network-bound):

bash
python3.12 -m venv .venv
.venv/bin/pip install -r requirements.txt
.venv/bin/playwright install chromium   # JP pipeline only (DigiKey probing)

Step 4 — write the config files

Reversible only; refuse to overwrite a target that already exists — except a confirmed stub. A USER.md byte-identical to USER.md.example holds nothing to lose, so overwrite it in place rather than demanding rm first. Never overwrite a USER.md that has any real content, and never touch an existing .env.

Always reach this step, whatever the locale. USER.md is what retires this guide — finish without writing it and the gate fires again next session, trapping the user in setup. An unimplemented locale is still a locale: record it truthfully.

  1. cp USER.md.example USER.md, then fill from this conversation:
    • §0 所属地 — the country as the user said it, even with no skill covering it. Never substitute a neighbour to make routing "work". If unimplemented, append the option they picked, e.g. 德国(无对应 skill — 走手工选品 → component-preparing).
    • §0 沟通语言 + §5 语言 — both, same value. Filling only §5 leaves the summary table mismatched.
    • §3 焊接能力 — ask now, one question: smallest package you can hand-solder, and do you have hot air / reflow? Gates part selection directly (a QFN pick is useless to an iron-only bench).
    • Everything else stays [待填] — skills ask when relevant.
  2. Keys, by locale: CN → none, skip .env entirely. JP (or any DigiKey-based locale) → cp .env.example .env, name the two variables, link the free registration. Never write or echo a key.

Step 5 — close out, and retire

Setup is done. This guide is gated on USER.md being absent, so it will not run again. To delete it outright: rm -rf .claude/skills/setup

Then hand off: project-init for a new board, circuit-design if they already know the topology.

Do not

  • ❌ Send anything but the single question in Step 1
  • ❌ Keep speaking English after they answered in another language
  • ❌ Silently fall back to JP or CN for an unlisted country
  • ❌ Promise a component-selecting-<XX> skill without passing the feasibility gate
  • ❌ Run pip install / venv builds / playwright install without asking
  • ❌ Overwrite a USER.md holding real content, or any existing .env (a stub USER.md is the one exception)
  • ❌ Finish the conversation without writing USER.md

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 Setup AI skill do?

First-run setup of a freshly cloned workspace — locale, toolchain, USER.md. Invoke ONLY when root `USER.md` is missing, or the user asks to set up / configure / 初始化 the workspace. A filled `USER.md` means setup is done: never invoke.

Why use Setup on TypingMind?

Because you install it once and use it with any model. Setup 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 Setup in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Zane456/PCB-Agent-Teams/tree/main/.claude/skills/setup. 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 Setup?

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 Setup?

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

Is the Setup AI skill free?

It is published on GitHub by Zane456. Check the repository for licensing terms. 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 👇