Dev Setup Config logo

Dev Setup Config

Community
diegomarino
dev-setup-config

This skill should be used when the user asks to "show dev-setup config", "change the worktrees directory", "update the port pattern", "configure dev-setup settings", or wants to view or update settings in .claude/dev-setup.json.

Overview

Publisherdiegomarino
Repositoryclaude-toolshed
Skill namedev-setup-config
Stars
58
Forks
5
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by diegomarino on GitHub. Read the source before you install it.

Installation

Install the Dev Setup Config 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/diegomarino/claude-toolshed/tree/main/plugins/dev-setup/skills/dev-setup-config
  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/diegomarino/claude-toolshed.git /tmp/claude-toolshed
mkdir -p .claude/skills
cp -r /tmp/claude-toolshed/plugins/dev-setup/skills/dev-setup-config .claude/skills/dev-setup-config
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dev Setup Config 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 Dev Setup Config 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 Dev Setup Config 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.

dev-setup-config

Overview

View and update dev-setup plugin settings stored in .claude/dev-setup.json.

Config File

.claude/dev-setup.json in the project root.

If file is absent: use these defaults (do not error):

json
{
  "worktrees_dir": ".worktrees",
  "env_file": ".env",
  "wt_port_pattern": "_WT_PORT"
}

Settings

KeyTypeDefaultDescription
worktrees_dirstring.worktreesBase directory for new worktrees. Relative to project root or absolute. ~ expansion supported.
env_filestring.envEnv file used as fallback when reading port defaults (after .wt-ports.env). For projects with .env.local, .env.development, etc.
wt_port_patternstring_WT_PORTSuffix that identifies worktree-isolated port variables in .env.example. Any var ending in this suffix will be allocated per worktree.

Process

Step 1: Read current config

Read .claude/dev-setup.json. If absent, use defaults from above.

Step 2a: Argument provided

If an argument was provided (e.g. /dev-setup-config wt_port_pattern _SVCPORT), parse it as <key> <value>:

  • If <key> is not one of worktrees_dir, env_file, wt_port_pattern: print error "Unknown key: . Valid keys: worktrees_dir, env_file, wt_port_pattern" and stop. Do not write to the file.
  1. Validate the value (see Validation below)
  2. Merge into .claude/dev-setup.json — do NOT overwrite other keys
  3. Confirm: Config saved: <key> = <value>
  4. Done. Do NOT show the menu. Do NOT ask for confirmation before saving.

Step 2b: No argument — interactive menu

Show current values and ask which to change:

Current config (.claude/dev-setup.json):

  1. worktrees_dir   -> .worktrees
  2. env_file        -> .env
  3. wt_port_pattern -> _WT_PORT

What would you like to change? (1-3, or q to quit)

On invalid input: re-show the prompt.

On selection:

  1. Prompt for new value
  2. Validate (see Validation below)
  3. Merge into file
  4. Confirm: Saved: <key> = <new-value>

Do NOT ask for y/N confirmation before saving. Validate → merge → confirm.

Validation

  • worktrees_dir: non-empty string. Warn if path contains spaces.
  • env_file: non-empty string. Warn if the file does not currently exist in the project.
  • wt_port_pattern: non-empty string matching [A-Z0-9_]+ (case-insensitive). No prefix requirement — SVCPORT, _SVCPORT, and MYPORT are all valid. Warn if no vars in .env.example end with the new pattern.

Writing the File

  1. Create .claude/ directory if it does not exist: mkdir -p .claude
  2. Read current JSON (or use defaults if absent)
  3. Update only the changed key
  4. Write back

Always merge — never overwrite the entire file.

Common Mistakes

  • Asking y/N before saving in argument mode — do not. Validate → save → confirm, no pre-write prompt.
  • Overwriting entire file — always read-update-write (merge), not replace
  • Not creating .claude/ dir — directory may not exist yet
  • Erroring when file absent — use defaults silently, do not error
  • Requiring a specific prefix — wt_port_pattern accepts any non-empty string matching [A-Z0-9_]+ (case-insensitive). Do NOT require the value to start with _ or any other specific character. SVCPORT, _SVCPORT, and MYPORT are all valid.

Frequently asked questions

What does the Dev Setup Config AI skill do?

This skill should be used when the user asks to "show dev-setup config", "change the worktrees directory", "update the port pattern", "configure dev-setup settings", or wants to view or update settings in .claude/dev-setup.json.

Why use Dev Setup Config on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/diegomarino/claude-toolshed/tree/main/plugins/dev-setup/skills/dev-setup-config. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Dev Setup Config?

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 Dev Setup Config?

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

Is the Dev Setup Config AI skill free?

It is published on GitHub by diegomarino. 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 👇