Init Tauri App logo

Init Tauri App

Community
glebis
init-tauri-app

Scaffold a new Tauri v2 project with the cenno/cull house conventions — delegates boilerplate to `npm create tauri-app`, then layers an opinionated core plus opt-in modules (CLI+MCP, SQLite, tray/updater, release/preflight, Swift sidecar). Use when the user wants to start a new Tauri desktop app, "init a tauri project", or "scaffold a tauri app".

Overview

Publisherglebis
Repositoryclaude-skills
Skill nameinit-tauri-app
Stars
379
Forks
56
Bundled files
43
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.

  • 43 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Init Tauri App 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.
  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/glebis/claude-skills.git /tmp/claude-skills
mkdir -p .claude/skills
cp -r /tmp/claude-skills/init-tauri-app .claude/skills/init-tauri-app
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Init Tauri App 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 Init Tauri App 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 Init Tauri App 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.

init-tauri-app

Scaffolds a new Tauri v2 project pre-loaded with conventions proven in two production apps (cenno, cull). Delegates version-current boilerplate to the official scaffolder, then applies a durable convention layer and any opt-in modules the user selects.

When to use

  • "Start a new Tauri app", "init a tauri project", "scaffold a tauri desktop app".

Prerequisites (verify before scaffolding)

  • node + npm on PATH (node --version)
  • cargo + rustc on PATH (cargo --version)
  • macOS + Xcode CLT only required if the Swift-sidecar module is selected

Procedure

1. Gather inputs (AskUserQuestion)

Ask, in one batch:

  • App name (kebab-case). Validate ^[a-z][a-z0-9-]*$.
  • Identifier (reverse-DNS, default com.glebkalinin.<name>).
  • Target directory (default ~/ai_projects/<name>). Abort if it exists and is non-empty.
  • Frontend framework: react-ts | svelte-kit | vanilla-ts.
  • Modules (multi-select): CLI+MCP · SQLite · Tray/Updater · Release/Preflight · Swift sidecar.
  • JTBD artifact (optional): a path to a jtbd.json. If not given, the skill auto-discovers ./jtbd.json then ~/jtbd/<name>/jtbd.json. See Step 1.5.

If Swift sidecar selected but host is non-macOS or xcrun --find swift fails: warn and drop it.

1.5 Ingest JTBD (optional, additive)

  1. Resolve the artifact, first hit wins: explicit path → ./jtbd.json~/jtbd/<name>/jtbd.json. If none found, skip this whole step (the scaffold proceeds with empty product context — no error).
  2. Confirm: echo the artifact's hook and ask the user to confirm before using it. On decline, skip.
  3. Validate: the artifact must parse and have name, hook, jtbd. If not, warn and skip ingestion (never abort the scaffold). render-jtbd.sh exits 3 on invalid input — treat that as "skip".
  4. Pre-fill: if valid, default the app name to name and identifier to com.glebkalinin.<name> (still confirm with the user in Step 1 if not already chosen).
  5. The artifacts are written during Step 3 (core layer) — see the JTBD block there.

2. Scaffold base

bash
cd <parent-of-target>
npm create tauri-app@latest <name> -- --template <framework> --manager npm --yes

Then cd <target> && npm install.

Known upstream fix (current rustc + Tauri 2.11.x): a bare scaffold's first cargo check can fail with error[E0119] on cookie/time (transitive cookie 0.18.1 vs time 0.3.48). This is not a skill bug — it hits any fresh create-tauri-app. If it occurs, run once in src-tauri/: cargo update -p time --precise 0.3.47, then re-check.

3. Apply core layer

Copy every file from assets/core/ into the project, applying the renames in the table below, then run a baseline gate. Substitute <name> (and <identifier> where the token appears) in AGENTS.md and README.

assetdestination
core/AGENTS.mdAGENTS.md
core/CLAUDE.md.claude/CLAUDE.md
core/gitignore.gitignore (merge: append only house lines not already present; skip lines — including comment headers — that already exist)
core/rust-toolchain.tomlsrc-tauri/rust-toolchain.toml
core/node-version.node-version
core/mcp.json.mcp.json
core/capabilities/default.jsonsrc-tauri/capabilities/default.json (overwrite)
core/scripts/check-versions.shscripts/check-versions.sh (chmod +x)
core/README.mdREADME.md
core/CONTRIBUTING.mdCONTRIBUTING.md

If a JTBD artifact was confirmed in Step 1.5, also:

  • Render assets/jtbd/PRODUCT.md.templatedocs/PRODUCT.md via scripts/render-jtbd.sh <artifact> assets/jtbd/PRODUCT.md.template <artifact-path>.
  • Render assets/jtbd/guardrails-check.md.templatedocs/internal/guardrails-check.md.
  • Render assets/jtbd/agents-product-section.md.template and insert it into AGENTS.md immediately after the first heading (so product context leads the file).
  • Copy the artifact verbatim to project-root jtbd.json (never modify the source).
  • Field→destination details: assets/jtbd/jtbd-map.md.

Create empty tracked dir docs/internal/.gitkeep and docs/.gitkeep. Enable TS strict: ensure tsconfig.json has strict, noUnusedLocals, noUnusedParameters true.

Gate: cd src-tauri && cargo check and cd .. && npm run build. Both must pass before modules.

4. Compose selected modules

For each selected module, in this order — cli-mcp, sqlite, tray-updater, swift-sidecar, release-preflight — open assets/modules/<m>/INSERT.md and follow it exactly: it lists files to copy, Cargo deps to merge into src-tauri/Cargo.toml [dependencies], and insertion points in src-tauri/src/lib.rs (tauri::generate_handler![...]) and src-tauri/src/main.rs.

After EACH module: cd src-tauri && cargo check. If it fails, fix the just-applied merge before continuing (failures localize to the current module). For modules with a frontend/script part, also run the relevant check named in that INSERT.md.

5. Final verification + handoff

  • cd src-tauri && cargo check → must pass
  • npm run build → must pass
  • bash scripts/check-versions.sh → must pass
  • Offer git init && git add -A && git commit -m "chore: scaffold via init-tauri-app".
  • Print a summary: framework, modules applied, modules skipped (with reason), next commands (npm run tauri dev).

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 Init Tauri App AI skill do?

Scaffold a new Tauri v2 project with the cenno/cull house conventions — delegates boilerplate to `npm create tauri-app`, then layers an opinionated core plus opt-in modules (CLI+MCP, SQLite, tray/updater, release/preflight, Swift sidecar). Use when the user wants to start a new Tauri desktop app, "init a tauri project", or "scaffold a tauri app".

Why use Init Tauri App on TypingMind?

Because you install it once and use it with any model. Init Tauri App 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 Init Tauri App in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/glebis/claude-skills/tree/main/init-tauri-app. 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 Init Tauri App?

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 Init Tauri App?

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

Is the Init Tauri App AI skill free?

Yes. It is published on GitHub by glebis 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 👇