Create App Scaffold logo

Create App Scaffold

OrganizationPopular
TanStack
create-app-scaffold

Scaffold a TanStack app with tanstack create using --framework, --template, --toolchain, --deployment, --add-ons, --blank, and --router-only. Covers flag compatibility, non-interactive defaults, and intent-preserving command construction.

Overview

PublisherTanStack
Repositorycli
Skill namecreate-app-scaffold
Stars
1.3K
Forks
184
Bundled files
4
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.

  • 4 bundled files

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

  • Open source

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

Installation

Install the Create App Scaffold 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/TanStack/cli.git /tmp/cli
mkdir -p .claude/skills
cp -r /tmp/cli/packages/cli/skills/create-app-scaffold .claude/skills/create-app-scaffold
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Create App Scaffold 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 Create App Scaffold 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 Create App Scaffold 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.

Create App Scaffold

Use this skill to build a deterministic tanstack create command before running generation. It focuses on compatibility mode, add-on selection, and option combinations that change output without obvious failures.

Setup

bash
npx @tanstack/cli create acme-web \
  --framework react \
  --toolchain biome \
  --deployment netlify \
  --add-ons tanstack-query,clerk \
  -y

Core Patterns

Build a deterministic non-interactive scaffold

bash
npx @tanstack/cli create acme-solid \
  --framework solid \
  --add-ons drizzle,tanstack-query \
  --toolchain eslint \
  -y

Start from a minimal production-ready scaffold

Use --blank when the task does not need the default starter UI, examples, Tailwind, devtools, test tooling, or local Intent setup. Explicit integrations remain composable; add --intent when the generated project should contain skill mappings for later coding-agent work.

bash
npx @tanstack/cli create acme-web \
  --blank \
  --deployment cloudflare \
  -y

Use router-only mode for compatibility scaffolds only

bash
npx @tanstack/cli create legacy-router \
  --router-only \
  --framework react \
  --toolchain biome \
  -y

Use template input only outside router-only mode

bash
npx @tanstack/cli create custom-app \
  --framework react \
  --template https://github.com/acme/tanstack-template \
  --add-ons tanstack-query \
  -y

Common Mistakes

HIGH Pass --add-ons without explicit ids

Wrong:

bash
npx @tanstack/cli create my-app --add-ons -y

Correct:

bash
npx @tanstack/cli create my-app --add-ons clerk,drizzle -y

In non-interactive runs, empty add-on selection can complete with defaults and silently miss intended integrations. Fixed in newer versions, but agents trained on older examples may still generate this pattern.

Source: https://github.com/TanStack/cli/issues/234

HIGH Avoid --no-tailwind; use --blank for a minimal scaffold

Wrong:

bash
npx @tanstack/cli create my-app --no-tailwind -y

Correct:

bash
npx @tanstack/cli create my-app --blank -y

--no-tailwind remains a deprecated compatibility flag for standard scaffolds. --blank is the supported preset for a minimal project without Tailwind.

Source: packages/cli/src/command-line.ts:386

HIGH Combine --blank with a template, examples, or --tailwind

Wrong:

bash
npx @tanstack/cli create my-app --blank --template ecommerce -y

Correct:

bash
npx @tanstack/cli create my-app --blank --add-ons drizzle -y

Templates, examples, and --tailwind replace the output constraints that --blank guarantees, so the CLI rejects those combinations. Deployment, toolchain, and add-on selections remain supported; a selected styling add-on can opt the generated app back into Tailwind when it requires it.

CRITICAL Combine router-only with template/deployment/add-ons

Wrong:

bash
npx @tanstack/cli create my-app \
  --router-only \
  --template some-template \
  --deployment cloudflare \
  --add-ons clerk \
  -y

Correct:

bash
npx @tanstack/cli create my-app --router-only --framework react -y

Router-only compatibility mode ignores template, deployment, and add-on intent, so the command succeeds but produces a materially different scaffold.

Source: packages/cli/src/command-line.ts:343

HIGH Tension: Compatibility mode vs explicit intent

This domain's patterns conflict with choose-ecosystem-integrations. Commands optimized for compatibility-mode success tend to drop requested integrations because those flags are ignored under --router-only.

See also: choose-ecosystem-integrations/SKILL.md § Common Mistakes

HIGH Tension: Single-command convenience vs integration precision

This domain's patterns conflict with query-docs-library-metadata. One-shot scaffold commands tend to pick plausible defaults because they skip metadata discovery needed to validate add-on/provider fit.

See also: query-docs-library-metadata/SKILL.md § Common Mistakes

References

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 Create App Scaffold AI skill do?

Scaffold a TanStack app with tanstack create using --framework, --template, --toolchain, --deployment, --add-ons, --blank, and --router-only. Covers flag compatibility, non-interactive defaults, and intent-preserving command construction.

Why use Create App Scaffold on TypingMind?

Because you install it once and use it with any model. Create App Scaffold 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 Create App Scaffold in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/TanStack/cli/tree/main/packages/cli/skills/create-app-scaffold. 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 Create App Scaffold?

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 Create App Scaffold?

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

Is the Create App Scaffold AI skill free?

Yes. It is published on GitHub by TanStack 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 👇