Web Stack Like Corbin logo

Web Stack Like Corbin

Community
crutchcorn
web-stack-like-corbin

Choose and configure Corbin Crutchley's preferred web stack when starting a web app, selecting frontend or backend tooling, or making an explicit stack migration. Covers runtime, frameworks, routing, forms, validation, state, styling, API clients, data, auth, testing, and deployment preferences. Load it for any library choice in a web application, including a single library such as a form or routing library, so the preferred option is considered first. Explanatory writing or framework comparisons without a project technology decision do not need this skill. Do not use an unrelated feature or bug fix as a reason to replace an existing stack.

Overview

Publishercrutchcorn
Repositoryskills
Skill nameweb-stack-like-corbin
Stars
56
Forks
0
Bundled files
6
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.

  • 6 bundled files

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

  • Open source

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

Installation

Install the Web Stack Like Corbin 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/crutchcorn/skills/tree/main/web-stack-like-corbin
  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/crutchcorn/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/web-stack-like-corbin .claude/skills/web-stack-like-corbin
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Web Stack Like Corbin 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 Web Stack Like Corbin 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 Web Stack Like Corbin 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.

Web Stack Like Corbin

Use Corbin's preferred tools for open technology decisions. Preserve the user's explicit choices and working project constraints; this skill does not authorize a stack migration or deployment.

Load the relevant preferences

Read references/stack.md before selecting tools. It is the source of truth for preferred tools, acceptable alternatives, and conditional choices. For each dependency, identify the current feature or integration that will use it before adding it. Defer tools whose only consumer is a possible future feature, including validation libraries when no current input boundary needs them; the preferred stack is not an installation checklist.

Read references/compatibility.md when resolving package versions, configuring TypeScript execution or form logic, preserving the OpenAPI pipeline, or targeting a deployment runtime. Verify current upstream documentation before relying on release status or APIs.

Choose the architecture

  • Use Astro for marketing and other static sites.
  • Prefer React for application interfaces and TanStack Router for client-side routing.
  • Use TanStack Query for async/server state, TanStack Form v2 for form logic even while in alpha, and prefer Valibot for runtime validation.
  • Prefer TanStack Start when the application needs SSR. Keep its API side lightweight; put the substantive backend in a separate Hono app in the same monorepo.
  • Prefer Hono for the backend and PostgreSQL with Drizzle v1 RC for persistence when a database is needed.
  • Prefer Cloudflare for hosting. Match dependencies to the actual deployment runtime; Node.js is the default JavaScript runtime preference, not a claim that every host runs Node.js.

For existing projects, inspect their manifests, lockfiles, configuration, and deployment requirements first. Explain a material compatibility conflict and choose a supported path within the task's scope instead of silently changing the requested tool or version.

Configure the chosen tools

  • When choosing type-checking tooling, use TypeScript 6 for both frontend and backend. Keep type checking separate from runtime execution or transpilation; do not downgrade an existing project during unrelated work.
  • Use pnpm for package management. Prefer Nx for task orchestration when needed; Turborepo is also acceptable.
  • Prefer Prettier for formatting and ESLint for linting. Add language support where needed, including Astro or Vue. Do not run Prettier through ESLint plugins.
  • Use Stylelint for CSS/SCSS and Knip to identify unused code, dependencies, and exports. Investigate findings before removing anything.
  • Use CSS Modules with SCSS strictly for media-query variables. Do not introduce Tailwind or another styling system by default, or expand Sass into a general abstraction layer.
  • Generate client API types with openapi-typescript, use OpenAPI Fetch for clients, and MSW with openapi-msw for fetch mocks. Preserve the OpenAPI specification, generated types, client, and mock pipeline during refactors.
  • Use Vitest, including for the backend. For frontend tests, use Vitest Browser Mode with Playwright. A choice of test runner does not require new tests for every change.

Keep formatting, linting, type checking, and the relevant build checks independently runnable. Record implementation and contributor setup in AGENTS.md or CONTRIBUTING.md; keep the project README focused on its users.

Check the result

Check that each selected dependency serves a present requirement, the selected versions support one another, and the build targets the intended runtime. Run relevant existing checks and report any verification that could not be completed. Explain departures from these preferences in terms of the user's requirement or a concrete compatibility constraint.

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 Web Stack Like Corbin AI skill do?

Choose and configure Corbin Crutchley's preferred web stack when starting a web app, selecting frontend or backend tooling, or making an explicit stack migration. Covers runtime, frameworks, routing, forms, validation, state, styling, API clients, data, auth, testing, and deployment preferences. Load it for any library choice in a web application, including a single library such as a form or routing library, so the preferred option is considered first. Explanatory writing or framework comparisons without a project technology decision do not need this skill. Do not use an unrelated feature o...

Why use Web Stack Like Corbin on TypingMind?

Because you install it once and use it with any model. Web Stack Like Corbin 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 Web Stack Like Corbin in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/crutchcorn/skills/tree/main/web-stack-like-corbin. 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 Web Stack Like Corbin?

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 Web Stack Like Corbin?

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

Is the Web Stack Like Corbin AI skill free?

It is published on GitHub by crutchcorn. 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 👇