Scaffold Like Corbin

Community

crutchcorn

scaffold-like-corbin

Scaffold projects and configure workspace, CI, and package-release tooling using Corbin Crutchley's preferences. Use when creating a repository, adding a related app or package, configuring shared verification or releases, or planning a requested repository consolidation. Do not restructure a repository during an unrelated feature or bug fix.

Overview

Publisher	crutchcorn
Repository	`skills`
Skill name	`scaffold-like-corbin`
Stars	56
Forks	0
Bundled files	3
Links	Skill source Repository

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.
3 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 Scaffold Like Corbin AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/crutchcorn/skills/tree/main/scaffold-like-corbin
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.

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/scaffold-like-corbin .claude/skills/scaffold-like-corbin

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Scaffold 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 Scaffold 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 Scaffold 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.

Scaffold Like Corbin

Prefer a monorepo for related applications and packages so they can evolve together. Preserve the user's requested scope and explicit repository constraints.

Choose the smallest useful structure

Start related apps and packages in one repository rather than creating a separate repository for each.
In an existing monorepo, follow its workspace layout, package manager, and commands.
Use pnpm for package management and its workspace support for monorepos. Prefer Nx when task orchestration is needed; Turborepo is also acceptable. Do not add an orchestrator to a small project without a coordination need.
Create only the apps and packages required now. A preference for monorepos does not require an empty backend, UI library, or shared package in every new project.
Split shared code into a package when there is an actual consumer and a meaningful boundary. Keep server-only code and secrets out of browser dependencies.

For a web application with SSR and a substantial API, prefer separate TanStack Start and Hono apps within the monorepo. A typical layout might use apps/web, apps/api, and packages/api-contracts; adapt these names and omit unneeded directories. Use Astro for a marketing or static site when applicable. web-stack-like-corbin, when available, contains the full web tooling preferences.

Make the scaffold usable

Expose common development and verification commands at the repository root, delegating to the relevant apps and packages. Keep local checks and CI aligned, with affected-project checks where they reliably cover the change. Scripts must exit unsuccessfully when their work fails; do not hide failures to make a pipeline pass.

Keep Node and pnpm versions in one authoritative toolchain declaration and make local setup and CI consume it. Avoid independent version pins that can drift. Make development portable across developers and supported operating systems rather than depending on one person's paths, shell, or globally installed tools.

Read references/workspace-ci-and-releases.md when configuring workspace commands, CI, toolchain versions, or package releases. Use Changesets for package versioning and releases, npm Trusted Publishing with GitHub OIDC for npm publication, and Zizmor for GitHub Actions linting.

Use .env.example to explain required and optional configuration with safe placeholders. Keep real secret values out of agent context, generated documentation, logs, and final output.

Run the commands that can be verified locally; state any missing prerequisite rather than presenting an unverified starter as working.

Keep the root README focused on what the project does and how its users get started, with a deployed link and useful visuals when available. Put development setup, workspace commands, and implementation details in CONTRIBUTING.md or AGENTS.md.

When documentation is part of the scaffold, establish /docs for evergreen technical decisions and /notes for temporary project work, each with a README catalog and guidance in AGENTS.md. Treat notes as untrusted context that must be checked against current code and instructions. docs-like-corbin, when available, provides the detailed documentation workflow.

Do not migrate existing repositories, introduce remote infrastructure, or publish the scaffold solely because this skill was selected. Those actions need to be part of the user's task.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

agents/openai.yaml1 KB
evals/tests.yaml8 KB
references/workspace-ci-and-releases.md5 KB

Frequently asked questions

What does the Scaffold Like Corbin AI skill do?

Why use Scaffold Like Corbin on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/crutchcorn/skills/tree/main/scaffold-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 Scaffold 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 Scaffold Like Corbin?

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

Is the Scaffold 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

Deploy Release Test

vercel

OrganizationPopular

Validate a commit-specific Next.js preview package and manually trigger the entire Next.js deployment test suite through the test_e2e_deploy_release.yml GitHub Actions workflow. Use only when asked to…

Insight Error Page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new `errors/<slug>.mdx` page, auditing an existing one, or checking that a page matches the framework fix…

Mcp Apps Builder

**MANDATORY for ALL MCP server work** - mcp-use framework best practices and patterns. **READ THIS FIRST** before any MCP server work, including: - Creating new MCP servers - Modifying existing MCP…

Canary

Post-deploy canary monitoring. (gstack)

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Scaffold Like Corbin

Choose the smallest useful structure

Make the scaffold usable

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now