Zero-config backend, hosting, and version control for non-technical builders. Connects Supabase, Vercel, and GitHub through natural conversation.
Install and configure Cortex — connects GitHub, Vercel, and Supabase to Claude so you can build and deploy real apps through conversation. Use when the user needs to set up Cortex for the first time or reconnect.
Start building a new project. Interviews the user about their idea, produces a clear plan, and determines what infrastructure they actually need — before writing any code. Use when the user wants to build something new or is unsure where to start.
A Claude Code plugin that gives non-technical builders real infrastructure — GitHub, Vercel, and Supabase — through natural conversation.
claude plugin install cortex@Dana-Innovations/cortex-claude-plugins
/cortex:setupGuided installation of the Cortex MCP server. Connects your Claude to GitHub (version control), Vercel (hosting), and Supabase (database). Explains everything in plain English — no terminal knowledge required.
/cortex:vibecodeStart building a new project. Interviews you about your idea, figures out what you actually need, and produces a clear plan before writing any code. Determines whether you need a simple static site or a full backend with user accounts and a database.
/cortex:setup — authenticates and connects your services/cortex:vibecode — describe your idea, get a plan, then buildThe plugin automatically checks if Cortex is configured when you start a session. If not, it'll nudge you to run setup.
The vibecode skill determines the simplest infrastructure that meets your needs:
| Tier | What It Is | When You Need It |
|---|---|---|
| 0 | Static site (GitHub + Vercel) | Portfolio, landing page, docs |
| 1 | Client app (GitHub + Vercel) | Tools, calculators, single-user apps |
| 2 | Backend-lite (+ Supabase) | Forms, public data, no login needed |
| 3 | Full stack (+ Supabase auth) | User accounts, personalized data |
| 4 | Multi-service (+ integrations) | Payments, email, external APIs |
It always recommends the lowest tier and tells you what would trigger upgrading later.
.claude-plugin/plugin.json # Plugin manifest + MCP server config
.mcp.json # Cortex MCP server definition
hooks/hooks.json # Session start hook (config check)
skills/setup/SKILL.md # /cortex:setup skill
skills/setup/scripts/ # Hook scripts
skills/vibecode/SKILL.md # /cortex:vibecode skill
MIT
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub dana-innovations/cortex-claude-plugins --plugin cortex-codeSonance skills for Claude. Guided workflows and smart defaults powered by you, your colleagues, and Cortex.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.