AI Overview

Hype Stack is built to work well with AI coding assistants. The repo includes structured rules and skills that teach AI agents how the codebase works, so they produce code that follows your conventions instead of guessing.

What's included

Cursor rules (.cursor/rules/)

24 rule files that cover every major area of the codebase:

AreaRules
BackendError handling, features structure, route validation, file uploads, deletion cascades, frontend URLs, general patterns
FrontendFeature organization, styling, theming, data fetching
TestingBackend testing, frontend testing, workflow conventions
Code styleHuman voice, no em-dash, verification after changes
InfrastructurePermissions, registry, CLI testing, pack SDK types

These rules are always active. When an AI agent works in the repo, it follows the same conventions you'd enforce in code review.

Agent skills (.agents/skills/)

6 skills that give AI agents deeper capabilities:

SkillWhat it does
brainstormingExplores intent and requirements before building anything
create-packGuides pack creation with the right file structure
frontend-designProduces polished, non-generic UI designs
honoBuilds Hono routes with proper patterns and testing
prisma-postgresHandles database setup and provisioning
find-skillsDiscovers and installs new skills

Why this matters

Without rules, AI tools generate generic code. With rules, they generate code that fits your architecture. The AI knows to use validate() middleware instead of ctx.req.json(), throws ApplicationError instead of catching errors locally, and organizes features in <domain>/<feature>/ folders instead of flat structures.