nbialk

Guide developers through creating and updating ChatGPT and MCP apps. Covers the full lifecycle: brainstorming ideas against UX guidelines, bootstrapping projects, implementing tools/views, debugging, running dev servers, deploying and connecting apps to ChatGPT. Use when a user wants to create or update a ChatGPT app, MCP app, MCP server or use the Skybridge framework.

Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.

Add and use PostHog in Next.js (App Router) applications. Use when needing to (1) integrate PostHog analytics, (2) set up LLM analytics for AI SDK / Anthropic generations, (3) add error tracking, or (4) implement feature flags. Covers SDK setup, user identification, event capture, exception tracking, source maps, and server/client flag evaluation. Curated for a Next.js + Vercel AI SDK stack.

Create a GitHub repo (if needed) and set up Dependabot, CI workflow, auto-merge workflow, and GitHub branch ruleset.

Bootstrap a Next.js project with Prisma (PostgreSQL), tRPC, React Query, optional Clerk auth, next-themes, sonner, shadcn/ui config, and a clean folder structure. Use when the user says "set up this project", "scaffold with Prisma and tRPC", "/repo-init-next-js", "add Prisma and tRPC to this Next.js app", or wants to initialize a fresh Next.js project with the full stack.

Scaffold a new Node.js/pnpm project with TypeScript, ESLint, Prettier, .gitignore, and CLAUDE.md.

Detect and close ground-truth leakage in LLM eval datasets — cases where the model under evaluation can see material that contains or strongly implies the expected answer, so eval scores are inflated and no longer reflect real capability. Use when building, reviewing, or debugging an eval/benchmark dataset (especially for RAG or tool-using/agentic systems), when eval scores look suspiciously high, when a weak or blind baseline still passes, or when deciding whether retrieved context, tool/observation outputs, dataset fields, or upstream-stage outputs leak the target answer.