Generate a structured implementation plan before writing any code. Produces a spec with requirements, data model, API surface, edge cases, and open questions. Use when starting a non-trivial feature, when the user says "plan this out", or before any implementation that touches more than 2 files.

Scaffold a complete full-stack feature — API route, DB query, TypeScript types, and frontend component — in one shot. Use when the user says "add a [feature]", "I need a [thing] page", or "scaffold [X]" and wants everything wired up fast.

Do a quick UI polish pass on a component or page to make it look more professional. Use when the user says "make this look better", "polish the UI", "it looks ugly", or right before a demo.

Write an enthusiastic, well-structured PR description for the current changes. Use when the user is about to open a pull request and says "write a PR description", "describe these changes", or "hype up this PR".

Audit the app for real-time performance bottlenecks and fix them — slow queries, missing indexes, N+1 problems, cache misses, and polling that should be websockets. Use when the user says "make it faster", "it's slow under load", "optimize the DB", or "add real-time updates".

Set up a data ingestion or sync pipeline — from source to destination, with transformation. Supports Airbyte, custom ETL scripts, and webhook-based ingestion. Use when the user says "sync data from X", "pull data into the DB", "set up a pipeline", or "ingest from API".

Evaluate, score, and systematically improve prompts in the codebase. Identifies weak prompts, generates test cases, scores outputs, and proposes optimized versions. Use when the user says "improve this prompt", "why is the AI doing X", "eval my prompts", or "optimize the agent".

Audit the overall code quality, architecture, and maintainability of a project or file and give an honest, unfiltered assessment. Use when the user asks "is this good?", "what do you think of this codebase?", or wants a holistic review before shipping.

Package and deploy an AI agent to production with logging, tracing, and health checks. Supports TrueFoundry, Modal, Railway, Fly.io, and containerized deploys. Use when the user says "deploy this agent", "put this in prod", "containerize my agent", or "add observability".

Add authentication and authorization to an app — login, signup, session management, and protected routes. Supports Auth0, NextAuth, Clerk, Supabase Auth, and custom JWT. Use when the user says "add login", "protect this route", "add auth", or "users need accounts".

Find and remove all debug console.log / print / debugger statements left in the codebase. Use before committing, before a PR review, or when the user says "clean up debug stuff" or "remove all the logs".

Add a demo mode to the app that bypasses auth and loads mock data, so the app works flawlessly during a hackathon presentation without needing a real account or live backend. Use when the user says "set up demo mode", "make it work without login", or "I need it to look good for the judges".

Run a pre-ship checklist against the codebase to catch embarrassing issues before a hackathon deadline or production deploy. Use when the user says "am I ready to ship?", "check before I submit", or "what am I missing?".

Generate and run realistic seed data for the project's database. Use when the user says "seed the database", "add some fake data", "I need test data", or the app looks empty during a demo.

Audit all environment variable usage in the codebase and generate a complete, documented .env.example. Use when the user says "what env vars do I need?", "document the config", "set up .env.example", or when onboarding someone new to the project.

Find and remove stale feature flags that are permanently enabled, permanently disabled, or abandoned. Use when the user says "clean up feature flags", "remove the old flags", or after a feature has been fully rolled out for more than a sprint.

Generate a structured mental model of an unfamiliar codebase — entry points, data flow, key abstractions, and gotchas. Use when starting on a new repo, when the user says "explain this codebase", "how does this work", "onboard me", or before making large changes to unfamiliar code.

Add voice AI to an app — inbound/outbound phone calls, voice agents, or speech-to-text/text-to-speech pipelines. Supports Bland AI, ElevenLabs, Deepgram, and Web Speech API. Use when the user says "add voice", "make it speak", "phone call feature", or "voice agent".

Generate a tight, compelling hackathon pitch and live demo script from the current codebase. Use when the user says "help me pitch this", "write my demo script", "what's my elevator pitch", or it's crunch time before a presentation.