Work on the liquor_store_agentic_monitor hackathon demo — agentic multimodal retail POS monitoring (mock CV/ASR + POS fusion), Streamlit UI, policy tuning, segments JSON, webhooks, deploy.
It monitors 1000+ agents's interactions
Call the World Token Factory API to run geospatial risk assessments on any business. Decomposes businesses into operational steps, identifies risk factors, and runs multi-depth AI analysis returning structured risk tokens with failure rates, uncertainty scores, loss ranges, and cited evidence.
Build an AI-powered healthcare intake assistant with a lip-synced Anam avatar, LiveKit voice pipeline, and real-time form updates via RPC
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".
Voice-first AI senior care companion. Calls seniors daily to check mood, medications, and needs. Detects falls, loneliness, and service requests (food, medicine, bathing, transportation). Alerts family with recommended local services. Use when building senior care, voice AI, or healthcare check-in applications.
Build and configure an AI-powered phone hotline for loan support using Bland AI, Auth0, and Senso. USE FOR: setting up AI phone agents for lending, creating voice-based loan support systems, integrating Auth0 passwordless OTP with Bland AI voice agents, connecting Senso knowledge bases to phone call workflows, building fintech customer service hotlines. NOT FOR: general web app development, non-voice chatbots, or projects unrelated to phone-based loan support.
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.
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".
Packages a locally created Claude skill for publishing to Shipables. Give it a path to your skill directory and it will read the SKILL.md, generate a shipables.json, bundle everything into a .tar.gz archive in /tmp/, and tell you exactly where to find it — ready to drag and drop into the Shipables upload UI. Trigger this skill whenever the user wants to publish, package, upload, or ship a skill to Shipables, or when they say things like "package my skill", "get my skill ready to publish", "prepare skill for shipables", or "create archive for my skill".
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".
Ambient stress detection agent that monitors developer fatigue via webcam and autonomously takes over GCP Cloud Shell or browser tasks when stress threshold is crossed. Powered by Gemini 3 Flash vision, Railtracks orchestration, and Augment Code codebase context.
Use when adding authentication or login to any app - detects your stack (React, Next.js, Vue, Nuxt, Angular, Express, Fastify, React Native), sets up an Auth0 account if needed, and routes to the correct SDK setup workflow.
Build self-improving runtime security for autonomous AI agents — intercept actions, dispatch adversarial investigators, generate evolving scoring rules, and enforce deterministic block decisions with no LLM in the enforcement path.
Voice AI agent skills and MCP tools for Bland AI. Make phone calls, manage personas, knowledge bases, pathways, and more. Use when the user wants to build, test, or manage AI-powered phone agents.
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".
Build AI-powered room styling apps with Gemini vision + image generation, Unkey rate limiting, Assistant UI chat components, and Next.js App Router