dev-specialisms:hashbrown-core

Build React apps with generative UI, tool calling, and sandboxed JavaScript.

4|1|Updated Jan 23, 2026

Search Tags:#react #ai #tool-calling #structured-data #generative-ui #sandbox-runtime #hashbrown

Ready to run

npx skills add https://github.com/aaronbassett/aaronbassett-marketplace --skill dev-specialisms-hashbrown-core

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: dev-specialisms:hashbrown-core
Source: https://github.com/aaronbassett/aaronbassett-marketplace/tree/main/plugins/dev-specialisms/skills/hashbrown-core
Command: npx skills add https://github.com/aaronbassett/aaronbassett-marketplace --skill dev-specialisms-hashbrown-core

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes assets (resource) and references (resource) components.

What problem does it solve?

This skill enables building AI-powered React apps using Hashbrown to render generative UI, call client-side tools, and safely execute sandboxed JavaScript.

Core Features & Use Cases

Generative UI: Expose whitelisted React components for dynamic UI rendering by the LLM.
Client-side Tool Calling: Define tools the model can invoke to read app state or trigger actions.
Streaming & Runtime: Stream model outputs and run sandboxed JavaScript in a controlled runtime.
Use Cases: Build browser agents, AI-powered UIs, chatbots, and data-driven dashboards with structured data.

Quick Start

Follow the assets guidance to set up a React app with HashbrownProvider, expose components with exposeComponent, and wire tools using useTool.

Frequently Asked Questions about dev-specialisms:hashbrown-core

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I build AI-powered React apps with generative UI?▼

To build AI-powered React apps with generative UI, use Hashbrown to expose whitelisted React components for dynamic rendering by the LLM alongside a frontend provider and backend adapter. This enables dynamic interfaces driven by model outputs.

How does client-side tool calling work in a React application?▼

Client-side tool calling in a React application works by defining tools the model can invoke using the useTool hook, allowing the LLM to read app state or trigger actions directly within the browser. Hashbrown manages this tool execution safely.

Can I safely execute sandboxed JavaScript in a React app?▼

Yes, you can safely execute sandboxed JavaScript in a React app using Hashbrown's controlled runtime. It allows the LLM to run JavaScript in a secure browser environment without compromising application state or security.

What do I need to set up streaming responses for AI chatbots in React?▼

Setting up streaming responses for AI chatbots in React requires a frontend HashbrownProvider and a backend adapter like OpenAI. This architecture streams model outputs directly to the client UI efficiently.

Does Hashbrown work with OpenAI adapters for structured data dashboards?▼

Yes, Hashbrown works with OpenAI adapters to build data-driven dashboards with structured data. You configure the backend adapter to process model outputs and expose React components for dynamic visualization.

What is the best way to expose React components to an LLM?▼

The best way to expose React components to an LLM is using Hashbrown's exposeComponent function. This whitelists specific UI components so the generative AI can dynamically render them based on model reasoning and structured data.