- Home
- Skills
- Frontend & Web Apps
- chatbot creator skill
More screenshots
Works with the AI Agents you already use
chatbot creator skill
Scaffold a complete FastAPI and React chatbot project with JWT auth, SQLite, and WebSocket streaming.
Free
chatbot creator skill
Example session with this skill installed
I need to build a new chatbot project from scratch with a React frontend and a FastAPI backend that supports streaming.
- Read your context and instructions
- Compiled the chatbot creator
I have scaffolded a complete LLM chatbot application. The project includes a FastAPI backend with JWT authentication and LangGraph services, paired with a React TypeScript frontend featuring WebSocket streaming for real-time responses.
Project Structure Overview
| Component | Technology | Path |
|---|---|---|
| Backend API | FastAPI + SQLAlchemy | /backend/app/api |
| Orchestration | LangGraph + Memory | /backend/app/services |
| Database | SQLite + SQLAlchemy | /backend/app/database.py |
| Frontend | React + Vite + TS | /frontend/src |
| State Mgmt | Custom Hooks (Auth/Chat) | /frontend/src/hooks |
# Backend Setup
cd backend
python -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activate
pip install -r requirements.txt
# Set your API keys in .env
uvicorn app.main:app --reload
# Frontend Setup
cd ../frontend
npm install
npm run dev
Next steps
- Add your
OPENAI_API_KEYorANTHROPIC_API_KEYtobackend/.env. - Run
npm run buildin the frontend folder to verify the TypeScript types. - Access the dashboard at
http://localhost:5173to register your first user account.
Connects securely to your tools. The creator never sees your data.
About this skill
Building a full-stack LLM application from scratch usually requires hours of boilerplate setup for authentication, database schemas, and WebSocket streaming. This skill automates the entire process, scaffolding a complete FastAPI and React project ready for Claude, OpenAI, or Gemini integration.
What it does
- Scaffolds full-stack projects by generating a complete directory structure for backend and frontend.
- Configures user authentication using JWT tokens, bcrypt password hashing, and secure login/registration flows.
- Enables real-time streaming via native WebSocket implementations in both FastAPI and React.
- Manages chat persistence with a pre-configured SQLite database and SQLAlchemy models for sessions and messages.
- Integrates LangGraph for sophisticated LLM orchestration using stateful graphs and memory.
How it works
- Safety check to identify existing directories and request explicit overwrite permission.
- Backend generation of FastAPI modules, security utilities, and LangGraph service layers.
- Frontend generation of a TypeScript React app, including custom hooks for auth and chat.
- Validation via a Python script to ensure all 30+ files are correctly placed.
Frameworks & tools
Python 3.11, FastAPI, SQLAlchemy, LangGraph, SQLite, React 18, TypeScript, Vite, and JWT.
Why this beats prompting it yourself
Prompting a full-stack app usually results in disconnected snippets or missing imports. This skill enforces a strict, production-ready architecture with consistent schemas across both the Python and TypeScript layers.
Use cases
- Launching a private internal AI chatbot for a team.
- Prototyping a new LLM-powered SaaS product.
- Creating a sandbox for testing LangGraph logic with a real UI.
- Scaffolding a technical demonstration for clients.
Known limitations
Does not include Docker configurations, CI/CD pipelines, or social OAuth providers. Limited to SQLite for local development.
Requires Python 3.11+ and Node.js. Supports email/password auth and SQLite only. No cloud deployment or CI/CD configurations included.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
1 use
Times used to date
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 1 month ago
- Free with an Agensi account
Requires