AliFullStack

🥈Silver

AliFullStack is a local-first, open-source AI app builder for operations teams. It enables rapid development, testing, and deployment of full-stack applications with LLM integration. Teams can build internal tools, automate workflows, and connect to existing systems without vendor lock-in.

5390Updated 1mo ago

Intermediate30min to implementautomation

Saves ~240 min per use

Quick InstallView Source

git clone https://github.com/SFARPak/AliFullStack.git

Works with:

Claude

Overview

About This Skill

How to Use

1. **Define Your Use Case**: Start by clearly outlining the problem you’re solving (e.g., automating a manual process, building a dashboard, or creating a workflow tool). Use the prompt template to customize the tool’s purpose, tech stack, and LLM integration. 2. **Set Up AliFullStack**: Install AliFullStack locally using their CLI: `npm install -g @ali-fullstack/cli`. Initialize a new project with `ali init [PROJECT_NAME]` and select the template that matches your stack (e.g., React + Node.js). 3. **Configure the LLM**: In the project’s `config/llm.js` file, specify the model (e.g., `mistral-7b-instruct`), API key, and system prompts. Test the LLM integration locally before deploying. 4. **Develop and Test**: Use AliFullStack’s built-in development server (`ali dev`) to iterate on the frontend and backend. Leverage their hot-reload feature for rapid prototyping. Write unit tests for critical paths (e.g., LLM validation logic). 5. **Deploy**: Run `ali deploy --env [ENVIRONMENT]` to push your app to production. AliFullStack supports local-first deployment, so you can also export the app as a standalone executable for offline use. **Tips for Better Results:** - Start small: Build a minimal viable tool (e.g., a form + database) and expand iteratively. - Use AliFullStack’s pre-built components (e.g., auth, database connectors) to save time. - Monitor LLM performance: Log prompts, responses, and errors to refine the system prompts over time. - Involve end-users early: Share prototypes with your team to gather feedback before finalizing the tool.

Setup & Installation

Quick Install

No install command available. Check the GitHub repository for manual installation instructions.

Alternative Install (Git Clone)

git clone https://github.com/SFARPak/AliFullStack

Requirements

Claude Code or compatible AI agent
Works with: Claude

Quick Start Guide

Install the Skill

Copy the install command above and run it in your terminal.

Open Your AI Agent

Launch Claude Code, Cursor, or your preferred AI coding agent.

Try It Out

Use the prompt template or examples below to test the skill.

Customize

Adapt the skill to your specific use case and workflow.

Usage Examples

Prompt Template

Build a full-stack internal tool for [TEAM_NAME] using AliFullStack to [SPECIFIC_GOAL]. The tool should include a [FRONTEND_COMPONENT] (e.g., dashboard, form, or table) connected to a [BACKEND_SERVICE] (e.g., database, API, or automation). Use [PROGRAMMING_LANGUAGE] for the frontend and [PROGRAMMING_LANGUAGE] for the backend. Include LLM integration for [LLM_TASK] (e.g., summarization, classification, or data extraction). Provide the complete codebase with setup instructions and deployment steps.

Example Output

Here’s a full-stack internal tool built with AliFullStack for the Operations team at GreenEarth Solutions to automate their vendor invoice processing workflow. The tool includes a React-based frontend with a drag-and-drop invoice upload interface, a Node.js backend that processes invoices using OCR and LLM-powered validation, and a PostgreSQL database to store vendor data and invoice statuses. The LLM (using the `mistral-7b-instruct` model) extracts key fields like vendor name, invoice number, and amount, then cross-references them with the company’s vendor database to flag discrepancies.

**Frontend (React):**
- A dashboard displays a real-time table of pending invoices, sorted by urgency. Each row includes a 'Review' button that triggers the LLM validation process.
- A form allows users to manually input invoice details if OCR fails, with dropdowns pre-populated from the vendor database.
- The UI updates dynamically via WebSocket connections to the backend, ensuring the team sees changes in real-time.

**Backend (Node.js):**
- The `/upload` endpoint accepts PDF/JPEG/PNG files, stores them in an S3 bucket, and queues them for processing.
- The `/process` endpoint uses Tesseract.js for OCR and the LLM to extract and validate invoice data against the vendor database. Invalid invoices are flagged for manual review.
- The `/status` endpoint provides a RESTful API for the frontend to fetch invoice statuses and updates.

**Database (PostgreSQL):**
- Schema includes tables for `vendors` (id, name, contact, approved_invoice_threshold), `invoices` (id, vendor_id, file_path, status, extracted_data), and `audit_logs` (id, invoice_id, action, timestamp).

**LLM Integration:**
- The LLM is prompted with: "Extract the vendor name, invoice number, date, and total amount from this invoice. Return the data in JSON format. If the vendor name doesn’t match our database, flag it as invalid."
- The backend parses the LLM’s response and updates the invoice status accordingly.

**Deployment:**
1. Clone the AliFullStack template: `git clone https://github.com/ali-fullstack/ali-fullstack-template.git`
2. Install dependencies: `npm install` (frontend) and `npm install` (backend).
3. Set up the database: `docker-compose up -d` (PostgreSQL + S3 mock).
4. Configure the LLM: Add your API key to `.env` and select the model in `config/llm.js`.
5. Run the app: `npm run dev` (frontend) and `npm start` (backend).
6. Deploy using AliFullStack’s built-in CLI: `ali deploy --env production`.

The tool reduced invoice processing time by 60% in the first week of use, with the LLM handling 85% of validations automatically.