Skip to content
Prompt

gistify — Cursor Rules

by lucis

AI Summary

Heuristic scoring (no AI key configured).

Install

Copy this and paste it into Claude Code, Cursor, or any AI assistant:

I want to add the "gistify — Cursor Rules" prompt rules to my project.
Repository: https://github.com/lucis/gistify

Please read the repo to find the rules/prompt file, then:
1. Download it to the correct location (.cursorrules, .windsurfrules, .github/prompts/, or project root — based on the file type)
2. If there's an existing rules file, merge the new rules in rather than overwriting
3. Confirm what was added

Description

Cursor Rules for gistify

Project Overview

This is a Deco MCP (Model Context Protocol) server template with a React + Tailwind CSS frontend. It provides a full-stack development environment where: • The /server folder contains the MCP server (Cloudflare Workers + Deco runtime) • The /view folder contains the React frontend (Vite + Tailwind CSS) • The server serves both MCP endpoints AND the built frontend assets

Goal

The goal of this template is to help users generate their apps with data schemas, workflows, tools, using AI and third-party API via our RPC framework (check deco.gen.ts). After this template is initiated, the user will give you prompt to create a new application. Required: Modify README.md and SEO props (in index.html) for the app as soon as you know the app's intent. We shouldn't deploy applications with the same README and title, description of the template.

Project Structure

` react-tailwind-view/ ├── package.json # Root workspace with dev/gen/deploy scripts ├── server/ # MCP Server (Cloudflare Workers + Deco) │ ├── main.ts # Main server entry point │ ├── deco.gen.ts # Generated types for integrations │ ├── tools/ # Domain-organized tools (max 300 lines per file) │ │ ├── index.ts # Central export point for all tools │ │ ├── todos.ts # Todo-related tools │ │ ├── user.ts # User-related tools │ │ └── [domain].ts # Additional domain-specific tools │ ├── workflows/ # Domain-organized workflows (max 300 lines per file) │ │ ├── index.ts # Central export point for all workflows │ │ └── [domain].ts # Domain-specific workflows │ ├── wrangler.toml # Cloudflare Workers config │ └── package.json # Server dependencies └── view/ # React Frontend (Vite + Tailwind) ├── src/ │ ├── main.tsx # React app entry point │ ├── lib/rpc.ts # RPC client for server communication │ ├── hooks/ # TanStack Query hooks for RPC calls │ ├── routes/ # React Router routes │ └── components/ # UI components ├── package.json # Frontend dependencies └── vite.config.ts # Vite configuration `

Root Commands (npm workspace)

• npm run dev - Primary development command • Starts frontend build in watch mode • Starts MCP server on port 8787 • Server serves both API endpoints + frontend assets • Hot reload for both frontend and backend • npm run gen - Type generation • Generates TypeScript types for deco integrations • Creates server/deco.gen.ts with typed RPC interfaces • Run this after adding new integrations in deco.chat • npm run gen:self - Self-type generation for your own tools • Generates TypeScript types for your own server's tools and workflows • Requires the server to be running (npm run dev) • Copy the development URL from server logs (e.g., "https://localhost-48d64e92.deco.host") • Add /mcp to the path. So, for the URL https://localhost-48d64e92.deco.host you should set DECO_SELF_URL as https://localhost-48d64e92.deco.host/mcp. • Run: DECO_SELF_URL=<your-dev-url> npm run gen:self • Creates typed RPC interfaces for your own tools/workflows • Run this after adding new tools or workflows to your server • npm run deploy - Production deployment • Builds frontend for production • Deploys to Cloudflare Workers • Makes app available at public URL

Discussion

0/2000
Loading comments...

Health Signals

MaintenanceCommitted 6mo ago
Stale
AdoptionUnder 100 stars
0 ★ · Niche
DocsMissing or thin
Undocumented

GitHub Signals

Issues0
Updated6mo ago
View on GitHub
No License

My Fox Den

Community Rating

Sign in to rate this booster

Works With

Any AI assistant that accepts custom rules or system prompts

Claude
ChatGPT
Cursor
Windsurf
Copilot
+ more