RomanSlack

Discerio — AI skill for Claude Code

AI community

Learn Agentic AI through play.

How to install Discerio

This entry records only its repository, not the path inside it, so there is no exact command to give. Open RomanSlack/Discerio and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Discerio does

Learn Agentic AI through play. Built at HackPrinceton Fall 2025, where it won 🥇1st Place in the YC Challenge and 🥇1st Place in the Dedalus Special Track, Discer.io is an MMO sandbox to build and deploy AI workflows with drag-and-drop blocks.

Alternatives in AI

Skills Manage — Desktop app to manage AI coding agent skills across Claude Code, Cursor, Gemini CLI, Codex, and 20+ platforms 2.2k ★
Internal Safety Collapse — We built an adversarial codespace setup 1.2k ★
Agor — Orchestrate Claude Code, Codex, and Gemini sessions on a multiplayer canvas 1.2k ★

README

Discer.io

Learn Agentic AI Through Play

[![React](https://img.shields.io/badge/React-19-61dafb?logo=react&logoColor=white)](https://react.dev/) [![FastAPI](https://img.shields.io/badge/FastAPI-0.115-009688?logo=fastapi&logoColor=white)](https://fastapi.tiangolo.com/) [![TypeScript](https://img.shields.io/badge/TypeScript-5.0-3178c6?logo=typescript&logoColor=white)](https://www.typescriptlang.org/) [![OpenAI](https://img.shields.io/badge/OpenAI-API-412991?logo=openai&logoColor=white)](https://openai.com/) [![Daedalus](https://img.shields.io/badge/Daedalus-Labs-7c3aed)](https://www.dedaluslabs.ai/) [![Tailwind CSS](https://img.shields.io/badge/Tailwind-CSS-38bdf8?logo=tailwind-css&logoColor=white)](https://tailwindcss.com/)

Discer.io Banner

Overview

Discer.io is an interactive platform that teaches agentic AI concepts through a multiplayer battle royale game. Build AI agents using a visual block-based programming interface, deploy them into a live combat arena, and watch them make real-time decisions using large language models. Created for HackPrinceton Fall 2025.

Project Links

Visual Programming Interface

A React-based drag-and-drop environment where users design agent behavior without writing code. Agents are composed of:

Action Blocks: Entry points (onStart, onAttacked)
Agent Blocks: LLM decision points with system/user prompts
Tool Blocks: Game actions (move, attack, collect, switch_weapon, plan, search)

Agent Orchestration Backend

FastAPI server managing agent execution with dual LLM provider support:

Daedalus Mode: Multi-provider access (OpenAI, Anthropic, Google) with MCP server integration
OpenAI Mode: Direct API calls for lower latency
Parallel agent execution with configurable step