pokemon-player

Automate Pokemon gameplay by running a headless server and issuing button inputs.

Updated May 1, 2026
One-click install
npx skills add https://github.com/xiaoquqi/hermes-agent-skills --skill pokemon-player-xiaoquqi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pokemon-player
Source: https://github.com/xiaoquqi/hermes-agent-skills/tree/main/gaming/pokemon-player
Command: npx skills add https://github.com/xiaoquqi/hermes-agent-skills --skill pokemon-player-xiaoquqi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables autonomous Pokemon gameplay by running a headless game server, interpreting RAM state, and issuing inputs from the terminal, reducing the need for manual control and enabling scalable demonstrations or testing.

Core Features & Use Cases

  • Remote-controlled gameplay: starts a Pokemon-agent server, connects to a ROM, and streams state for decision making.
  • Automated decision loop: observe, orient, decide, act, verify, and save progress to memory.
  • Use Case: Learn strategy by watching AI play through classic Gen 1 routes or evaluate different play styles.

Quick Start

Start the pokemon-agent server with a provided ROM and port, then verify startup with GET /health.

Frequently Asked Questions about pokemon-player

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

FAQPage Schema
How do I automate Pokemon gameplay with a headless emulator?

To automate Pokemon gameplay, this Skill runs a headless game server, interprets RAM state, and issues button inputs based on vision feedback. It uses an observe-orient-decide-act loop to play through ROMs autonomously without manual control.

What do I need to set up an AI agent to play Pokemon?

You need a Pokemon-agent-compatible setup with Python 3.10 or higher and a valid Pokemon ROM. A running server exposing endpoints like GET /state and POST /action is also required to enable the automated decision loop.

How does an AI agent read game state and make decisions in Pokemon?

The AI agent reads game state by querying RAM data through a GET /state endpoint and processing vision feedback. It then follows an observe, orient, decide, act, and verify sequence to issue button inputs via POST /action.

Can I use this to test Pokemon strategies across different ROMs?

Yes, you can use this Skill to test strategies and demonstrate autonomous gameplay across various ROMs. It connects to your provided ROM and streams state for decision making, allowing you to evaluate different play styles.

Does autonomous Pokemon gameplay require manual save management?

No, the automated decision loop includes a save step after acting and verifying progress. The Skill automatically saves progress to memory using the POST /save endpoint, eliminating the need for manual save management.