skills.rest
ruiyangruiyi
ruiyangruiyiCOMMUNITY
Explore all skills by this author →
GitHub

pokemon-player

Control a headless Pokémon emulator using RAM reads and vision verification.

Updated May 26, 2026
Search Tags:#computer vision#pokemon#save state#emulator#gameplay automation#headless server#ram state
One-click install
npx skills add https://github.com/ruiyangruiyi/hermes-agent --skill pokemon-player-ruiyangruiyi
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pokemon-player
Source: https://github.com/ruiyangruiyi/hermes-agent/tree/main/skills/gaming/pokemon-player
Command: npx skills add https://github.com/ruiyangruiyi/hermes-agent --skill pokemon-player-ruiyangruiyi

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes assets (resource) components.

What problem does it solve?

This Skill helps you play and observe Pokémon gameplay automatically by running a headless emulator and using RAM reads plus vision to decide actions.

Core Features & Use Cases

  • Headless Pokémon emulation: Runs Pokémon games through a server interface using a local ROM you provide, then accepts API calls for state, actions, screenshots, and save/load.
  • RAM + vision gameplay loop: Reads structured game state from RAM while also taking screenshots for spatial awareness, then verifies moves visually to avoid getting lost.
  • Safe progression controls: Guides when to save, load, and periodically store progress using a PKM memory convention (with specific save/load endpoints).

Quick Start

Ask the agent to play Pokemon using your provided ROM and start/resume the game so you can watch the AI navigate, battle, and save progress.

Frequently Asked Questions about pokemon-player

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

FAQPage Schema
How do I automate Pokémon gameplay using a headless emulator?▼

The gameplay loop uses RAM reads to extract structured game state and takes screenshots for spatial awareness. This combination allows the agent to make informed move decisions while using visual verification to avoid getting lost during gameplay.

What do I need to set up to run automated Pokémon gameplay?▼

Progress is managed through a PKM memory convention that guides when to save and load. The agent periodically stores progress using specific save/load API endpoints, ensuring safe progression controls prevent significant loss if the agent makes a poor decision.

Can I use headless emulation to watch an AI play Pokémon in real time?▼

Yes, headless emulation supports live watching through a dashboard tunnel workflow. The agent server provides screenshot endpoints that capture the current game state, allowing you to observe the AI navigating, battling, and saving progress as it happens.

Does automated Pokémon gameplay require computer vision to verify moves?▼

Yes, computer vision is used alongside RAM state reads to verify moves visually. Screenshots provide spatial awareness that RAM reads alone cannot capture, ensuring the agent stays oriented and does not get lost during complex navigation or battles.

Related Skills

Explore More Software Engineering Skills→
cabeznocabezno

pokemon-player

Control a headless Pokémon emulator using RAM state and screenshot vision.

Community
Advanced
SethyPagnaSethyPagna

pokemon-player

Control headless Pokémon gameplay via emulator state and in-game actions.

Community
Advanced
RheasilviaRheasilvia

pokemon-player

Automates headless Pokemon emulation with pyboy, RAM monitoring, and vision feedback for battles and navigation.

Community
Advanced
guccangguccang
3

pokemon-player

Operate Pokemon emulator environments and manage game progression through AI-driven gameplay sessions.

Community
Advanced