skills.rest
carterwayneskhizeine
carterwayneskhizeineCOMMUNITY
Explore all skills by this author →
GitHub

pokemon-player

Automate Gen 1-style Pokémon gameplay via headless emulator with RAM and screenshot verification.

19|4|Updated Apr 22, 2026
Search Tags:#pokemon#emulator#ram reads#ai gameplay#save states#vision verification#dashboard streaming
One-click install
npx skills add https://github.com/carterwayneskhizeine/hermes-agent-windows-R --skill pokemon-player-carterwayneskhizeine
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pokemon-player
Source: https://github.com/carterwayneskhizeine/hermes-agent-windows-R/tree/main/skills/gaming/pokemon-player
Command: npx skills add https://github.com/carterwayneskhizeine/hermes-agent-windows-R --skill pokemon-player-carterwayneskhizeine

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes assets (resource) components.

What problem does it solve?

This Skill helps users play or observe Pokémon gameplay automatically by running a headless emulator and controlling the game through RAM reads plus vision-based verification.

Core Features & Use Cases

  • Headless emulation control: Runs Pokémon games via the pokemon-agent package and drives gameplay using a defined action loop.
  • RAM + vision decisioning: Reads game state (position/HP/dialog flags) while also taking screenshots and using vision analysis to avoid navigation mistakes.
  • Save/Load for safe progress: Supports periodic saving, targeted loading, and save listing to reduce risky failure points.

Quick Start

Ask the AI to start the Pokémon Player workflow and begin the game using the ROM it already has available on this machine.

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 using a headless emulator with AI?▼

To automate Pokemon gameplay, run a headless emulator and drive actions using RAM state reads combined with screenshot-based vision verification. This allows an AI agent to safely navigate and battle through the game loop.

How does RAM state and vision verification work for AI Pokemon navigation?▼

RAM state reads extract game variables like position and HP, while vision verification takes screenshots to visually confirm the game state. Combining both prevents the AI from making navigation mistakes during gameplay.

Can I resume AI Pokemon gameplay from saved states?▼

Yes, you can resume AI Pokemon gameplay from saved states. The system supports periodic saving, targeted loading, and save listing via API endpoints to reduce risky failure points and safely recover progress.

Do I need a specific ROM or server to run automated Pokemon gameplay?▼

You need a user-provided ROM file and a running pokemon-agent server to execute the automated gameplay. The AI uses health-checked game loops polling /state and /screenshot endpoints to control the headless emulator.

Can I stream a live dashboard while the AI plays Pokemon headlessly?▼

Yes, you can stream a live dashboard tunnel while the AI plays Pokemon headlessly. This provides a real-time visual feed of the automated gameplay and AI decisioning process.

What are the limitations of using RAM reads for Gen 1 Pokemon AI gameplay?▼

RAM reads for AI gameplay are limited to specific Gen 1-style Pokemon games. You must provide the correct ROM and maintain a running pokemon-agent server, as the AI relies on these to function correctly.

Related Skills

Explore More Software Engineering Skills→
gunabotgunabot
7

add-gmail

Integrate Gmail with NanoClaw for automated email reading, sending, and replying.

Community
Advanced
JamesFincherJamesFincher

pokemon-player

Automate Pokémon gameplay with RAM reads and vision-verified screenshots.

Community
Advanced
LuminaVaultLuminaVault

pokemon-player

Automate Pokemon gameplay via headless emulation with pyboy and RAM analysis.

Official
Advanced
zangjeicyzangjeicy

pokemon-player

Execute autonomous Pokemon gameplay via headless emulator with vision-based state verification.

Community
Advanced