Get the FREE Ultimate OpenClaw Setup Guide →
d

Pokemon Red

Scanned

@drbarq

npx machina-cli add skill @drbarq/pokemon-red --openclaw
Files (1)
SKILL.md
5.5 KB

Pokemon Red — You Are the Trainer

You play Pokemon Red directly. No middleman script. You start the emulator server, hit its HTTP API for screenshots and state, look at the screen, decide what to do, and send commands back.

Setup (first time)

Clone the repo and install dependencies:

git clone https://github.com/drbarq/Pokemon-OpenClaw.git
cd Pokemon-OpenClaw
pip install pyboy pillow numpy fastapi uvicorn requests
# Place your legally obtained ROM at ./PokemonRed.gb

Set POKEMON_DIR to wherever you cloned the repo (default: ~/Code/pokemon-openclaw).

Start a Session

# Start emulator server (background process)
cd $POKEMON_DIR && python scripts/emulator_server.py --save ready --port 3456

Turn Loop

Every turn, do these in order:

1. Get state + screenshot

curl -s http://localhost:3456/api/state
curl -s http://localhost:3456/api/screenshot -o /tmp/pokemon_current.png

Then use the image tool to look at the screenshot. Always look before acting.

2. Decide: Navigate or Manual?

Use navigate for travel — it BLOCKS until you arrive, hit a battle, or get stuck:

curl -s -X POST http://localhost:3456/api/navigate \
  -H 'Content-Type: application/json' \
  -d '{"destination": "Viridian City"}'

Navigate returns one of:

  • "status": "arrived" — you're there! Continue quest.
  • "status": "battle" — wild encounter interrupted. Fight it, then navigate again.
  • "status": "stuck" — couldn't reach destination. Try manual buttons or different route.
  • "status": "error" — unknown destination or no path. Check destinations list.

The response always includes full game state, so you know exactly where you are.

Important: Navigate blocks — set a long timeout (60-120s) on the curl call.

Check available destinations first:

curl -s http://localhost:3456/api/destinations

Check which maps have pathfinding data:

curl -s http://localhost:3456/api/maps

Fall back to manual buttons only when:

  • Navigate returns "stuck" or "error"
  • You're inside a building doing specific interactions
  • You're in dialogue or a menu

3. Manual controls (when needed)

# Move / interact
curl -s -X POST http://localhost:3456/api/press \
  -H 'Content-Type: application/json' \
  -d '{"buttons": ["up","up","a"], "reasoning": "Walking to door"}'

Valid buttons: up, down, left, right, a, b, start, select. Send 1-5 per turn.

4. Battle (when in_battle is true in state)

  • Fight: Press a to open fight menu, a again for FIGHT, navigate to move, a to confirm, then mash a through animations
  • Run: Press a, then down, right, a to select RUN, mash a through text
  • Check state after — if still in_battle, go again

5. Quest tracking

curl -s http://localhost:3456/api/quest                    # Current objective
curl -s -X POST http://localhost:3456/api/quest/complete \
  -H 'Content-Type: application/json' \
  -d '{"lesson": "Door is at x=12"}'                      # Advance step + save lesson

6. Save frequently

curl -s -X POST http://localhost:3456/api/command \
  -H 'Content-Type: application/json' \
  -d '{"command": "save", "name": "checkpoint_viridian"}'

Key Endpoints

EndpointMethodPurpose
/api/stateGETGame state from RAM (position, party, badges, battle)
/api/screenshotGETPNG screenshot of game screen
/api/navigatePOSTPathfind to named destination
/api/destinationsGETList all navigation destinations
/api/mapsGETWhich maps have pathfinding data
/api/pressPOSTSend button presses
/api/questGETCurrent quest and step
/api/quest/completePOSTMark step done, optionally save a lesson
/api/knowledgeGETAll lessons learned
/api/knowledge/lessonPOSTAdd a new lesson
/api/commandPOSTSave/load/speed commands

Strategy Priority

  1. Navigate first. For any travel, use /api/navigate. It blocks until arrival or battle — no polling needed.
  2. Handle battles immediately. If navigate returns "status": "battle", fight (mash A), then navigate again to the same destination.
  3. Check quest. Always know your current objective. Don't wander.
  4. HP management. Below 30% → consider healing. Below 15% → definitely heal. Navigate to nearest pokecenter.
  5. Ignore text_active. The text detection flag is broken (always true). Don't spam B to dismiss phantom text.
  6. Save often. Every 10 turns or after any milestone.

Session Pattern

A sub-agent session should:

  1. Start emulator server (if not already running)
  2. Check quest status and destinations
  3. Play 20-50 turns (navigate + manual as needed)
  4. Save state before exiting
  5. Report progress (location, level, quest step, any highlights)

Keep notes in /tmp/pokemon_notepad.txt for continuity within a session.

For Full Game Strategy

See references/game_instructions.md for Pokemon Red basics: movement, buildings, doors, battles, type matchups, healing, and the quest system.

Source

git clone https://clawhub.ai/drbarq/pokemon-redView on GitHub

Overview

Pokemon Red is played directly by an OpenClaw agent acting as the player. It starts a PyBoy-based emulator server, reads game state from RAM, and decides actions via an HTTP API. This setup supports battles, exploration, grinding, and competitive play between agents, using a legally obtained ROM and Python 3.10+.

How This Skill Works

The agent runs emulator_server.py and communicates through HTTP endpoints. It retrieves the current state with /api/state and the screen image with /api/screenshot, then issues actions via /api/navigate or /api/press. Navigate blocks until arrival, a battle starts, or it gets stuck; manual button presses are used when needed, and frequent saves help preserve progress.

When to Use It

  • You want a full, autonomous playthrough of Pokemon Red from start to finish.
  • You need robust pathfinding to travel between locations while handling occasional battles.
  • You intend to grind levels or farm encounters in a controlled, repeatable way.
  • You want to run multiple agent instances in parallel to compare strategies or performance.
  • You seek reproducible sessions with checkpoints and systematic state logging.

Quick Start

  1. Step 1: Clone the repo, install dependencies, and place the ROM at ./PokemonRed.gb.
  2. Step 2: Start the emulator server: cd $POKEMON_DIR && python scripts/emulator_server.py --save ready --port 3456.
  3. Step 3: Use the API to fetch state, view screenshots, and issue navigate/press commands to play.

Best Practices

  • Place your legally obtained ROM at ./PokemonRed.gb and set POKEMON_DIR to your clone location.
  • Use Python 3.10+ and install dependencies: pyboy, pillow, numpy, fastapi, uvicorn, requests.
  • Clone the repo, configure the directory, and start the server with the provided command.
  • Always inspect the state and screenshot before acting; use navigate for travel when possible.
  • Set a long timeout (60-120s) on navigate and save frequently to preserve progress.

Example Use Cases

  • Run a complete playthrough from start to a defined endpoint (e.g., defeating a gym or reaching a target town).
  • Automate grinding by repeatedly navigating routes with battles to reach a target level.
  • Execute parallel sessions to compare routing strategies or battle decision paths.
  • Explore routes and map data via /api/maps to validate available destinations and pathfinding.
  • Create checkpoints with /api/command for save states to enable reproducible experiments.

Frequently Asked Questions

Add this skill to your agents
Sponsor this space

Reach thousands of developers