Let an AI play Pokemon through an emulator, using screenshots and game memory to guide movement, dialogue, and battles. The skill covers browser viewing, progress tracking, and saving or resuming play with a user-provided ROM.
Play Pokemon via headless emulator + RAM reads.
Review the instructions the agent will receive before you install.
Play Pokemon games via headless emulation using the pokemon-agent package.
The repo is NousResearch/pokemon-agent on GitHub. Clone it, then set up a Python 3.10+ virtual environment. Use uv (preferred for speed) to create the venv and install the package in editable mode with the pyboy extra. If uv is not available, fall back to python -m venv + pip.
If a checkout already exists (e.g. ~/pokemon-agent with a venv ready), just cd there and source .venv/bin/activate instead of recloning.
You also need a ROM file. Ask the user for theirs (a previous setup may already have one at roms/pokemon_red.gb inside the checkout). NEVER download or provide ROM files — always ask the user.
From inside the pokemon-agent directory with the venv activated, run pokemon-agent serve with --rom pointing to the ROM and --port 9876. Run it in the background with &. To resume from a saved game, add --load-state with the save name. Wait 4 seconds for startup, then verify with GET /health.
Use an SSH reverse tunnel via localhost.run so the user can view the dashboard in their browser. Connect with ssh, forwarding local port 9876 to remote port 80 on the keyless localhost.run endpoint (ssh -R 80:localhost:9876 ssh://nokey@localhost.run). Redirect output to a log file, wait 10 seconds, then grep the log for the .lhr.life URL. Give the user the URL with /dashboard/ appended. The tunnel URL changes each time — give the user the new one if restarted.
POST /save with a descriptive name. Good examples: before_brock, route1_start, mt_moon_entrance, got_cut
POST /load with the save name.
GET /saves returns all saved states.
Use --load-state flag when starting the server to auto-load a save. This is faster than loading via the API after startup.
GET /state for position, HP, battle, dialog. GET /screenshot and save to ~/.hermes/cache/scratch/pokemon.png, then use vision_analyze. Always do BOTH — RAM state gives numbers, vision gives spatial awareness.
Priority: dialog > battle > heal > story objective > training > explore
POST /action with a SHORT action list (2-4 actions, not 10-15).
Take a screenshot and use vision_analyze to confirm you moved where intended. This is the MOST IMPORTANT step. Without vision you WILL get lost.
When walking through a door or stairs, the screen fades to black during the map transition. You MUST wait for it to complete. Add 2-3 wait_60 actions after any door/stair warp. Without waiting, the position reads as stale and you will think you are still in the old map.
When you exit a building, you appear directly IN FRONT of the door. If you walk north, you go right back inside. ALWAYS sidestep first by walking left or right 2 tiles, then proceed in your intended direction.
Gen 1 text scrolls slowly letter-by-letter. To speed through dialog, hold B for 120 frames then press A. Repeat as needed. Holding B makes text display at max speed. Then press A to advance to the next line. The a_until_dialog_end action checks the RAM dialog flag, but this flag does not catch ALL text states. If dialog seems stuck, use the manual hold_b + press_a pattern instead and verify via screenshot.
Ledges (small cliff edges) can only be jumped DOWN (south), never climbed UP (north). If blocked by a ledge going north, you must go left or right to find the gap around it. Use vision to identify which direction the gap is. Ask the vision model explicitly.
On the battle menu, RUN is bottom-right. To reach it from the default cursor position (FIGHT, top-left): press down then right to move cursor to RUN, then press A. Wrap with hold_b to speed through text/animations.
On the battle menu FIGHT is top-left (default cursor position). Press A to enter move selection, A again to use the first move. Then hold B to speed through attack animations and text.
| Prefix | Purpose | Example |
|---|---|---|
| PKM:OBJECTIVE | Current goal | Get Parcel from Viridian Mart |
| PKM:MAP | Navigation knowledge | Viridian: mart is northeast |
| PKM:STRATEGY | Battle/team plans | Need Grass type before Misty |
| PKM:PROGRESS | Milestone tracker | Beat rival, heading to Viridian |
| PKM:STUCK | Stuck situations | Ledge at y=28 go right to bypass |
| PKM:TEAM | Team notes | Squirtle Lv6, Tackle + Tail Whip |
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Set up the 1Password CLI and use stored passwords or API keys in commands and configuration templates. Choose an authentication method, retrieve secret references, and pass credentials to processes through environment variables.
Build an Excel workbook linking the income statement, balance sheet, and cash flow statement. Populate historical figures, create formula-based forecasts, compare scenarios, and check that balances and cash totals agree across all three statements.
Adapt existing PyTorch training scripts to use multiple GPUs or machines with limited code changes. The skill guides configuration, launch commands, mixed precision, which uses lower-precision numbers, and DeepSpeed or FSDP settings for distributing training work and memory.
Configure Hermes to run AI models through Actual Computer on your own hardware. Set up either the hosted relay or a local connection, select models, verify responses, and troubleshoot request errors or empty output.
Test an app from the perspective of a frustrated, less technical user. Find confusing steps and barriers, separate actionable usability problems from personal complaints, and produce screenshots, suggested fixes, and prioritized tickets.
Resolve Git merge conflicts between two agents by comparing both changes and their stated goals. Combine compatible work, explain choices where designs differ, and verify the merged result with project builds or tests.