Skip to content
Prompt

CursorHackathon — System Prompt

by EndlessMelody

AI Summary

A Dungeon Master system prompt for action-oriented, consequence-driven narrative games that integrates game mechanics and provides interactive next steps. Useful for game developers, AI enthusiasts, and RPG creators building narrative-driven applications.

Install

Copy this and paste it into Claude Code, Cursor, or any AI assistant:

I want to add the "CursorHackathon — System Prompt" prompt rules to my project.
Repository: https://github.com/EndlessMelody/CursorHackathon

Please read the repo to find the rules/prompt file, then:
1. Download it to the correct location (.cursorrules, .windsurfrules, .github/prompts/, or project root — based on the file type)
2. If there's an existing rules file, merge the new rules in rather than overwriting
3. Confirm what was added

Description

None

Key Features

• Action-Oriented: Player inputs are treated as actions, not story prompts • Consequence-Driven: Every action must have at least one concrete outcome • Interactive: Always provides 2-3 actionable next steps • Event-Integrated: Game mechanics (dice, combat) are naturally incorporated

Dungeon Master AI System Prompt

This is the system prompt used by the AI to generate action-oriented, consequence-driven narrative responses in the game.

Current Implementation

The system prompt is defined in backend/app.py in the get_dm_prompt() function. It's designed to: • Treat player input as actions - Every input is evaluated as an action with consequences • Always provide results - Every action triggers discoveries, obstacles, NPC interactions, or environmental changes • Include actionable options - Each response ends with 2-3 specific next actions the player can take • Integrate game events - Dice rolls, combat results, and skill checks are naturally woven into the narrative

Example Response Format

Good response: > "You search along the cliff edge and discover a narrow path hidden behind overgrown shrubs. A faint draft and the sound of dripping water suggest a cave ahead. You could approach the path carefully, inspect the shrubs for traps, or call out to check for echoes or creatures inside." Bad response (too passive): > "You are in a dark forest. The trees are tall and mysterious."

Discussion

0/2000
Loading comments...

Health Signals

MaintenanceCommitted 4mo ago
Stale
AdoptionUnder 100 stars
0 ★ · Niche
DocsMissing or thin
Undocumented

GitHub Signals

Issues0
Updated4mo ago
View on GitHub
No License

My Fox Den

Community Rating

Sign in to rate this booster

Works With

Any AI assistant that accepts custom rules or system prompts

Claude
ChatGPT
Cursor
Windsurf
Copilot
+ more