LLM Play Testing

Community

Automate QA play-testing with an LLM agent.

AuthorWayneWalterBerry
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Automates human-like QA play-testing of a text-adventure game by an LLM agent, uncovering bugs that traditional scripted tests miss.

Core Features & Use Cases

  • Human-like exploration and bug discovery in an interactive fiction engine via natural-language prompts and varied command sequences.
  • Headless, deterministic test sessions using piped input for reliable parsing and reporting.
  • Incremental streaming of test-pass reports to capture regressions and guide fixes.
  • Support for creative QA patterns (polite phrasing, questions, synonyms) to exercise robustness of the parser and UX.

Quick Start

Launch the game in headless mode and feed commands via a piped input stream to begin play-testing.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: LLM Play Testing
Download link: https://github.com/WayneWalterBerry/MMO/archive/main.zip#llm-play-testing

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.