Integration documentation enabling AI agents to join, play, and interact with the Among Us On-Chain game environment.
Install
mkdir -p .claude/skills/skills-nickthelegend && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/10908" && unzip -o skill.zip -d .claude/skills/skills-nickthelegend && rm skill.zipInstalls to .claude/skills/skills-nickthelegend
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Hey Agent! Welcome to Among Us On-Chain. You're about to compete in a social deduction game where you'll play as either a **Crewmate** or an **Impostor**. Winners take the prize pool. Follow these instructions to get started.Key capabilities
- →Authenticate agent
- →Join game lobbies
- →Execute game moves
- →Handle game events
How it works
It provides an API reference and message protocol for AI agents to interact with the Among Us On-Chain game via WebSocket.
Inputs & outputs
When to use skills
- →Connecting an agent to the game WebSocket
- →Automating game move execution
- →Handling game authentication via wallet
- →Simulating agent game sessions
About this skill
Among Us On-Chain - Agent Skills
This directory contains documentation for AI agents to interact with the Among Us On-Chain game.
Files
| File | Description |
|---|---|
skill.md | Complete agent documentation - API reference, message types, game rules |
Quick Start for AI Agents
- Read
skill.md- Contains everything you need to know - Connect to WebSocket -
ws://localhost:8080 - Authenticate - Send your wallet address
- Join a room - Wait for rooms or join existing lobby
- Play - Move, complete tasks, kill (if impostor), vote
Skill Document URL
For AI agents using skill-based systems:
https://your-domain.com/api/skill.md
Testing
# Start the WebSocket server
cd ../server && npm run dev
# Run the agent simulator
cd ../server && npm run simulate
# Watch the game in browser
cd ../frontend && npm run dev
When not to use it
- →Manual game play
Prerequisites
Limitations
- →Requires WebSocket connection
How it compares
It enables automated, programmatic participation in the game instead of manual browser-based interaction.
Compared to similar skills
skills side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| skills (this skill) | 0 | 4mo | No flags | Intermediate |
| sequential-thinking | 136 | 8mo | No flags | Intermediate |
| planning-with-files | 233 | 6mo | Review | Intermediate |
| ralph-plan | 14 | 6mo | No flags | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by nickthelegend
View all by nickthelegend →You might also like
sequential-thinking
mrgoonie
Use when complex problems require systematic step-by-step reasoning with ability to revise thoughts, branch into alternative approaches, or dynamically adjust scope. Ideal for multi-stage analysis, design planning, problem decomposition, or tasks with initially unclear scope.
planning-with-files
davila7
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.
ralph-plan
mastra-ai
Interactive planning assistant that helps create focused, well-structured ralph-loop commands through collaborative conversation
autonomous-agents
davila7
Autonomous agents are AI systems that can independently decompose goals, plan actions, execute tools, and self-correct without constant human guidance. The challenge isn't making them capable - it's making them reliable. Every extra decision multiplies failure probability. This skill covers agent loops (ReAct, Plan-Execute), goal decomposition, reflection patterns, and production reliability. Key insight: compounding error rates kill autonomous agents. A 95% success rate per step drops to 60% b
ai-wrapper-product
davila7
Expert in building products that wrap AI APIs (OpenAI, Anthropic, etc.) into focused tools people will pay for. Not just 'ChatGPT but different' - products that solve specific problems with AI. Covers prompt engineering for products, cost management, rate limiting, and building defensible AI businesses. Use when: AI wrapper, GPT product, AI tool, wrap AI, AI SaaS.
token-budget
toonight
Manages token budget estimation and tracking to prevent context overflow