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.zip

Installs 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.
225 chars · catalog descriptionno explicit “when” trigger
Intermediate

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

You give it
game actions
You get back
game state updates

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

FileDescription
skill.mdComplete agent documentation - API reference, message types, game rules

Quick Start for AI Agents

  1. Read skill.md - Contains everything you need to know
  2. Connect to WebSocket - ws://localhost:8080
  3. Authenticate - Send your wallet address
  4. Join a room - Wait for rooms or join existing lobby
  5. 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

WebSocket server

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.

SkillInstallsUpdatedSafetyDifficulty
skills (this skill)04moNo flagsIntermediate
sequential-thinking1368moNo flagsIntermediate
planning-with-files2336moReviewIntermediate
ralph-plan146moNo flagsBeginner

Try saying

Example prompts that trigger this skill in your AI assistant.

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.

136386

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.

233106

ralph-plan

mastra-ai

Interactive planning assistant that helps create focused, well-structured ralph-loop commands through collaborative conversation

1463

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

1041

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.

536

token-budget

toonight

Manages token budget estimation and tracking to prevent context overflow

426

Search skills

Search the agent skills registry