Category
Multiplayer, Live Ops & Monetization Skills for AI Agents
Skills for the parts of a game that run beyond one session: networking, player accounts and cloud saves, purchases, ads and economies that don’t rely on predatory tricks.
6 free skills, MCP servers and kits
Pick a Multiplayer & live ops skill to start with
Godot Multiplayer
Networked Godot 4.7 games: ENet host and join, @rpc functions, per-node authority and state replication with spawners and synchronizers.
Unity In-App Purchases
Implements, configures, and debugs Unity In-App Purchases, including subscriptions, receipt validation, and direct-to-customer payments via Stripe or Coda.
Unity LevelPlay Ads
Integrates the LevelPlay ad mediation SDK via the Ads Mediation package.
Unity Live Game Services
Builds and operates live games with Unity Services.
Game Monetization
Design free-to-play economies, battle passes and cosmetic shops with anti-predatory guardrails.
skills-gamedev (Skillary)
26 game development skills from the Skillary catalog: game design, level and narrative design, monetization, playtesting, Unity, Unreal, Blender, audio and engineering.
What a Multiplayer & live ops skill gives your agent
Networking basics done right
Host and join, RPCs, authority and replication, with the server staying in charge of game state.
Backend services
Accounts, cloud save, leaderboards and remote config through Unity Gaming Services.
Monetization with guardrails
IAP, ad mediation and battle pass design with anti-predatory rules built in.
How to use a game dev skill
Three steps in Claude Code, Codex, Cursor or any agent that reads SKILL.md.
- 01
Install it
Run the command on the skill's page, or copy the install prompt and let your agent run it.
- 02
Ask in plain words
Describe what you want. The agent loads the skill when your request matches, or you can call it by name.
- 03
Review and play
Run the game, read what the agent changed, and ask for fixes in the same session.
Why use a skill instead of a prompt?
A prompt is gone after one chat. A skill stays in your project: the agent reads the same checklist, engine rules and pitfalls every time the task comes up, so the results stay consistent and you stop repeating yourself.