I haven’t watched yet but I tossed the transcript into claude and chat gpt
ChatGPT:
- Main Idea: The best marketing tool for your game is the game itself.
- Key Strategy: Develop and engage a community around your game during its development.
- Understanding Steam: Learn how Steam works for both developers and players to tailor your marketing approach.
- Marketing Tips: Focus on unique aspects of Steam’s platform to market your game effectively.
- Overall Goal: Integrate marketing efforts with game development for better results.
Claude:
- Your game is your best marketing tool
- Be authentic to your game and target audience
- Steam offers tools to market to your unique audience
- Build wishlists and community well before launch
- Focus on gameplay in trailer, screenshots, description, tags
- Get feedback via beta, playtests, demos; join Next Fest
- Launch: Steam emails wishlisters, features in queues
- Post-launch: keep engaging players via updates, discounts, events
- Stay authentic and responsive to build your audience
The key is to know your game and audience, start marketing early, leverage Steam’s tools, and continue nurturing your community after release. Authenticity and active engagement are crucial for success on Steam.
With such a complex system like that it would probably be beneficial to actually build the parts you care about and take advantage of libraries handling the querying of Data like ECS and rendering with bevy. Otherwise you’ll run into the risk of being limited by the library in one way or another.
Define a bunch of structs that you can use compositionally in bevy’s ECS. Create specific systems that react to components being added, removed, or changed. Set conditions like Burnability, Durability, Temperature… etc. React to those conditions or thresholds being met. Your reaction could even be a component. Damage(5), IgnoreArmorDamage(3), CurrencyUpdate(-5), GiveItem(Item::Sword(Stats {…}))
It basically gives you a foundation that feels like scripting but with the power of compile time safety for virtually everything. You get to “model” the data how you want instead of being limited or overwhelmed. And with ECS it really helps make things feel like Lego blocks that you can easily reuse across the entire project.