Summer Board To Game logo

Summer Board To Game

Organization
SummerEngine
summer-board-to-game

Bring a Summer Board's typed cards into the game as Godot Resources, load them through BoardData, and keep board and game in step.

Overview

PublisherSummerEngine
Repositorysummer
Skill namesummer-board-to-game
Stars
91
Forks
8
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by SummerEngine on GitHub. Read the source before you install it.

Installation

Install the Summer Board To Game AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/SummerEngine/summer/tree/main/library/skills/summer-board-to-game
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/SummerEngine/summer.git /tmp/summer
mkdir -p .claude/skills
cp -r /tmp/summer/library/skills/summer-board-to-game .claude/skills/summer-board-to-game
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Summer Board To Game in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Summer Board To Game on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Summer Board To Game is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Board cards in the game

Cards on the board are the game's design data. Export them once and the game loads exactly what the board says: one Resource class per type (CharacterData for Character), one .tres per card, and a BoardData script that lists them all. The board is the source; the game follows it.

1. Export

board.export {gameId, agent}                        -> files: [{path, content}], skipped, how
board.export {gameId, agent, types: ["Character"]}  -> only those types and what they link to

Write every file in files at its path with your file tools. A file under res://data/ that starts with the generated header and is not in files belongs to a card or type that is gone: delete it. Then let the editor scan the project (open it, or it rescans on focus) and check the console for errors.

What you get:

  • res://data/types/character_data.gd: class_name CharacterData extends Resource, one @export per field. A choice is @export_enum, a link is the linked type (@export var faction: FactionData, @export var drops: Array[ItemData]). A field named like a GDScript word gets a trailing _ (class is class_).
  • res://data/characters/ember_knight.tres: one per card.
  • res://data/board_data.gd: class_name BoardData, every card preloaded, a list per type and a lookup by name.

skipped lists links left out: a card that is gone, a card of the wrong type, or a link that would make two files load each other (Fox's rival is Ember Knight and the Knight's rival is Fox: one of the two is left out). Fix the cards if the game needs that link.

Every generated file starts with a Generated from the Summer Board header. Re-exporting replaces them. Your own scripts never go in res://data/.

2. Use it in gameplay code

gdscript
# Every card of a type, as typed Resources.
for c in BoardData.characters:
	if c.role == "enemy":
		spawn_table.append(c)

# One card by name.
var boss: CharacterData = BoardData.character("Ember Knight")
health.max_value = boss.hp
for item in boss.drops:
	loot.add(item)

# Links are real references.
print(boss.faction.name)
  • Read stats from the resource; do not copy numbers into scripts. The person tunes hp on the card, and the game follows.
  • A resource is shared by everything that loads it. Before changing values at run time (damage taken, upgrades), duplicate() it, or keep run-time state in the node.
  • A link whose card is gone, or that skipped names, is null. Check before use where a missing card would crash.
  • Names follow the type: BoardData.quest_steps and BoardData.quest_step("...") for QuestStep.
  • Look up by name only for named things (the boss, the starting level). Iterate for lists (all enemies, all levels).

3. Keep board and game in step

  • Tune on the card, then re-export. board.canvas {action: "update", itemId, props: {hp: 1200}}, then board.export. Never edit a generated .gd or .tres by hand or in the inspector: the next export overwrites it.
  • A field the game needs and the type lacks: add it to the type (summer-board-types section 3), fill the cards, re-export. Do not add an @export to the generated class.
  • Logic is not data. How a boss fights is a script in the game; its hp, speed and drops are the card. A card can name the behaviour as a choice (behaviour: "charger") that your code maps to a script.
  • Say what you did. After an export the game uses, board.post one line: what changed in the game ("Enemies now spawn from the 6 Character cards with role enemy").
  • Re-export when the board changes. A card update that a teammate's message names, or a task done on a card the game uses, means re-export before you test.

4. Before you say it is done

  • The project opens with no errors from res://data/.
  • Play the scene that uses the data (playtesting-a-feature): the boss has the card's hp, the level list matches the board.
  • board.query the types you used: no card has issues. A card with a missing required field exports with that field at its default, which is usually a bug in play.

From a shell

No Summer MCP tools in this session? Run each one as a command; when summer --version is missing or below 4.0, use npx -y summer-engine@latest in place of summer. Fields are flags in kebab-case (--scene-path res://main.tscn) or one --input '<json>', and summer ops describe <op> prints the exact input. The summer-cli skill has the rest.

In this skillCommand
summer_get_script_errorssummer engine get-script-errors
summer_playsummer engine play
summer_stopsummer engine stop
summer_searchsummer ops search "<what you want>"

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Summer Board To Game AI skill do?

Bring a Summer Board's typed cards into the game as Godot Resources, load them through BoardData, and keep board and game in step.

Why use Summer Board To Game on TypingMind?

Because you install it once and use it with any model. Summer Board To Game is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Summer Board To Game in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/SummerEngine/summer/tree/main/library/skills/summer-board-to-game. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Summer Board To Game?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Summer Board To Game?

As many as you like. As long as a model supports skills, you can use Summer Board To Game with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Summer Board To Game AI skill free?

Yes. It is published on GitHub by SummerEngine under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇