Game Design Design Pillars Extractor logo

Game Design Design Pillars Extractor

Community
Stanestane
game-design-design-pillars-extractor

Extract 3 to 5 actionable design pillars from a game, feature, loop, or system based on what the design actually rewards and prioritizes. Use when a team can describe mechanics but cannot clearly articulate the principles those mechanics serve, when pillars are vague, generic, or contradictory, or when you need a sharper set of tradeoff-driven pillars that can guide decisions and cut features.

Overview

PublisherStanestane
Repositorygame-design-skills-bundle
Skill namegame-design-design-pillars-extractor
Stars
87
Forks
18
Bundled files
2
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.

  • 2 bundled files

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

  • Open source

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

Installation

Install the Game Design Design Pillars Extractor 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/Stanestane/game-design-skills-bundle/tree/master/game-design-design-pillars-extractor
  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/Stanestane/game-design-skills-bundle.git /tmp/game-design-skills-bundle
mkdir -p .claude/skills
cp -r /tmp/game-design-skills-bundle/game-design-design-pillars-extractor .claude/skills/game-design-design-pillars-extractor
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Game Design Design Pillars Extractor 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 Game Design Design Pillars Extractor 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 Game Design Design Pillars Extractor 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.

Game Design Design Pillars Extractor

Extract the real pillars a design is built around, not the polite slogans attached to it.

Use this skill when a team has a pile of mechanics, references, and ambitions but no sharp articulation of what the design actually prioritizes. The goal is to reverse-engineer 3 to 5 actionable pillars from the game's systems, loops, and tradeoffs.

Good pillars are directional. They help decide what to keep, what to cut, and what kinds of changes are off-brand. Bad pillars are just nice words wearing capital letters.

Read references/family-conventions.md when you want the shared style, prioritization, and diagnosis rules for this game-design skill family. Read references/output-patterns.md when you want the preferred recommendation and minimal-fix structure.

Core principle

A meaningful design pillar does two things:

  • names what the design is trying hard to deliver
  • implies what the design is willing to sacrifice to deliver it

If a pillar does not create a constraint, it is not a pillar yet.

What to produce

Generate:

  1. Extracted pillars - 3 to 5 clear, testable pillars
  2. Support map - which systems actually reinforce each pillar
  3. Conflict map - where systems or candidate pillars push against each other
  4. Missing or weak dimensions - important priorities that are undefined, accidental, or under-supported
  5. Decision guidance - which pillars should dominate future choices

Process

1. Define the extraction target

Clarify:

  • what exact game, feature set, or loop is being analyzed
  • whether the pillars are for the whole product or a subset
  • whether you are extracting current pillars or intended pillars

Write:

  • Extraction target
  • Scope
  • Current versus intended state

2. Map the dominant design behaviors

Look at:

  • core loop
  • repeat decisions
  • reward structure
  • punishment structure
  • progression model
  • randomness profile
  • pacing
  • agency level
  • social or solo emphasis

Ask:

  • What does the design repeatedly encourage the player to do?
  • What kinds of decisions matter most?
  • What behaviors are rewarded, tolerated, or ignored?

3. Infer the implicit priorities

Ask:

  • What is this design optimizing for in practice?
  • What is it willing to make harder, slower, riskier, narrower, or less accessible in order to preserve that?
  • Which experiences seem central rather than incidental?

This is where you move from feature description to design intention.

4. Detect tradeoffs and contradictions

Look for places where:

  • one system rewards patience while another rewards speed
  • one feature pushes mastery while another floods the loop with noise
  • one layer promises freedom while another funnels players into one dominant path
  • a supposed pillar is not actually reinforced by gameplay

Do not hide contradictions. Surface them.

5. Synthesize 3 to 5 pillars

For each pillar, provide:

  • Name
  • What it means
  • What it prioritizes
  • What it sacrifices
  • Which systems support it

Prefer short, sharp names that imply a stance, such as:

  • Controlled Chaos
  • Readable Mastery
  • High-Risk Commitment
  • Expressive Preparation
  • Ruthless Momentum

Avoid vague filler such as:

  • Fun
  • Immersion
  • Engagement
  • Quality
  • Innovation

6. Identify missing or weak pillars

Ask:

  • Which important experience dimensions are currently accidental or under-defined?
  • Which design goals are talked about but not structurally supported?
  • Which player promises are present in language but absent in systems?

7. Turn the pillars into decision guidance

State:

  • which pillar should win when tradeoffs appear
  • which features do not support any pillar and should be challenged
  • which future ideas fit or violate the extracted set

Response structure

Use this structure unless the user asks for something else:

Extraction Target

  • ...

Extracted Design Pillars

  1. ...
  2. ...
  3. ...

For each pillar:

  • Meaning: ...
  • Prioritizes: ...
  • Sacrifices: ...
  • Supporting systems: ...

Conflicts and Contradictions

  • ...

Missing or Weak Pillars

  • ...

Decision Guidance

  1. ...
  2. ...
  3. ...

Fast mode

Use this quick pass when speed matters:

  • What does the design reward most consistently?
  • What is it clearly willing to sacrifice?
  • What three priorities best describe the actual game?
  • Which feature does not belong?

Usage notes

This extractor is especially useful for:

  • early concept framing
  • preproduction alignment
  • pitch cleanup
  • feature triage
  • post-prototype coherence checks
  • making design docs less hand-wavy

Common patterns to watch for:

  • teams often confuse feature lists with pillars
  • a pillar that cannot say "no" is not doing any work
  • contradictory pillars usually reflect unresolved design conflict, not healthy nuance
  • the strongest pillar should be obvious in repeated gameplay, not just in slide decks
  • if every pillar sounds universally positive, they are probably too generic to guide decisions

Working principle

Mechanics reveal priorities even when the team does not.

Use this skill to extract the principles the design is actually living by, then decide whether those principles are worth keeping.


Part of the Game Design Skills Bundle by Stanislav Stankovic. Licensed under PolyForm Noncommercial 1.0.0 — free for personal, academic and nonprofit use. Commercial use requires a licence, sold as skill packs. See https://github.com/Stanestane/game-design-skills-bundle for terms.

Required Notice: Copyright Stanislav Stankovic (https://www.stane-island.net/)

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 Game Design Design Pillars Extractor AI skill do?

Extract 3 to 5 actionable design pillars from a game, feature, loop, or system based on what the design actually rewards and prioritizes. Use when a team can describe mechanics but cannot clearly articulate the principles those mechanics serve, when pillars are vague, generic, or contradictory, or when you need a sharper set of tradeoff-driven pillars that can guide decisions and cut features.

Why use Game Design Design Pillars Extractor on TypingMind?

Because you install it once and use it with any model. Game Design Design Pillars Extractor 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 Game Design Design Pillars Extractor in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Stanestane/game-design-skills-bundle/tree/master/game-design-design-pillars-extractor. 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 Game Design Design Pillars Extractor?

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 Game Design Design Pillars Extractor?

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

Is the Game Design Design Pillars Extractor AI skill free?

It is published on GitHub by Stanestane. Check the repository for licensing terms. 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 👇