Game Design One Page Design Doc logo

Game Design One Page Design Doc

Community
Stanestane
game-design-one-page-design-doc

Create a concise one-page game design document and export it as both markdown and PDF. Use when a user wants a one-page design doc, one-pager, pitchable design summary, or compact game concept sheet that captures identity, pillars, summary, features, interface, aesthetic direction, sound, audience, platform, and milestone plan on a single page.

Overview

PublisherStanestane
Repositorygame-design-skills-bundle
Skill namegame-design-one-page-design-doc
Stars
87
Forks
18
Bundled files
4
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.

  • 4 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 One Page Design Doc 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-one-page-design-doc
  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-one-page-design-doc .claude/skills/game-design-one-page-design-doc
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Game Design One Page Design Doc 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 One Page Design Doc 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 One Page Design Doc 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 One-Page Design Doc

Create a one-page game design document that is readable, decision-useful, and visually polished — exportable as a PDF that looks like a real product.

Use this skill when the user wants a compact game design summary rather than a bloated GDD. The output is designed to be passed around in meetings, dropped in Slack, or emailed to publishers without embarrassment.

Read references/family-conventions.md when you want the shared style and prioritization rules for this game-design skill family. Read references/source-notes.md when you want the distilled takeaways from the reference template and the GDC talk overview.

Core principle

A one-page design doc is not a small bad GDD. It is a compressed communication tool.

It should:

  • state what the game is
  • state why it is interesting
  • state what feeling or fantasy it is chasing
  • state the core features and interaction model
  • state enough production framing to make it actionable

It should not:

  • try to explain every subsystem
  • drown the reader in lore
  • use vague slogans instead of specifics
  • hide the real game behind marketing fluff

What to produce

Produce:

  1. One-page PDF — the shareable, visually designed version
  2. One-page markdown doc — the editable text version
  3. Structured source JSON — the intermediate data used for rendering

Visual design

The PDF renderer (scripts/render_one_page_gdd.py) produces a professional dark-theme layout:

  • Dark background — near-black navy #0F111A, with a lighter panel for the header
  • Teal accent colour — #00C8A0 for rules, section headings, pillar tag nubs, and bullet markers
  • Pillar tags — design pillars rendered as pill-shaped labels with a teal left accent in the header
  • Two-column body — left column for mechanics-heavy content, right column for production/aesthetic content
  • Section rules — a teal horizontal rule above each section label
  • Poppins typeface — used when available (falls back to Liberation Sans or DejaVu)
  • Branded footer — document label on the left, game title on the right

The renderer uses ReportLab (vector PDF — real text, not a raster image), making the output searchable, copy-pasteable, and print-sharp.

Font requirements

The renderer searches for fonts in standard system locations automatically:

  • Linux: /usr/share/fonts/truetype/google-fonts/, /usr/share/fonts/truetype/liberation/
  • macOS: ~/Library/Fonts/, /Library/Fonts/
  • Windows: C:/Windows/Fonts/

Preferred: Poppins (Bold, Medium, Regular, Light) from fonts.google.com
Fallback: Liberation Sans (included in most Linux systems)

Dependencies

bash
pip install reportlab

Default section structure

Left column:

  • Genre / Story / Mechanics Summary
  • Key Features
  • Interface & Controls

Right column:

  • Art Style
  • Music & Sound
  • Roadmap / Launch Criteria (includes platform, audience, milestones, launch date)

Header band:

  • Game title
  • Identity / Mantra (subtitle)
  • Design Pillars (as pill tags)

Process

1. Clarify the design input

Collect or infer the minimum needed:

  • game title or working title
  • game identity / mantra
  • 2 to 3 design pillars
  • concise gameplay/story/mechanics summary
  • 3 to 6 key features
  • input / interface model
  • art references or aesthetic direction
  • sound direction or emotional audio goals
  • platform
  • target audience
  • milestone plan or launch criteria

If the user gives messy notes, compress them rather than asking endless questions.

2. Write for one-page density

Keep each section tight.

Guidelines:

  • prefer short bullets over dense paragraphs
  • keep pillars punchy (2–4 words each)
  • keep the summary to a compact paragraph
  • keep features to the strongest few, not every idea
  • make roadmap milestones concrete enough to be useful
  • write like the doc will be skimmed in under two minutes

3. Preserve design clarity over style fluff

If the concept is fuzzy:

  • choose clarity over hype
  • expose contradictions instead of smoothing them over
  • keep claims grounded in actual mechanics or fantasy

4. Build the structured source JSON

Write a JSON file matching the renderer schema.

Expected fields:

  • title
  • identity_mantra
  • design_pillars (array, 2–4 items)
  • summary
  • features (array, 3–6 items)
  • interface
  • art_style
  • music_sound
  • platform
  • audience
  • milestones (array)
  • launch_day

See references/example-input.json for a worked example.

5. Render markdown and PDF

bash
# Install dependency first if needed:
pip install reportlab

# Render:
python scripts/render_one_page_gdd.py --input <slug>.json --md <slug>.md --pdf <slug>.pdf

The renderer auto-discovers fonts. If content is too long, shorten the copy before rerendering — do not try to fit more by cramming.

6. Check fit and trim aggressively

Before finalizing, verify:

  • the concept is legible at a glance
  • the features list is not overstuffed
  • the PDF still feels like a one-pager (not wall-to-wall text)
  • the roadmap is realistic enough to be useful
  • the strongest idea is visible immediately

If the PDF looks crowded, shorten the writing. If there is too much whitespace, the document is probably well-scoped — do not pad it.

Output expectations

By default, create files in the current working directory or a user-specified target folder:

  • <slug>.json
  • <slug>.md
  • <slug>.pdf

Use a slug based on the game title when naming files.

Response structure

When using this skill, report:

  • where the JSON, markdown, and PDF files were written
  • any sections that had to be compressed heavily
  • any major ambiguities or contradictions you preserved or surfaced

References

Read these when useful:

  • references/source-notes.md for the distilled source principles and section model
  • references/example-input.json for renderer input shape and field conventions

Working principle

If a team cannot explain the game on one page, the design is probably not clear enough yet.

Use this skill to produce a one-pager people can actually read, discuss, and pass around.


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 One Page Design Doc AI skill do?

Create a concise one-page game design document and export it as both markdown and PDF. Use when a user wants a one-page design doc, one-pager, pitchable design summary, or compact game concept sheet that captures identity, pillars, summary, features, interface, aesthetic direction, sound, audience, platform, and milestone plan on a single page.

Why use Game Design One Page Design Doc on TypingMind?

Because you install it once and use it with any model. Game Design One Page Design Doc 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 One Page Design Doc in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Stanestane/game-design-skills-bundle/tree/master/game-design-one-page-design-doc. 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 One Page Design Doc?

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 One Page Design Doc?

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

Is the Game Design One Page Design Doc 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 👇