Game Design Attribution Audit logo

Game Design Attribution Audit

Community
Stanestane
game-design-attribution-audit

Audit a game, feature, combat scenario, progression step, failure state, onboarding beat, or reward outcome through the lens of attribution theory: how players explain success and failure. Use when evaluating whether players will blame themselves, the system, luck, or hidden rules; diagnosing perceived unfairness, learned helplessness, rage, or churn after losses; or identifying where clarity, control, and feedback are too weak for healthy learning.

Overview

PublisherStanestane
Repositorygame-design-skills-bundle
Skill namegame-design-attribution-audit
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 Attribution Audit 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-attribution-audit
  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-attribution-audit .claude/skills/game-design-attribution-audit
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Game Design Attribution Audit 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 Attribution Audit 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 Attribution Audit 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 Attribution Audit

Audit a design by asking how players will explain what just happened.

Use this skill to evaluate whether a success or failure is likely to be interpreted as deserved, learnable, and controllable, or as arbitrary, unfair, and outside the player's influence. Focus on player perception of causality, not designer intent or mechanical correctness.

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

Players do not respond only to outcomes. They respond to the story they tell themselves about why the outcome happened.

Healthy failure attribution usually feels:

  • internal enough to preserve responsibility
  • controllable enough to support improvement
  • unstable enough to preserve hope

Toxic failure attribution usually feels:

  • external
  • uncontrollable
  • stable

That combination produces reactions like "the game screwed me" or "this always happens and I can do nothing about it."

Attribution lenses

1. Locus

Ask whether the player is likely to locate the cause internally or externally.

  • Internal: "I made the wrong choice" or "I misplayed"
  • External: "the game cheated" or "the system decided against me"

2. Stability

Ask whether the player sees the cause as recurring or one-off.

  • Stable: "this is just how this game always works"
  • Unstable: "that happened this time, but next run could go differently"

3. Controllability

Ask whether the player believes they can influence the outcome in future attempts.

  • Controllable: "I can improve this"
  • Uncontrollable: "nothing I do matters"

What to produce

Generate:

  1. Attribution profile - likely player interpretation across locus, stability, and controllability
  2. Perception summary - what the player is likely to think happened
  3. Fairness diagnosis - whether the outcome feels deserved, understandable, and learnable
  4. Risk assessment - frustration, learned helplessness, toxicity, or churn risk
  5. Design actions - specific changes to improve attribution quality

Process

1. Define the audit target

Clarify:

  • what exact scenario, feature, or failure state is being audited
  • what outcome triggered the audit
  • who the relevant player is

Write:

  • Audit target
  • Outcome type
  • Player context

2. Reconstruct the event from the player's point of view

Map:

  • what the player did
  • what the system did
  • what feedback the player received
  • what information was visible versus hidden

Ask:

  • What action did the player believe they were taking?
  • What result did they expect?
  • What actually happened?
  • What evidence did the game provide about cause and effect?

3. Classify the likely attribution profile

For the observed outcome, judge:

  • Locus - internal, mixed, or external
  • Stability - stable, mixed, or unstable
  • Controllability - high, partial, or low

Use this format:

DimensionLikely player readingWhy
LocusInternal / Mixed / External...
StabilityStable / Mixed / Unstable...
ControllabilityHigh / Partial / Low...

4. Infer the likely player interpretation

Translate the attribution profile into player-facing language.

Examples:

  • "I got greedy and deserved that"
  • "That was bad luck, but I could have mitigated it"
  • "The game hid the rule and punished me"
  • "This encounter is just broken"

Prefer the exact sentence a frustrated player might actually say.

5. Diagnose why the attribution landed there

Look for root causes such as:

  • hidden mechanics
  • weak telegraphing
  • delayed or ambiguous feedback
  • inconsistent rules
  • excessive randomness
  • low agency or missing mitigation tools
  • punishment that is too severe for the level of clarity provided

6. Check compounding risk patterns

Pay special attention to combinations like:

  • low clarity + high punishment
  • high randomness + low mitigation
  • repeated failure + stable external attribution
  • weak feedback + complex systems
  • low control + high stakes

These combinations tend to create helplessness, blame, and churn faster than any one issue alone.

7. Convert the diagnosis into design changes

For each issue, specify:

  • Problem
  • Why players read it that way
  • Suggested change
  • Expected perception shift

Examples:

  • improve telegraphing -> shifts blame from system to player decision
  • expose hidden rules -> increases controllability
  • add mitigation option -> turns fatalism into recoverable error
  • reduce punishment severity -> lowers hostility during learning

Response structure

Use this structure unless the user asks for something else:

Audit Target

  • ...

Event Reconstruction

  • ...

Attribution Profile

  • Locus: ...
  • Stability: ...
  • Controllability: ...

Likely Player Interpretation

  • ...

Fairness and Learning Diagnosis

  • ...

Risk Assessment

  • ...

Recommendations

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

Minimal Fix

  • ...

Fast mode

Use this quick pass when speed matters:

  • What does the player think caused the outcome?
  • Does it feel internal or external?
  • Does it feel controllable next time?
  • Does it feel like a one-off or a permanent rule?
  • What one change would most improve perceived control or clarity?

Usage notes

This audit is especially useful for:

  • combat deaths
  • boss fights
  • failure loops
  • loot outcomes
  • economy punishments
  • onboarding mistakes
  • puzzle failures
  • competitive losses
  • high-RNG systems that may be misread as rigged

Common patterns to watch for:

  • a system can be mechanically fair and still attract external blame
  • a hard loss can feel acceptable if the cause is clear and avoidable
  • severe punishment raises the attribution bar: clarity and control must rise with it
  • repeated confusion hardens unstable frustration into stable hostility

Working principle

A good failure says, "you can learn this." A bad failure says, "the game just does that."

Use this skill when you need to understand not only what happened, but what players will believe happened.


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 Attribution Audit AI skill do?

Audit a game, feature, combat scenario, progression step, failure state, onboarding beat, or reward outcome through the lens of attribution theory: how players explain success and failure. Use when evaluating whether players will blame themselves, the system, luck, or hidden rules; diagnosing perceived unfairness, learned helplessness, rage, or churn after losses; or identifying where clarity, control, and feedback are too weak for healthy learning.

Why use Game Design Attribution Audit on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Stanestane/game-design-skills-bundle/tree/master/game-design-attribution-audit. 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 Attribution Audit?

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 Attribution Audit?

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

Is the Game Design Attribution Audit 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 👇