game design attribution audit
Audit game mechanics using Attribution Theory to diagnose unfairness, reduce player churn, and improve feedback loops.
$5
Works with the AI tools you already use
Claude Code
Cursor
Codex CLI
GitHub Copilot
Gemini CLI+20 moreClaude CodeCursorCodex CLIGitHub CopilotGemini CLI
OpenClaw
Manus
Grok+17 agentsgame design attribution audit
Example session with this skill installed
Audit the 'Frostbite' mechanic in our survival game. Players lose 20% health instantly if they stay in shadows for 5 seconds. Feedback is a small blue icon. Players are complaining it's 'random'.
- Read your context and instructions
- Compiled the game design attribution
- Generated the UI component
The audit identifies a high risk of stable, external attribution. The instant health drop combined with a subtle UI cue makes the system appear arbitrary rather than a survival challenge the player can master.
Audit Target
- Mechanic: Frostbite (Shadow-based health drain)
- Outcome: 20% instant health loss
- Player Context: Exploration in survival environment
Event Reconstruction
- Player Action: Moving through shadows, likely focused on navigation or threats.
- System Action: Timer triggers after 5 seconds of shadow contact, subtracting health.
- Feedback: A small blue icon appears on the UI.
- Gap: The punishment is binary and sudden, with no environmental "warning" state before the damage tick.
Attribution Profile
| Dimension | Likely player reading | Why |
|---|---|---|
| Locus | External | The damage feels like it "happens to" them from the system, not a result of a misplay. |
| Stability | Stable | Players think "shadows are just broken/buggy" because the trigger feels inconsistent. |
| Controllability | Low | Without clear telegraphing, players feel they can't avoid what they can't see coming. |
Likely Player Interpretation
"I was just walking and my health randomly dropped. This game is buggy and unfair."
Fairness and Learning Diagnosis
The fairness is low because the clarity does not match the severity of the punishment. A 20% health loss is a "high-stakes" event, but the "small blue icon" is low-clarity feedback. Players aren't learning the boundary of the shadow; they are just experiencing sudden loss.
Risk Assessment
High churn risk. The combination of low control and high punishment leads to learned helplessness. Players will avoid exploration to stay safe, breaking the core survival loop.
Recommendations
Add a Pre-damage State: Introduce a "shivering" screen overlay or frost effect on the camera during the 5-second window.
2. Gradient Feedback: Change the blue icon to a filling meter that pulses as it nears the 5-second limit.
3. Audio Cues: Add an audible teeth-chattering sound that increases in volume before the health tick occurs.
Minimal Fix
Add a screen-space frost vignette that intensifies over the 5 seconds spent in shadow, making the transition from "safe" to "danger" unmistakable.
Next steps
- Implement the screen vignette VFX.
- Test if players can identify the shadow boundary without looking at the UI icon.
- Monitor "unfairness" mentions in playtest logs after adding the telegraph.
game-design-attribution-audit.tsx
TSX · React component
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
What you get
About this skill
The problem
Game mechanics can be mathematically balanced yet feel "rigged" or unfair to players. When users can't trace a failure to their own actions, they stop learning, blame the system, and eventually churn.
What it does
- Evaluates player perception of causality across Locus, Stability, and Controllability dimensions.
- Diagnoses root causes of "rage-quitting" such as weak telegraphing or hidden rules.
- Reconstructs failure states from the player's perspective to identify feedback gaps.
- Provides specific design interventions to shift external blame toward internal responsibility.
Why this beats prompting it yourself
This skill applies formal Attribution Theory to game design, moving beyond vague "fun" or "difficulty" critiques. It forces the AI to ignore designer intent and focus strictly on the psychology of player frustration, ensuring you catch learned helplessness patterns that generic prompts miss.
Use cases
- Auditing high-stakes boss fights to ensure deaths feel earned rather than cheap.
- Evaluating loot drop or RNG systems to prevent players from feeling targeted by the engine.
- Reviewing onboarding tutorials where early mistakes might lead to permanent confusion.
- Analyzing competitive losses to maintain sportsmanship and minimize toxicity.
Known limitations
Does not perform mathematical balancing or simulate actual play sessions; requires a detailed description of the mechanic and feedback loop to be effective.
How to install
Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.
- 1
Download the ZIP
Free skills download straight away. Paid skills unlock right after purchase.
- 2
Unzip into your skills folder
Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.
- 3
Ask your agent to use it
Restart the agent if it was already running. It picks the skill up automatically - no config needed.
Skills folder by agent
Click the path to copy it. Create the folder if it does not exist yet.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean 12 days ago
- Passed all security checks, Safe to install