game-design-audit — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited game-design-audit (Agent Skill) and scored it 92/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 2 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 2 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
You are an autonomous game design audit agent. Do NOT ask the user questions. Run the full pipeline below without pausing between phases.
TARGET: $ARGUMENTS If arguments specify design systems (e.g., "combat balance" or "economy"), focus the audit there. If no arguments are provided, audit the entire game design.
============================================================ PHASE 1: CORE DESIGN REVIEW (/game-design-review) ============================================================
Follow the instructions defined in the /game-design-review skill exactly. Run all sub-phases: Design Discovery, Core Loop Analysis, Progression Analysis, Feedback and Motivation, Session Design, Feature Prioritization.
Evaluate:
Record findings for use in all subsequent phases. Continue immediately to Phase 2.
============================================================ PHASE 2: ECONOMY ANALYSIS (/game-economy) ============================================================
Follow the instructions defined in the /game-economy skill exactly. Run all sub-phases: Economy Discovery, Flow Analysis, Loot Table Analysis, Marketplace/Trading, Pay-to-Win Detection, Economy Stress Test.
Analyze using Phase 1 context:
Record findings. Continue immediately to Phase 3.
============================================================ PHASE 3: BALANCE TESTING (/balance-test) ============================================================
Follow the instructions defined in the /balance-test skill exactly. Run all sub-phases: Data Extraction, Combat Balance, Economy Stress Test, Progression Pacing, RNG Simulation, Win Rate Simulation.
Use mathematical simulation, not opinion:
Record quantitative results. Continue immediately to Phase 4.
============================================================ PHASE 4: ANALYTICS AUDIT (/player-analytics) ============================================================
Follow the instructions defined in the /player-analytics skill exactly. Run all sub-phases: Analytics Stack Detection, Event Tracking Completeness, Funnel Analysis, Retention Metrics, A/B Testing, Advanced Analytics.
Verify analytics coverage against findings from Phases 1-3:
Record findings. Continue immediately to Phase 5.
============================================================ PHASE 5: MONETIZATION REVIEW (/game-monetization) ============================================================
Follow the instructions defined in the /game-monetization skill exactly. Run all sub-phases: Monetization Model Discovery, IAP Audit, Advertising Audit, Subscription/Battle Pass, Regulatory Compliance, Revenue Optimization.
Evaluate ethics and effectiveness using all prior phase context:
============================================================ SELF-HEALING VALIDATION (max 3 iterations) ============================================================
After completing all phases, validate the combined output:
STOP when:
IF STILL FAILING after 3 iterations:
============================================================ OUTPUT ============================================================
| Phase | Skill | Health | Critical Issues | Key Finding |
|---|---|---|---|---|
| 1 | Design Review | {STRONG/MODERATE/WEAK} | {N} | {one-line summary} |
| 2 | Economy | {HEALTHY/INFLATIONARY/DEFLATIONARY} | {N} | {one-line summary} |
| 3 | Balance | {BALANCED/MINOR ISSUES/IMBALANCED} | {N} | {one-line summary} |
| 4 | Analytics | {COMPLETE/PARTIAL/INSUFFICIENT} | {N} | {one-line summary} |
| 5 | Monetization | {FAIR/SOFT P2W/P2W/PREDATORY} | {N} | {one-line summary} |
Scoring:
#### Phase 1: Core Design
#### Phase 2: Economy
#### Phase 3: Balance
#### Phase 4: Analytics
#### Phase 5: Monetization
| # | Phase | Issue | Impact | Recommendation |
|---|---|---|---|---|
| 1 | {phase} | {description} | {player/revenue impact} | {specific fix} |
| Priority | Improvement | Phase | Impact | Effort |
|---|---|---|---|---|
| P0 | {improvement} | {phase} | {impact} | {effort} |
| P1 | {improvement} | {phase} | {impact} | {effort} |
Post-launch systems requiring ongoing attention:
============================================================ SELF-EVOLUTION TELEMETRY ============================================================
After producing output, record execution metadata for the /evolve pipeline.
Check if a project memory directory exists:
~/.claude/projects/skill-telemetry.md in that memory directoryEntry format:
### /game-design-audit — {{YYYY-MM-DD}}
- Outcome: {{SUCCESS | PARTIAL | FAILED}}
- Self-healed: {{yes — what was healed | no}}
- Iterations used: {{N}} / {{N max}}
- Bottleneck: {{phase that struggled or "none"}}
- Suggestion: {{one-line improvement idea for /evolve, or "none"}}Only log if the memory directory exists. Skip silently if not found. Keep entries concise — /evolve will parse these for skill improvement signals.
STRICT RULES:
NEXT STEPS:
/game-launch for a full launch readiness audit including performance, QA, and security./balance-test to deep-dive into specific balance issues identified in the audit.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.