game-launch — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited game-launch (Agent Skill) and scored it 96/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 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.
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 launch readiness agent. Do NOT ask the user questions. Run the full pipeline below without pausing between phases.
TARGET: $ARGUMENTS If arguments specify platforms or areas (e.g., "Steam + Xbox" or "mobile performance focus"), scope the audit accordingly. If no arguments, audit the entire project for all target platforms.
============================================================ PHASE 1: PERFORMANCE AUDIT (/game-performance) ============================================================
Follow the instructions defined in the /game-performance skill exactly. Run all sub-phases: Engine Detection, Rendering Performance, Memory/GC, Physics/Update, Loading/Streaming, Platform-Specific Concerns.
Evaluate against platform budgets:
Record performance findings and whether they are launch-blocking. Continue immediately to Phase 2.
============================================================ PHASE 2: QA VERIFICATION (/game-qa) ============================================================
Follow the instructions defined in the /game-qa skill exactly. Run all sub-phases: Project Detection, Null Reference Detection, Boundary Testing, Input Validation, Save/Load Integrity, Localization, Audio, Platform Compliance.
Focus on launch-blocking defects:
Record QA findings with severity classification. Continue immediately to Phase 3.
============================================================ PHASE 3: ACCESSIBILITY REVIEW (/game-accessibility) ============================================================
Follow the instructions defined in the /game-accessibility skill exactly. Run all sub-phases: Platform Detection, Visual Accessibility, Audio Accessibility, Motor Accessibility, Cognitive Accessibility, Communication (CVAA), Settings.
Evaluate compliance and access barriers:
Record accessibility findings and compliance status. Continue immediately to Phase 4.
============================================================ PHASE 4: SECURITY AUDIT (/game-security) ============================================================
Follow the instructions defined in the /game-security skill exactly. Run all sub-phases: Attack Surface Mapping, Client Authority, Memory Manipulation, Network Security, Save Tampering, API Security, Anti-Cheat Architecture.
Focus on exploitable vectors:
Record security findings with risk scores. Continue immediately to Phase 5.
============================================================ PHASE 5: UX AUDIT (/game-ux) ============================================================
Follow the instructions defined in the /game-ux skill exactly. Run all sub-phases: UI Discovery, HUD Clarity, Menu Navigation, Tutorial/Onboarding, Control Feel, Camera System, Loading/Transitions.
Evaluate player-facing quality:
============================================================ 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 | Status | Critical Issues | Blocking? |
|---|---|---|---|---|
| 1 | Performance | {PASS/CONDITIONAL/FAIL} | {N} | {Yes/No} |
| 2 | QA | {PASS/CONDITIONAL/FAIL} | {N} | {Yes/No} |
| 3 | Accessibility | {PASS/CONDITIONAL/FAIL} | {N} | {Yes/No} |
| 4 | Security | {PASS/CONDITIONAL/FAIL} | {N} | {Yes/No} |
| 5 | UX | {PASS/CONDITIONAL/FAIL} | {N} | {Yes/No} |
GO: No critical issues. Ship with confidence. CONDITIONAL GO: Minor issues exist but none are launch-blocking. Ship with known issues documented. NO GO: Critical issues that must be resolved before launch.
| # | Phase | Issue | Severity | Effort to Fix |
|---|---|---|---|---|
| 1 | {phase} | {description} | CRITICAL | {hours/days} |
| # | Phase | Issue | Severity | Priority |
|---|---|---|---|---|
| 1 | {phase} | {description} | {MEDIUM/LOW} | {P2/P3} |
#### Performance
#### QA
#### Accessibility
#### Security
#### UX
| Priority | Issue | Phase | Estimated Effort |
|---|---|---|---|
| P1 | {issue} | {phase} | {effort} |
| P2 | {issue} | {phase} | {effort} |
============================================================ 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-launch — {{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-design-audit for a comprehensive design health assessment./game-performance to deep-dive into specific performance bottlenecks.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.