원클릭으로
gsp-playability-verifier
Use when verifying a game build against its quality target before claiming it is complete.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Use when verifying a game build against its quality target before claiming it is complete.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Use when auditing structure, boundaries, coupling, or state-management risks in an existing game project.
Use when auditing UI sounds, reward/failure cues, danger cues, or audio feedback layering in a game.
Use when converting game audit findings into a structured multi-axis scorecard.
Use when choosing a backend profile for a game based on capabilities, project state, and quality target.
Use when reviewing a built or in-progress game against the locked brief before claiming completion.
Use when deciding development mode, quality target, task granularity, or refactor policy for game work.
| name | gsp-playability-verifier |
| description | Use when verifying a game build against its quality target before claiming it is complete. |
Verify the build against its actual target, not a generic low bar.
Follow the gsp-orchestrator output strategy:
docs/game-studio/quality-report.md../shared/templates/quality-report.md./shared/checklists/first-playable-rubric.md./shared/checklists/polished-prototype-rubric.md./shared/checklists/playability-verifier-output-checklist.md./shared/checklists/ui-ux-hard-rules.mdfirst-playable, use ./shared/checklists/first-playable-rubric.md.polished-prototype, also use ./shared/checklists/polished-prototype-rubric.md.production-feature or live-patch, verify the requested feature set plus regression risk in touched areas.For each critical check, report:
Do not declare success merely because something runs. The verifier exists to catch “technically alive, product-wise weak” outcomes. When runtime evidence is missing, say so explicitly. In a multi-agent build flow, this skill is the default verifier stage after implementation review, not an optional final flourish.