메뉴
Show vibe-check command reference and usage guide. Use when the user asks what vibe-check commands are available or how to use them.
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
Run full production readiness assessment. Use when the user wants to evaluate if their app is ready for real users — checks security, performance, accessibility, testing, monitoring, CI/CD, discoverability, analytics, reliability, legal, and platform concerns.
Review vibe-check findings and apply fixes with your approval. Use when the user wants to address issues found by /check — presents findings, suggests fixes, and only applies changes after explicit confirmation.
Re-run production readiness assessment and compare against previous results. Use when the user has fixed issues and wants to see their progress — shows before/after scores and what improved.
Run standalone codebase analysis at a conceptual level. Use when the user wants to understand their project structure, stack, conventions, and architecture without running a full assessment.
Ask questions about your vibe-check assessment results. Use when the user wants to understand findings, get clarification on recommendations, or discuss priorities from a previous /check run.
| name | help |
| description | Show vibe-check command reference and usage guide. Use when the user asks what vibe-check commands are available or how to use them. |
| user-invocable | true |
Output ONLY the reference content below. Do NOT add:
Vibe Check helps you assess production readiness and generate actionable outputs.
/check
This single command analyzes your codebase, asks a few questions, and writes a complete assessment to .vibe-check/.
/check
Full production readiness assessment. Analyzes codebase, collects inputs, and writes all results to .vibe-check/ directory including:
summary.md — Quick 1-page overviewreport.md — Full readiness report with scoresaction-plan.md — Prioritized taskschecklist/ — Individual items with fix instructionsmetadata.json — Machine-readable data/refresh
Re-runs assessment on existing .vibe-check/. Shows what improved or regressed since last check. Use after fixing issues to track progress.
/fix Auto-fix agent-doable checklist items. Each fix is verified and committed atomically.
/fix # Fix all agent-doable items
/fix item-003 # Fix a specific item
/discuss Interactive conversation about your report. Ask questions, get clarification on findings, dive deeper into specific items, or get help fixing issues.
/help Show this command reference.
/check to generate initial assessment.vibe-check/summary.md for overview/fix to auto-fix agent-doable items/discuss for items that need manual work/refresh to see progress/map-codebase Standalone codebase analysis (stack, architecture, structure, conventions, testing, integrations, concerns).
After running /check, your project will have:
.vibe-check/
├── README.md # How to use this directory
├── summary.md # Executive summary
├── report.md # Full report
├── action-plan.md # Prioritized tasks
├── checklist/
│ ├── index.md # All items overview
│ └── item-001-*.md # Individual items
└── metadata.json # Machine-readable data
Each checklist item includes:
Items marked "Agent-Doable: Yes" or "Partial" can be auto-fixed:
/fix # Fix all agent-doable items
/fix item-003 # Fix a specific item
Each fix is verified (lint, typecheck, tests) and committed atomically.
Skill invocation syntax varies by AI tool:
/skill-name (e.g., /check, /refresh, /fix)@vibe-check skill-name (e.g., @vibe-check check)The skills work identically regardless of how they're invoked.