Design e Frontend

Gate ② 质量门禁。README risk Q2 走 RC，Q3 串行走 R1、R2、R3；reviewer 一轮列全发现并交 x-fix 批量修复。

화면 단위 E2E 테스트 자동화. Figma/코드 기반 테스트 케이스 도출 → Playwright 코드 생성 → Forge Loop(에스컬레이션 기반 자율 실행). "E2E 돌려줘", "화면 테스트 만들어줘", "이 페이지 자동 테스트" 등의 요청에 사용.

Canvas API Connection Skill

Generate C4 Container diagrams (Simon Brown standard) as editable .drawio XML files. Use when the user asks for architecture diagrams, system diagrams, C4 diagrams, container diagrams, or wants to visualize system architecture. Also use proactively when explaining systems with 3+ components where a visual would clarify the architecture.

65 plugins that turn Claude Code into an autonomous development team. 24 agents, 34 skills, 5 hooks. Includes 12-plugin anti-hallucination suite. One-line install.

Scan frontend src directories and generate docs/components.md so Claude Code can reuse existing Vue/React components during design-to-code generation.

Detects when Claude is uncertain but presenting answers confidently. Teaches Claude to recognize and communicate uncertainty clearly instead of masking it with confident language.

Multi-angle review of responses before delivery. Audits from 4 perspectives -- factual accuracy, logical consistency, completeness, and safety. Use for high-stakes responses where errors have real consequences.

65 plugins that turn Claude Code into an autonomous development team. 24 agents, 34 skills, 5 hooks. Includes 12-plugin anti-hallucination suite. One-line install.

Memory Sync Skill

Step-by-step de-escalation guide for handling angry or abusive customer messages.

软件正确性调查 skill。用于用户说“XX 不太对”“这个功能有 bug”“结果和预期不一致”“帮我查原因”，也用于用户要求 review 某个模块、文件、diff 或 PR 的正确性。遇到已知异常或模块 correctness review 时必须优先使用本 skill。 本 skill 使用贝叶斯根因调查：先列候选原因 H，再按日志、代码路径、测试、diff、spec 等证据 E 更新置信度，最后判断根因属于原始 spec 不一致、实现过程偏移、spec 缺口、环境/数据问题或证据不足。 x-cr 独立于 x-verify / x-qa-gate 自动门禁，产出 `reports/cr/cr-report-*.md`，x-fix 可按该 CR 报告继续修复。