5 results
Use when designing, reviewing, repairing, or implementing commercial UI/UX/GUI for product screens, dashboards, admin panels, SaaS tools, mobile apps, forms, tables, workflow states, design systems, or no-brand visual strategy.
Scan agent skill packages for static security risks. Use for skill audit, security check, prompt-injection review, suspicious scripts, unsafe dependencies, zip package review, and pre-install skill review. Not for runtime monitoring.
Trigger only when the user explicitly invokes $dsh-deliver or clearly asks to hand implementation to DSH. Do not trigger for ordinary implementation, read-only review, commit/push/MR/deploy, or image-only tasks.
DSH 装备升级套件：token 费用面板（dsh-cost）、会话文件预览（dsh-plugin-file-preview）、外网搜集（dsh-research-mcp，工具名 mcp__research__*）、视觉桥接（vision-bridge，给无视觉模型看图）、微信双向通道（dsh-wechat-bridge，微信发消息→本机执行→回微信）。已安装时，用户问"花了多少钱/预览这个文件/搜一下外网/看这张图"直接按对应组件办事；未安装时给出 install.sh 一键安装命令。
多模型候选评审管线:调度智谱 GLM / Claude(CLI 无头,可走中转)/ Gemini(OpenAI 兼容口)/ Codex 四视角评审成长 artifact(教训/规则/审计板),输出严格 JSON(verdict/strengths/risks/suggestions/cannot_claim),结果只作 candidate_review_input,永不替代本地证据。适用:用户要求外部交叉评审、周期性仪式前自动评审、怀疑某条结论过度推广时。