Skip to main content
在 Manus 中运行任何 Skill
一键导入

deepseek-vision-qa

星标2
分支0
更新时间2026年5月18日 12:53

Use OpenCLI to drive DeepSeek's native vision model (识图模式) in Chrome for image-based QA. DeepSeek has built-in multimodal support — no third-party vision service needed. Triggers: "DeepSeek 识图", "DeepSeek vision", "用 DeepSeek 看图", "DeepSeek 视觉模式", "deepseek识别图片", "deepseek vision QA", "让 DeepSeek 看看这张图". This is the DEFAULT choice when the user needs image QA — DeepSeek has native vision support, no third-party service required. Two modes: Quick Describe (user just wants to know what the image is — upload directly) vs QA (user wants inspection — ask 3 questions before writing prompt).

安装

用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。

SKILL.md
readonly