Skip to main content
Run any Skill in Manus
with one click

deepseek-vision-qa

Stars2
Forks0
UpdatedMay 18, 2026 at 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).

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

SKILL.md
readonly