Skip to main content

deepseek-vision

MUST use when the user sends or asks about images, photos, screenshots, pictures, audio, video, or mixed media documents, including requests to OCR/read text from an image. Route all media through Xiaomi MiMo V2.5 (mimo-v2.5) and mimo-v2.5-asr via scripts/mimo.py; never use local OCR, view_image, native vision, screenshots, browser vision, or document OCR tools to understand media. Not global: skip unrelated text-only chats.

Jump to install

Source facts

Repository
reF0o0/deepseek-vision-skill
Last source activity
August 17, 2026 at 10:33
Detected SKILL.md language
Chinese
Stars
5
Forks
1

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.