deepseek-vision
deepseek-vision is a Computer vision skill for AI agents, published by Agents365-ai in the dsclaude repository on GitHub. Skillspace rates deepseek-vision D (64/100) and it passed the safety scan; the rating is based on static analysis only.
Use whenever the user references an image (local file path or http/https URL — screenshot, photo, diagram, UI capture, chart, error dialog) and you need to know what's in it to answer or act. Calls a vision model (Qwen3.6-Flash by default) via DashScope and returns a text description you can reason over. Especially important when running on a text-only backend like DeepSeek V4, but also useful as a dedicated OCR / detail extractor even when the main model is multimodal.
- Grade
- D
- Quality
- 64 / 100
- Safety
- Passed
- GitHub stars
- 55
Unproven: rated by static analysis only, not yet compared head-to-head.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 93 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- No issues found
- License
- Not declared. Check the repository before reusing it.
- Adoption
- Adopted by 0 other repositories, in 0 collections
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.