$npx -y skills add cinience/alicloud-skills --skill aliyun-qvqUse when visual reasoning is needed with Alibaba Cloud Model Studio QVQ models, including step-by-step image reasoning, chart analysis, and visually grounded problem solving.
| 1 | Category: provider |
| 2 | |
| 3 | # Model Studio QVQ Visual Reasoning |
| 4 | |
| 5 | ## Validation |
| 6 | |
| 7 | ```bash |
| 8 | mkdir -p output/aliyun-qvq |
| 9 | python -m py_compile skills/ai/multimodal/aliyun-qvq/scripts/prepare_qvq_request.py && echo "py_compile_ok" > output/aliyun-qvq/validate.txt |
| 10 | ``` |
| 11 | |
| 12 | Pass criteria: command exits 0 and `output/aliyun-qvq/validate.txt` is generated. |
| 13 | |
| 14 | ## Critical model names |
| 15 | |
| 16 | Use one of these exact model strings: |
| 17 | - `qvq-plus` |
| 18 | - `qvq-max` |
| 19 | |
| 20 | ## Typical use |
| 21 | |
| 22 | - Mathematical reasoning from screenshots |
| 23 | - Diagram and chart reasoning |
| 24 | - Visually grounded multi-step problem solving |
| 25 | |
| 26 | ## Quick start |
| 27 | |
| 28 | ```bash |
| 29 | python skills/ai/multimodal/aliyun-qvq/scripts/prepare_qvq_request.py \ |
| 30 | --output output/aliyun-qvq/request.json |
| 31 | ``` |
| 32 | |
| 33 | ## Notes |
| 34 | |
| 35 | - Use `skills/ai/multimodal/aliyun-qwen-vl/` for standard image understanding. |
| 36 | - Use QVQ when the task explicitly needs stronger reasoning over visual evidence. |
| 37 | |
| 38 | ## References |
| 39 | |
| 40 | - `references/sources.md` |