mcpField
A
alicloud-ai-multimodal-qvq

alicloud-ai-multimodal-qvq

github.com/cinienceData & databases39692 installsUpdated 11w ago
Repository

About alicloud-ai-multimodal-qvq

A skill for preparing requests to Alibaba Cloud Model Studio’s QVQ models, aimed at visual reasoning tasks. It distinguishes QVQ reasoning from standard image understanding and specifies the supported model names.

Key features

  1. 01Prepares QVQ requests
  2. 02Supports qvq-plus and qvq-max
  3. 03Targets reasoning over visual evidence

Use cases

  1. 01Reasoning through math screenshots
  2. 02Analyzing diagrams and charts
  3. 03Solving multi-step visual problems

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/cinience/alicloud-skills --skill alicloud-ai-multimodal-qvq

After installing, type/alicloud-ai-multimodal-qvqin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

agents/
openai.yaml
references/
sources.md
scripts/
prepare_qvq_request.py

Details

From the project README

Category: provider

Model Studio QVQ Visual Reasoning

Validation

mkdir -p output/alicloud-ai-multimodal-qvq
python -m py_compile skills/ai/multimodal/alicloud-ai-multimodal-qvq/scripts/prepare_qvq_request.py && echo "py_compile_ok" > output/alicloud-ai-multimodal-qvq/validate.txt

Pass criteria: command exits 0 and output/alicloud-ai-multimodal-qwen-vqv/validate.txt is generated.

Critical model names

Use one of these exact model strings:

  • qvq-plus
  • qvq-max

Typical use

  • Mathematical reasoning from screenshots
  • Diagram and chart reasoning
  • Visually grounded multi-step problem solving

Quick start

python skills/ai/multimodal/alicloud-ai-multimodal-qvq/scripts/prepare_qvq_request.py \
  --output output/alicloud-ai-multimodal-qvq/request.json

Notes

  • Use skills/ai/multimodal/alicloud-ai-multimodal-qwen-vl/ for standard image understanding.
  • Use QVQ when the task explicitly needs stronger reasoning over visual evidence.

References

  • references/sources.md

Comments

Markdown supported