Qwencloud Vision

This lets Claude analyze images and videos using Qwen's vision models through QwenCloud's API. It handles OCR, multi-image comparison, screenshot understanding, chart reading, and video comprehension. The skill comes with three Python scripts: analyze.py for general vision tasks, reason.py for chain-of-thought visual reasoning with QVQ models, and ocr.py for text extraction. The default model is qwen3.6-plus, though you can swap in specialized ones like qwen3-vl-plus for precise object localization or qvq-max for mathematical reasoning over visual data. Everything runs locally with just Python 3.9 and your QwenCloud API key. The documentation is thorough about model selection and includes curl fallbacks if you need them.

skills.sh installs: 1.9K
GitHub stars: 44
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add qwencloud/qwencloud-ai --skill qwencloud-vision --agent claude-code

Installs into .claude/skills of the current project.

Files

Qwen Vision (Image & Video Understanding)

Analyze images and videos using Qwen VL and QVQ models. This skill is part of qwencloud/qwencloud-ai.

Skill directory

Use this skill's internal files to execute and learn. Load reference files on demand when the default path fails or you need details.

Location	Purpose
`scripts/analyze.py`	Image/video understanding, multi-image, thinking mode
`scripts/reason.py`	Visual reasoning (QVQ, chain-of-thought, streaming)
`scripts/ocr.py`	OCR text extraction
`scripts/vision_lib.py`	Shared helpers (base64, upload, streaming)
`references/execution-guide.md`	Fallback: curl, code generation
`references/curl-examples.md`	Curl for base64, multi-image, video, OCR
`references/visual-reasoning.md`	QVQ and thinking mode details
`references/prompt-guide.md`	Query prompt templates by task, thinking mode decision
`references/ocr.md`	OCR parameters and examples
`references/sources.md`	Official documentation URLs