qwen-image — Claude Code skill: what it does, how to install
qwen-image sends prompts to Alibaba Cloud DashScope API and displays generated art as markdown images. Useful for creating visuals directly within your coding agent session.
no license 122 installs ★ 51 updated 2026-02-12
npx skills add agentbay-ai/agentbay-skills --skill qwen-image -a claude-codeWhat qwen-image does
This skill triggers a Python script via uv to communicate with the qwen-image-plus and qwen-image-max model endpoints. When the generation finishes, it extracts the temporary Alibaba Cloud OSS URL from the script output and renders it in the conversation instead of saving files locally.
You can pick custom resolutions like the default 1664*928, square 1024*1024, or vertical 720*1280. It also accepts flags to avoid specific artifacts, turn off automatic prompt expansion, or bypass SSL checks behind corporate proxies. The execution fails immediately if uv is missing or no DASHSCOPE_API_KEY is supplied.
What it helps with
- produce AI artwork using English or Chinese text prompts
- render image previews directly in chat via cloud URLs
- adjust aspect ratios for horizontal banners, squares, or vertical layouts
- filter out unwanted visual artifacts with negative prompts
Example prompts for the agent
- Generate a horizontal landscape illustration of a mountain range at dawn
- Create a square image of a futuristic workspace without text or logos
- Render a 720*1280 portrait poster with classic calligraphy elements
How to install qwen-image
1Skills CLI (Vercel)
npx skills add agentbay-ai/agentbay-skills --skill qwen-image -a claude-code2Manually: put the files in place
~/.claude/skills/qwen-image/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/qwen-image/
1Skills CLI (Vercel)
npx skills add agentbay-ai/agentbay-skills --skill qwen-image -a codex2Manually: put the files in place
.agents/skills/qwen-image/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add agentbay-ai/agentbay-skills --skill qwen-image -a cursor2Manually: put the files in place
.cursor/skills/qwen-image/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install agentbay-ai/agentbay-skills qwen-image2Manually: put the files in place
.github/skills/qwen-image/SKILL.md1Skills CLI (Vercel)
npx skills add agentbay-ai/agentbay-skills --skill qwen-image -a gemini-cli2Platform CLI
gemini skills install https://github.com/agentbay-ai/agentbay-skills --path qwen-imageManually: put the files in place
.devin/skills/qwen-image/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add agentbay-ai/agentbay-skills --skill qwen-image -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about qwen-image
How to install qwen-image in Claude Code?
Run npx skills add agentbay-ai/agentbay-skills --skill qwen-image -a claude-code. The file will be written to ~/.claude/skills/qwen-image/SKILL.md.
What does the qwen-image skill do?
It connects your agent to Alibaba Cloud DashScope image generation models and outputs the resulting image as a markdown preview link.
What dependencies are required for qwen-image to work?
You need uv installed in your path, alongside a valid DashScope token configured via DASHSCOPE_API_KEY or ~/.openclaw/openclaw.json.