jimeng-api-image-gen — Claude Code skill: image generation
This skill creates images through the Volcengine Jimeng API 4.0 from text or source images. Use it when an agent needs generated artwork inside a project.
npx skills add wvlvik/toy-skills --skill jimeng-api-image-gen -a claude-codeWhat jimeng-api-image-gen does
The skill runs scripts/generate_image.py and sends the request to Volcengine Jimeng API 4.0. It covers text-to-image, edits based on image URLs, and batch creation. You can choose 1K, 2K, or 4K, pass exact --width and --height values, add a watermark, or request the raw JSON response.
Generation uses an asynchronous API task. The script checks the task result, then exposes the PNG URL and can download the file with --output. Image-to-image input accepts JPEG or PNG URLs, with up to 10 files at 15MB per file. Result URLs remain valid for 24 hours.
Set VOLC_ACCESSKEY and VOLC_SECRETKEY before running the script. Without both variables, the request will fail. Text prompts have an 800-character limit, and output dimensions must stay between 1024×1024 and 4096×4096.
What it helps with
- create an image from a text prompt
- edit a source image by URL
- produce several images from one request
- download the generated PNG to a file
- set an exact output width and height
Example prompts for the agent
- Generate a white Siamese cat on a windowsill and show the resulting image to me.
- Turn the image at this URL into a watercolor-style scene using
--images. - Create a sunset mountain landscape at
2Kand save it with--output /generated_images/mountain.png.
How to install jimeng-api-image-gen
1Skills CLI (Vercel)
npx skills add wvlvik/toy-skills --skill jimeng-api-image-gen -a claude-code2Manually: put the files in place
~/.claude/skills/jimeng-api-image-gen/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/jimeng-api-image-gen/
1Skills CLI (Vercel)
npx skills add wvlvik/toy-skills --skill jimeng-api-image-gen -a codex2Manually: put the files in place
.agents/skills/jimeng-api-image-gen/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add wvlvik/toy-skills --skill jimeng-api-image-gen -a cursor2Manually: put the files in place
.cursor/skills/jimeng-api-image-gen/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install wvlvik/toy-skills jimeng-api-image-gen2Manually: put the files in place
.github/skills/jimeng-api-image-gen/SKILL.md1Skills CLI (Vercel)
npx skills add wvlvik/toy-skills --skill jimeng-api-image-gen -a gemini-cli2Platform CLI
gemini skills install https://github.com/wvlvik/toy-skills --path skills/jimeng-api-image-genManually: put the files in place
.devin/skills/jimeng-api-image-gen/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add wvlvik/toy-skills --skill jimeng-api-image-gen -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 jimeng-api-image-gen
How do I install jimeng-api-image-gen in Claude Code?
Run npx skills add wvlvik/toy-skills --skill jimeng-api-image-gen -a claude-code, then check ~/.claude/skills/jimeng-api-image-gen/SKILL.md.
What does jimeng-api-image-gen do?
This skill sends text prompts or source images to Volcengine Jimeng API 4.0 for image creation and editing. It can also download the result and expose generation details.
What is required before using the Jimeng API?
Set VOLC_ACCESSKEY and VOLC_SECRETKEY. Image-to-image requests use JPEG or PNG inputs, with up to 10 files and a 15MB limit per file.
