image · smixs — Claude Code skill: image prompt guidance
Creates image prompts for Nano Banana and GPT Image 2.5, with model, quality, size, and aspect-ratio guidance.
npx skills add smixs/visual-skills --skill image -a claude-codeWhat image does
This skill writes ready-to-use prompts for images; it does not generate the images itself. It selects Nano Banana or GPT Image 2.5 and includes guidance for quality, dimensions, and framing. Use it for blog covers, posters, UI mockups, storyboards, character sheets, or work based on reference images.
Before drafting a prompt, it reads models.md, then the chosen model guide and golden-rules.md. It can load focused references for text rendering, edits, character consistency, multi-panel layouts, and style transfer. Video is the wrong route here, because the skill directs motion and image-to-video work to video.
What it helps with
- write a prompt for a blog cover
- choose an image model and output settings
- describe edits to an existing image
- create a multi-panel storyboard prompt
- turn a reference style into a text prompt
Example prompts for the agent
- Create a Nano Banana prompt for a blog cover.
- Write a GPT Image 2.5 prompt for a poster with text.
- Analyze the attached image and prepare a prompt that transfers its style.
How to install image
1Skills CLI (Vercel)
npx skills add smixs/visual-skills --skill image -a claude-code2Manually: put the files in place
~/.claude/skills/image/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/image/
1Skills CLI (Vercel)
npx skills add smixs/visual-skills --skill image -a codex2Manually: put the files in place
.agents/skills/image/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add smixs/visual-skills --skill image -a cursor2Manually: put the files in place
.cursor/skills/image/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install smixs/visual-skills image2Manually: put the files in place
.github/skills/image/SKILL.md1Skills CLI (Vercel)
npx skills add smixs/visual-skills --skill image -a gemini-cli2Platform CLI
gemini skills install https://github.com/smixs/visual-skills --path imageManually: put the files in place
.devin/skills/image/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add smixs/visual-skills --skill 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 image
How do I install image in Claude Code?
Run npx skills add smixs/visual-skills --skill image -a claude-code, then run npx skills add smixs/visual-skills --skill image -a claude-code again. The skill file is at ~/.claude/skills/image/SKILL.md.
What does the image skill do?
It prepares prompts for Nano Banana and GPT Image 2.5. Its output includes a model choice plus quality, size, and aspect-ratio recommendations.
Can image be used for video generation?
No. For clips, montage, and image-to-video tasks, the skill points to video.
Similar skills
Everything for Design →image by other authors comes first.
