Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

Image Prompt Director (Nano Banana & GPT Image 2.5)

Writes copy-ready image prompts with the right model, quality level, and aspect ratio for your request.

Image & VideoIntermediate★ 447⑂ 59AI score 8/10Last updated: Sep 16, 2026

What it does

  • Routes your request to the right engine: Nano Banana (NB2/NBP) or GPT Image 2.5 (Flare/Sunburst).
  • Applies model-specific syntax — a labeled 5-slot template (Scene / Subject / Important Details / Use Case / Constraints) for GPT Image, natural prose plus image grounding for Nano Banana.
  • Returns a fixed output block: Model / Quality / Size·Ratio / Prompt / Notes, ready to paste into the generator.
  • For edits, splits instructions into Change / Preserve / Constraints so only one thing moves per iteration.
  • Pulls in task-specific reference files on demand: text rendering, storyboards, slides, multi-panel grids, character continuity, de-slop (making output not look AI-made), and industry pattern libraries (e-commerce, fashion editorial, food & beverage, cinematic portraits, posters, UI/social).
  • It does not generate images itself, and it is not for video, 3D, or audio work.

Who it's for

  • Marketers and content creators who regularly need covers, ad visuals, and product shots
  • Designers building mockups, moodboards, and style references fast
  • Anyone upgrading from "tag soup" prompts to art-direction-grade briefs
  • Teams actually running Nano Banana or GPT Image 2.5

Example uses

  1. "Give me a hero product shot prompt for this insulated bottle" → pulls the e-commerce pattern and returns model, quality, 1:1 size, plus lighting, background, and material language.
  2. "Remove the background signage but keep everything else identical" → an edit prompt with an explicit Change/Preserve/Constraints block.
  3. "Here's a reference image — make a 3-panel storyboard in this style" → decomposes the style DNA, then writes a multi-panel grid prompt.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/smixs/visual-skills/HEAD/image/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the image folder from the GitHub repo smixs/visual-skills into my ~/.claude/skills/image/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/smixs/visual-skills.git && mkdir -p ~/.claude/skills && cp -r visual-skills/image ~/.claude/skills/image

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open your terminal (Terminal on macOS, PowerShell/WSL on Windows).
  2. Clone the repository: git clone https://github.com/smixs/visual-skills.git
  3. Make sure the skills folder exists: mkdir -p ~/.claude/skills
  4. Copy the skill in: cp -r visual-skills/image ~/.claude/skills/image
  5. Verify the reference files came along: ls ~/.claude/skills/image/references
  6. Restart Claude Code and try a prompt like "write me an image prompt for a blog cover" to confirm the skill triggers.
  7. The license is CC BY 4.0 — keep attribution to the author (Serge Shima) if you publish the results.
View source on GitHub ↗License: CC-BY-4.0