Banner Creator logo

Banner Creator

OrganizationPopular
ReScienceLab
banner-creator

Create banners using AI image generation. Discuss format/style, generate variations, iterate with user feedback, crop to target ratio. Use when user wants to create a banner, header, hero image, cover image, GitHub banner, Twitter header, or readme banner.

Overview

PublisherReScienceLab
Repositoryopc-skills
Skill namebanner-creator
Stars
1.8K
Forks
165
Bundled files
14
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 14 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by ReScienceLab on GitHub. Read the source before you install it.

Installation

Install the Banner Creator AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/ReScienceLab/opc-skills.git /tmp/opc-skills
mkdir -p .claude/skills
cp -r /tmp/opc-skills/skills/banner-creator .claude/skills/banner-creator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Banner Creator in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Banner Creator on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Banner Creator is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Banner Creator Skill

Create professional banners through AI image generation with an iterative design process.

Prerequisites

Required API Keys (set in environment):

Required Skills:

  • nanobanana - AI image generation (Gemini 3 Pro Image)

File Output Location

All generated files should be saved to the .skill-archive directory:

.skill-archive/banner-creator/<yyyy-mm-dd-summaryname>/

Example:

.skill-archive/banner-creator/2026-01-19-opc-banner/
  banner-01.png
  banner-02.png
  ...
  banner-03-cropped.png
  preview.html

Workflow

Step 1: Discovery & Requirements

Before generating, gather requirements from user:

Ask about:

  1. Purpose - Where will the banner be used?

    • GitHub README
    • Twitter/X header
    • LinkedIn banner
    • Website hero
    • YouTube channel art
  2. Target ratio/size - See references/formats.md:

    • 2:1 (1280x640) - GitHub README
    • 3:1 (1500x500) - Twitter header
    • 16:9 (1920x1080) - Website hero
  3. Style preference:

    • Match existing logo/brand?
    • Pixel art / 8-bit retro
    • Minimalist / flat design
    • Gradient / modern
    • Illustrated / artistic
  4. Content elements:

    • Brand name / project name?
    • Tagline / slogan?
    • Logo character to include?
  5. Color preferences:

    • Existing brand colors?
    • Let AI decide?

Wait for user confirmation before proceeding!

Step 2: Generate Banner Variations

Generate 20 banner variations using the nanobanana skill:

bash
# Generate single banner
python3 <nanobanana_skill_dir>/scripts/generate.py "{style} banner for {brand}, {description}, {text elements}" \
  --ratio 21:9 -o .skill-archive/banner-creator/<date-name>/banner-01.png

# Batch generate 20 banners
python3 <nanobanana_skill_dir>/scripts/batch_generate.py "{style} banner for {brand}, {description}, {text elements}" \
  -n 20 --ratio 21:9 -d .skill-archive/banner-creator/<date-name> -p banner

Guidelines:

  • Generate at 21:9 ratio (widest available), crop later to target
  • Use batch_generate.py for multiple variations (includes auto-delay)
  • Use sequential naming: banner-01.png, banner-02.png, etc.

Image Editing (for incorporating existing logo):

bash
python3 <nanobanana_skill_dir>/scripts/generate.py "add {logo character} to the left side of the banner" \
  -i /path/to/existing-logo.png --ratio 21:9 -o banner-with-logo.png

Step 3: Create HTML Preview

Copy the preview template and open in browser:

bash
cp <skill_dir>/templates/preview.html .skill-archive/banner-creator/<yyyy-mm-dd-summaryname>/preview.html

Then open in default browser:

bash
open .skill-archive/banner-creator/<yyyy-mm-dd-summaryname>/preview.html

IMPORTANT: Update the HTML to include the correct number of banners generated.

Step 4: Iterate with User

Ask user which banners they prefer:

  • "Which banners do you like? (e.g., #3, #7, #15)"
  • "What do you like about them?"
  • "Any changes you'd want?"

Based on feedback:

  1. Generate 10-20 more variations of favorite styles
  2. Use naming: banner-{original}-v{n}.png (e.g., banner-03-v1.png)
  3. Update HTML preview
  4. Repeat until user selects final banner

Step 5: Crop to Target Ratio

Once user approves a banner, crop to target size:

bash
python3 <skill_dir>/scripts/crop_banner.py {input.png} {output.png} --ratio 2:1 --width 1280

Common targets:

  • GitHub README: --ratio 2:1 --width 1280 → 1280x640
  • Twitter header: --ratio 3:1 --width 1500 → 1500x500
  • Website hero: --ratio 16:9 --width 1920 → 1920x1080

Step 6: Deliver Final Assets

Present final deliverables:

## Final Banner Assets

| File | Description | Size |
|------|-------------|------|
| banner-03.png | Original (21:9) | 2016x864 |
| banner-03-cropped.png | GitHub README (2:1) | 1280x640 |

All files saved to: `.skill-archive/banner-creator/<yyyy-mm-dd-summaryname>/`
Copy final banner to user's desired location.

Quick Reference

Common Prompt Patterns

With Text:

Wide banner for {brand}, {style} style, featuring "{text}" prominently displayed, {colors}, {scene/elements}

With Character:

Wide banner featuring {character description}, {style} style, {scene}, text "{brand name}" on {position}, {colors}

Abstract/Gradient:

Abstract {style} banner, {colors} gradient, geometric patterns, modern tech feel, text "{brand}" centered

Scene-based:

{Style} illustration banner, {scene description}, {character} in {action}, "{brand}" text overlay, {colors}

Supported Aspect Ratios

Generate at widest ratio, then crop:

  • 21:9 - Ultra-wide (recommended for generation)
  • 16:9 - Wide
  • 3:2 - Standard wide

References

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Banner Creator AI skill do?

Create banners using AI image generation. Discuss format/style, generate variations, iterate with user feedback, crop to target ratio. Use when user wants to create a banner, header, hero image, cover image, GitHub banner, Twitter header, or readme banner.

Why use Banner Creator on TypingMind?

Because you install it once and use it with any model. Banner Creator is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Banner Creator in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ReScienceLab/opc-skills/tree/main/skills/banner-creator. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Banner Creator?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Banner Creator?

As many as you like. As long as a model supports skills, you can use Banner Creator with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Banner Creator AI skill free?

Yes. It is published on GitHub by ReScienceLab under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇