Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
resciencelab avatar

Logo Creator

resciencelab/opc-skills

  • 2.7k installs
  • 1.2k repo stars
  • Updated July 27, 2026
  • resciencelab/opc-skills

logo-creator is an OPC skill that guides AI logo generation, user iteration, and export of cropped PNG, transparent, and SVG brand assets.

About

The logo-creator skill runs an iterative brand mark workflow using AI image generation through the companion nanobanana skill and three external APIs. Discovery gathers project name, style preference from a style guide, aspect ratio, color direction, and optional references before any generation starts, and the skill waits for user confirmation first. It batch-generates about twenty variations into a dated .skill-archive folder, opens an HTML preview template, and loops on user favorites with additional rounds until one logo is approved. Finalization crops whitespace, removes backgrounds via remove.bg, vectorizes to SVG with Recraft, and delivers PNG, cropped, transparent, and vector files with a summary table. Required keys are GEMINI_API_KEY, REMOVE_BG_API_KEY, and RECRAFT_API_KEY. Prompt patterns cover pixel art, minimalist flat, mascot, lettermark, and abstract geometric styles across ratios from square favicons to wide banners.

  • Discovery gate with style guide, ratio, and color confirmation before generation.
  • Batch generation of twenty variations via nanobanana with dated archive folders.
  • HTML preview template for side-by-side logo comparison in the browser.
  • Finalize pipeline with crop, background removal, and SVG vectorization scripts.
  • Prompt libraries for pixel, minimalist, mascot, lettermark, and abstract styles.

Logo Creator by the numbers

  • 2,669 all-time installs (skills.sh)
  • +69 installs in the week ending Jul 28, 2026 (Skillselion tracking)
  • Ranked #139 of 1,340 Generative Media skills by installs in the Skillselion catalog
  • Security screen: HIGH risk (skills.sh audit)
  • Data as of Jul 28, 2026 (Skillselion catalog sync)
At a glance

logo-creator capabilities & compatibility

Capabilities
style and ratio discovery with user confirmation · batch ai logo generation through nanobanana scri · html preview gallery for variation review · feedback driven refinement rounds with versioned · whitespace crop and background removal post proc · svg vectorization and final asset delivery table
Use cases
image generation · ui design · copywriting
Pricing
Bring your own API key
From the docs

What logo-creator says it does

Wait for user confirmation before proceeding!
SKILL.md
All generated files should be saved to the `.skill-archive` directory
SKILL.md
Generate 20 logo variations (default) using the `nanobanana` skill
SKILL.md
npx skills add https://github.com/resciencelab/opc-skills --skill logo-creator

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs2.7k
repo stars★ 1.2k
Security audit2 / 3 scanners passed
Last updatedJuly 27, 2026
Repositoryresciencelab/opc-skills ↗

How do I go from a brand name and style preference to reviewable logo variations and a final vector asset?

Create logo concepts with AI image generation, iterate on feedback, then crop, remove background, and export SVG assets.

Who is it for?

Early brand exploration when you have Gemini, remove.bg, and Recraft API keys plus the nanobanana skill installed.

Skip if: Skip for finished brand systems, manual vector refinement only, or workflows without image generation API keys.

When should I use this skill?

User wants to create a logo, icon, favicon, brand mark, mascot, emblem, or design a logo with AI.

What you get

Archived logo variations, HTML preview, and finalized PNG, cropped, transparent, and SVG deliverables in .skill-archive.

  • SVG logo files
  • Favicon and brand icon assets

By the numbers

  • Published as opc-skills version 1.0.0 with MIT license
  • Bundles command scripts under ./scripts/

Files

SKILL.mdMarkdownGitHub ↗

Logo Creator Skill

Create professional logos 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/logo-creator/<yyyy-mm-dd-summaryname>/

Example:

.skill-archive/logo-creator/2026-01-18-opc-logo/
  logo-01.png
  logo-02.png
  ...
  logo-09-cropped.png
  logo-09-nobg.png
  logo-09.svg
  preview.html

Guidelines:

  • Use current date in format yyyy-mm-dd
  • Add short summary name (project/brand name, kebab-case)
  • Create directory before generating first logo
  • Keep all variations and iterations in same folder
  • Final approved logo should be copied to user's desired location

Workflow

Step 1: Discovery & Requirements

Before generating, gather requirements from user:

Ask about: 1. Project/Brand name - What is the logo for? 2. Style preference - See references/styles.md for options:

  • Pixel art / 8-bit retro
  • Minimalist / flat design
  • 3D / isometric
  • Hand-drawn / sketch
  • Mascot / character
  • Monogram / lettermark
  • Abstract / geometric

3. Aspect ratio - Default is 1:1 (square), options:

  • 1:1 - Square (favicons, app icons)
  • 16:9 - Wide (headers, banners)
  • 4:3 - Standard
  • 2:3 - Portrait

4. Color preferences:

  • Monochrome (black & white)
  • Specific brand colors
  • Let AI decide

5. Reference images - Any existing logos or styles to reference?

Wait for user confirmation before proceeding!

Step 2: Generate Logo Variations

Generate 20 logo variations (default) using the nanobanana skill:

# Generate single logo
python3 <nanobanana_skill_dir>/scripts/generate.py "{style} logo for {brand}, {description}, {colors}" \
  --ratio 1:1 -o .skill-archive/logo-creator/<date-name>/logo-01.png

# Batch generate 20 logos
python3 <nanobanana_skill_dir>/scripts/batch_generate.py "{style} logo for {brand}, {description}, {colors}" \
  -n 20 --ratio 1:1 -d .skill-archive/logo-creator/<date-name> -p logo

Guidelines:

  • Use batch_generate.py for multiple variations (includes auto-delay)
  • Save to .skill-archive/logo-creator/<yyyy-mm-dd-summaryname>/ directory
  • Use sequential naming: logo-01.png, logo-02.png, etc.

Prompt Tips:

  • Include style keywords: "pixel art", "minimalist", "8-bit", "flat design"
  • Specify colors: "black on white", "monochrome", "blue gradient"
  • Add context: "tech startup", "food brand", "gaming company"
  • Request format: "icon", "emblem", "mascot", "lettermark"

Step 3: Create HTML Preview

Copy the preview template and open in browser:

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

Then open in default browser:

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

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

Step 4: Iterate with User

Ask user which logos they prefer:

  • "Which logos do you like? (e.g., #5, #12, #18)"
  • "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: logo-{original}-v{n}.png (e.g., logo-05-v1.png) 3. Update HTML preview 4. Repeat until user selects final logo

Step 5: Finalize Logo

Once user approves a logo, process it:

5a. Crop whitespace (make 1:1 with no margins):

python3 <skill_dir>/scripts/crop_logo.py {input.png} {output-cropped.png}

5b. Remove background:

python3 <skill_dir>/scripts/remove_bg.py {input.png} {output-nobg.png}

5c. Convert to SVG:

python3 <skill_dir>/scripts/vectorize.py {input.png} {output.svg}

Step 6: Deliver Final Assets

Present final deliverables:

## Final Logo Assets

| File | Description | Size |
|------|-------------|------|
| logo.png | Original | 1024x1024 |
| logo-cropped.png | No margins, 1:1 | ~800x800 |
| logo-nobg.png | Transparent background | ~800x800 |
| logo.svg | Vector (scalable) | ~20KB |

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

Quick Reference

Common Prompt Patterns

Pixel Art:

Pixel art {subject} logo, 8-bit retro style, black pixels on white background, {size}x{size} grid, minimalist icon

Minimalist:

Minimalist {subject} logo, flat design, clean lines, {color} on white, simple geometric shapes

Mascot:

Cute {animal/character} mascot logo, friendly expression, {style} style, {colors}, suitable for brand icon

Lettermark:

Letter "{letter}" logo, modern typography, {style} design, {colors}, clean professional look

Supported Aspect Ratios

  • 1:1 - Square (default for logos)
  • 2:3, 3:2 - Portrait/Landscape
  • 3:4, 4:3 - Standard
  • 4:5, 5:4 - Photo
  • 9:16, 16:9 - Wide
  • 21:9 - Ultra-wide

References

  • references/styles.md - Logo style guide with prompt examples
  • examples/opc-logo-creation.md - Full example conversation

Related skills

remotion-devRemotion Best PracticesGet Remotion-specific coding guidance that prevents common video rendering mistakes when creating animated React videos.442k4.1khalt-catch-fireRemotion RenderGenerate high-quality MP4 videos from React code using Remotion inside an AI coding agent.363k648halt-catch-fireAi Video GenerationTurn written prompts into short videos using AI video generation models directly from Cursor or Claude.363k648halt-catch-fireAi Avatar VideoGenerate short talking-head videos of custom AI avatars from text prompts.363k648halt-catch-fireAi Image GenerationLet their coding agent generate, iterate on, and insert high-quality images directly into web apps, marketing assets, or product features.363k648agentspace-soVideo EditIntelligently route video editing requests to the best RunComfy model without trial-and-error.357k31

How it compares

Pick logo-creator over general image skills when the deliverable must be an exported SVG logo, favicon, or brand icon rather than arbitrary raster art.

FAQ

Which API keys does logo-creator require?

GEMINI_API_KEY, REMOVE_BG_API_KEY, and RECRAFT_API_KEY, plus the nanobanana skill for Gemini image generation.

Where are generated files saved?

Under .skill-archive/logo-creator/<yyyy-mm-dd-summaryname>/ with sequential logo-NN.png names and preview.html.

How many variations are generated initially?

About twenty logo variations by default using batch_generate.py before user feedback drives refinement rounds.

Is Logo Creator safe to install?

skills.sh reports 2 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.

Generative Mediabrandingui
Browse by category
AI & AgentsFrontend & DesignBackend & DataDev ToolsAutomationTesting & ReviewSecurityMonitoring & CloudDocs & Planning
Design & frontend
Design systemsAnimation & motionAccessibility (a11y)CSS & TailwindUI designUXDesign to codeshadcn/uiLanding pagesBest design skills
Most searched skills
find-skillscavemanfrontend-designbrainstormingsystematic-debuggingstop-slopemil-design-engui-ux-pro-maxkarpathy-guidelinesweb-design-guidelinesreact-best-practicesgrill-meimprovemicrosoft-foundryagent-browser
Browse all listings
All agent skillsAll MCP serversAll marketplacesAll plugins

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.