design Skill (nextlevelbuilder): Logos, Banners, Slides

Makes Claude create logos, brand identity, corporate mockups, slides, banners, icons and social images from one design skill.

Installs: 44.9K; on skills.sh
Stars: 143.8K; on GitHub
Files: 37; besides SKILL.md
Updated: Nov 2026; last repo commit

design is one skill that routes a design request to the right workflow. It has built-in workflows for logos, corporate identity mockups, slides, banners, icons and social photos, and hands brand, tokens and UI work to the brand, design-system and ui-styling skills. Logo, mockup and icon assets come from Python scripts that call an image model.

Those scripts need a Gemini API key, and the logo script can use Atlas Cloud or MuAPI keys instead. Install the whole set of sibling skills, because the skill sends brand, token, slide and style work to them.

Good for

Founders who need a logo, brand kit and pitch deck without a designer
Marketers making banners and social images for several platforms
Developers who want brand, tokens and UI styling handled together

Install design

Claude Code

Copy this prompt.

Install the design skill in Claude Code. Run this command:

npx skills add https://github.com/nextlevelbuilder/ui-ux-pro-max-skill --skill design --skill brand --skill design-system --skill ui-styling --skill ui-ux-pro-max --skill slides

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Requires Node.js.

design routes to brand, design-system and ui-styling, calls ui-ux-pro-max for style and palette help, and its slides guide invokes the slides skill. After installing, run pip install google-genai pillow and set GEMINI_API_KEY. Pick one route, not both. The plugin points at the repo's .claude/skills folder, which holds 7 skills, and its manifest lists no hooks or MCP servers. The README says plugin installs fail with a symlink error on versions before v2.5.1.

From the vendor's docs. Source.

What's in the skill

When it loads

Comprehensive design skill: brand identity, design tokens, UI styling, logo generation (55 styles, Gemini, Atlas Cloud, or MuAPI AI), corporate identity program (50 deliverables, CIP mockups), HTML presentations (Chart.js), banner design (22 styles, social/ads/web/print), icon design (15 styles, SVG, Gemini 3.1 Pro), social photos (HTML→screenshot, multi-platform). Actions: design logo, create CIP, generate mockups, build slides, design banner, generate icon, create social photos, social media images, brand identity, design system. Platforms: Facebook, Twitter, LinkedIn, YouTube, Instagram, Pinterest, TikTok, Threads, Google Ads.

Sections in SKILL.md

When to Use
Sub-skill Routing
Script Paths
Logo Design (Built-in)
Logo: Generate Design Brief
Logo: Search Styles/Colors/Industries
Logo: Generate with AI
CIP Design (Built-in)
CIP: Generate Brief
CIP: Search Domains
CIP: Generate Mockups
CIP: Render HTML Presentation
Slides (Built-in)
Slides: Knowledge Base
Banner Design (Built-in)
Banner: Workflow

Key facts

Author: claudekit, per the SKILL.md metadata. Published in the nextlevelbuilder repo
Repo: nextlevelbuilder/ui-ux-pro-max-skill
Installs on skills.sh: 44,927 (Nov 2, 2026)
GitHub stars: 143,821 (Nov 2, 2026)
License: MIT
Last commit: Nov 1, 2026
Skill version: 2.1.0
Files: 38 files including SKILL.md: 18 reference files, 8 data tables, 8 scripts plus 3 test files
Bundled sub-skills: brand, design-system, ui-styling. Related: ui-ux-pro-max. The slides workflow invokes the slides skill
Needs: Python 3, pip install google-genai pillow, and GEMINI_API_KEY (MUAPI_API_KEY optional)
skills.sh checks: Gen Agent Trust Hub pass, Socket pass, Snyk pass

What it includes

Brief, style search and AI logo generation (55+ styles, 30 palettes, 25 industries)
Runs scripts/logo/search.py and generate.py. Gemini is the default provider, and --provider atlas or muapi picks another. Logos are generated on a white background.
Runs code · Logo design
Corporate identity mockups: 50+ deliverables, 20 styles, 20 industries
scripts/cip/generate.py makes mockups with Gemini flash or pro, with or without your logo, and can build a full set. render-html.py turns the images into an HTML presentation.
Runs code · CIP mockups
SVG icons in 15 styles, single, batch or multi-size
scripts/icon/generate.py uses gemini-3.1-pro-preview to write SVG text. Options include --batch and --sizes "16,24,32,48".
Runs code · Icon design
Strategic HTML decks with Chart.js and design tokens
The creation guide tells Claude to invoke the separate slides skill, so install that too.
Write · Slides
Social, ad, web and print banners in 22 styles
Gather requirements, research, design in HTML and CSS, export PNG, present options.
Write · Banner design
HTML and CSS images exported as screenshots for each platform
Exports through Chrome headless, Playwright or Puppeteer, and uses the brand, design-system and ui-ux-pro-max skills. Reports go to plans/reports/.
Runs code · Social photos
Hands brand, tokens and UI code to brand, design-system and ui-styling
The routing guide says which sub-skill takes which task.
Sub-skill routing
Logo, then CIP mockups, then a presentation
A three-step workflow that chains the logo script, the CIP script and the slides guide.
Complete brand package

From the official docs

Permissions

Medium risk

Claude runs Python scripts that call paid image APIs with your key and write files into your project. Use a key with a spending limit, and keep other secrets out of the .env files the scripts read.

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

Prompts and your logo go to an image provider
The logo, mockup and icon scripts call Gemini by default. The mockup script loads your logo file for image editing. Avoid confidential artwork. github.com
Each image uses your API key
Generation counts against your account with the provider. Set a spending limit on the key before you batch-generate. github.com
Scripts load every line of three .env files
Each script copies all KEY=VALUE lines from the skill folder, ~/.claude/skills/.env and ~/.claude/.env into its environment. Keep only what the skill needs there. github.com
Claude is told to fix failing scripts itself
SKILL.md says: "When scripts fail, try to fix them directly." Review any script edits before you approve them. github.com

Security advisories

No published security advisories as of Nov 2, 2026.

Technical details

Turning on read-only	The search commands only look things up, but the generate scripts write files and call paid APIs.
Talks to	Google Gemini image API, the default provider. Atlas Cloud (api.atlascloud.ai) or MuAPI (api.muapi.ai), only with --provider. pip install of google-genai and pillow during setup
Sign-in and keys	API keys come from your shell environment or from KEY=VALUE lines in the .env files the scripts read.
Scopes	Runs Python scripts from the skill folder Reads .env files from the skill folder, ~/.claude/skills/ and ~/.claude/ Writes generated logos, mockups, icons and HTML into your project

Questions

How do I install the design skill?

Use the install box above. It installs design with brand, design-system, ui-styling, ui-ux-pro-max and slides, the skills it routes to. It then needs pip install google-genai pillow and a GEMINI_API_KEY before the image scripts work.

Do I need an API key, and does it cost money?

For logos, mockups and icons, yes: SKILL.md sets GEMINI_API_KEY, with an optional MUAPI_API_KEY, and the logo script also reads ATLASCLOUD_API_KEY. Each image is a call to that provider with your key, so it counts against your account there. The logo, mockup and icon scripts are the ones that call these providers.

What does it send to outside services?

The logo, mockup and icon scripts send your prompt to the provider you pick, Gemini by default. For mockups with a logo, the script loads the logo file for image editing, so that file goes to the model as well. Do not use confidential artwork unless you are comfortable with the provider's terms.

Does it work in the Claude app or Claude.ai?

The author does not document it. The README says the full repository ZIP exceeds the 200-file upload limit of Claude.ai and that the project does not publish a separate upload ZIP. The skill folder has 38 files and its scripts need a place where Claude can run Python.

Is it safe to use?

It runs Python scripts that call paid image APIs with your key and write files into your project. The scripts also read .env files from the skill folder, ~/.claude/skills and ~/.claude, so keep unrelated secrets out of those files. SKILL.md also tells Claude to try to fix a failing script directly, so read any edits it proposes.

design vs ui-ux-pro-max?

ui-ux-pro-max is the repo's main skill: a searchable database of UI styles, palettes and fonts for building interfaces. design is the creative-asset skill for logos, mockups, slides, banners and icons, and it calls ui-ux-pro-max for style and palette help.

Information

updated Nov 2, 2026

Repository: nextlevelbuilder/ui-ux-pro-max-skill
Folder: cli/assets/skills/design

nextlevelbuilder/ui-ux-pro-max-skill skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 8

ui-ux-pro-max-skill README · github.com
plugin.json · github.com
commands.md · github.com
design SKILL.md · github.com
slides-create.md · github.com
logo/generate.py · github.com
cip/generate.py · github.com
logo-design.md · github.com