Agent skills
Skills for AI coding agents, each with what it costs to load, how much of it is scripts and what it touches on your machine.
How to read a skill
What it costs to keep
Idle in context, in use when it runs, and up to with its linked files.
Scripts or instructions
Script-led, mixed or model-led: how much the model has to work out itself.
What it can reach
Shell, network, file writes, git and credentials, declared or detected.
Quality, security, repo health
Out of 100, each with what it is made of. Turn a card over to see them.
algorithmic-art
198,136Design And Visual Art
Anthropic's generative art skill: Claude writes an algorithmic philosophy, then builds it as a seeded p5.js sketch in an interactive HTML viewer.
brand-guidelines
198,136Design And Visual Art
Anthropic's brand skill: the official colors, Poppins and Lora typography and accent rules Claude applies to make any artifact look on-brand.
canvas-design
198,136Design And Visual Art
Anthropic's skill for posters and static art: Claude writes a design philosophy as an art movement, then expresses it as one crafted PDF or PNG canvas.
frontend-design
198,136Design And Visual Art · Developer Tools · Frontend And UI Engineering
Design guidance that pushes Claude toward distinctive, intentional UI instead of templated defaults, from palette and type to layout and copy.
slack-gif-creator
198,136Design And Visual Art
Anthropic's skill for Slack GIFs: Claude draws frames with Pillow, eases the motion and saves a size-optimized emoji or message GIF that meets Slack's limits.
theme-factory
198,136Design And Visual Art
Anthropic's theming skill: ten preset color palettes and font pairings Claude applies to slides, docs, reports and HTML pages, or a custom theme made on the spot.
Brand
152,223Design And Visual Art
Keep brand voice, visual identity and messaging in one guidelines file, then sync it to design tokens and check assets against it.
Design
152,223Design And Visual Art
One design skill for logos, corporate identity mockups, SVG icons, banners, slides and social images, routing to brand, token and UI styling skills.
Design System
152,223Design And Visual Art · Frontend And UI Engineering
Three-layer design tokens, component specs and token-compliant slide decks, with scripts that generate CSS and flag hardcoded values.
Taste Skill (design-taste-frontend)
119,418Design And Visual Art · Frontend And UI Engineering
An agent skill that builds company websites from one design system and checks each page in headless Chrome before the build ends.
image
61,763Design And Visual Art
Creates and optimizes marketing images: picks between AI generation, design tools and real screenshots, sizes graphics per platform and builds OG cards.
hallmark
58,705Design And Visual Art · Frontend And UI Engineering
A design skill by Together AI that builds new web pages from a catalog of fifty themes under a hard floor of rules, then lints the result in a real browser.
seo-image-gen
31,220Design And Visual Art
Generate OG previews, blog heroes, product photos and infographics with Gemini from Claude Code, with SEO-ready sizes, alt text and schema advice.
Huashu Design
29,971Design And Visual Art
Turns one sentence into a finished HTML design: prototypes, decks, animations, infographics and Xiaohongshu image sets, drafted as three real directions first.
Ad Image Generation
11,199Advertising And Paid Media · Design And Visual Art
Generates paid ad images from a validated creative brief and brand profile through an image provider you configure, with a manifest of what was made.
design-md
11,108Design And Visual Art
Analyzes a Stitch project's screens, HTML and theme through MCP and writes a DESIGN.md that describes the design language in semantic terms.
stitch::extract-design-md
11,108Design And Visual Art
Reads a frontend codebase's stylesheets, Tailwind config and components to write a Stitch-ready DESIGN.md without building or running the app.
stitch::generate-design
11,108Design And Visual Art
Generates Stitch screens from text or images, edits existing screens and creates design variants, with a prompt enhancement step first.
stitch::manage-design-system
11,108Design And Visual Art
Creates and updates design systems in Google Stitch from a DESIGN.md, uploads them with a script and applies them to existing screens.
taste-design
11,108Design And Visual Art
Generates a DESIGN.md for Stitch that sets premium UI rules: calibrated color, strict typography, asymmetric layouts, spring motion and banned clichés.
character-refs
6,892Design And Visual Art
Generates a set of reference images for any story character from one description: a front full-body anchor, then headshot, profile, back and detail views.
ip-as-logo
6,657Design And Visual Art
Generate extremely simple, cute, rounded mascot characters with an image model: three proposed directions, six independent candidates, two character colors on one solid background.
get-prompt-from-image
6,167Design And Visual Art
Analyze a reference image and reverse-engineer a high-fidelity positive and negative prompt, in Chinese and English, for recreating it with an image model.
gpt-image
6,167Design And Visual Art
An agent runbook for generating, editing and inpainting images with GPT Image 2, 2.5 and 2.6 through a packaged CLI, plus sprite-sheet GIFs and image-led websites.