pixel-diff
Pixel-level image comparison between two screenshots. Generates a visual diff overlay highlighting differences. Use for comparing Figma designs against web…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Design & creation
22,057 results
x-post
Draft brand posts and threads for X with a distinct idea, platform-fit proof, and an action matched to the post's job.
generate-z-image
Generate images using the Evolink Z-Image-Turbo API. Use when the user asks to create, generate, or produce an AI image, illustration, or artwork. Trigger…
imagemagick
Guide for using ImageMagick command-line tools to perform advanced image processing tasks including format conversion, resizing, cropping, effects,…
fuzzing
Design, implement, debug, and maintain fuzzers for security testing. Use when building coverage-guided fuzzers (LibAFL, AFL++, LibFuzzer), writing fuzz…
seedream-image-generator
Generate images using the Doubao SeeDream API based on text prompts. Use this skill when users request AI-generated images, artwork, illustrations, or visual…
sign-ai-media
Sign images and videos with C2PA provenance declaring AI-generated media, and inspect existing AI/C2PA metadata. Use when the user asks to sign, label, tag,…
in-app-asset-generator
Generate and process 2D game assets, sprites, icons, UI graphics, and custom imagery for in-app experiences. Covers prompt engineering for consistent vector…
create-design-doc
As a UX/UI designer expert, generate a full set of UI/UX design materials (design-doc.md, screen transition diagram, storyboard, HTML wireframes, PC/mobile screenshots) from idea/requirements documents. "Design the UI," "Make wireframes," "Make a screen transition diagram"...
cyber-terminal-schematic
Compile the article topic, AI/tech concepts, Agent workflow, and data judgments into "Cyber Terminal Schematic" style image-generation prompts: pure black background + single neon green phosphor, choose any one of the eight native terminal graphic families (node topology / bar ranking / time-series line / matrix grid / hierarchical stacking / timeline / giant metric / left-right comparison) as the main visual, configurable HUD…
neo-brutalist-poster
Compile an article topic, product introduction, or technical project into a Neubrutalism-style image generation prompt: thick black borders, hard offset shadows, flat clashing color blocks, oversized headline type, component-feel composition. Use when the user mentions Neubrutalism, brutalist-style cover, Neubrutalism, neo-brutalism, Gumroad style, thick black borders, hard shadows, anti-refined design, or component-feel cover. First determine the three direction…
outline-figure-explainer
Compile a concept, process, or comparison into an explainer illustration prompt in the style of "thick black outlined stick figure + flat contrasting color blocks"—pure white background, round-headed black-line figure with no facial features, saturated color blocks without outlines, white thin-line icons inside the blocks, thin black connecting lines and arrows. When the user mentions explainer illustration, concept diagram, flowchart illustration, flat illustration, stick figure illustration, white-background flat style, explainer illustration, flat vector…
travel-collage-postcard
Generate complete prompts that can be used directly for image models for city travel postcards and city collage posters. This skill should be used when the user mentions city postcards, travel collages, city visual posters, image-generation prompts, or enters a city, city + country, festival, season, or event in a visual creation context; even if the user only provides a city name, it should also be used when the context clearly indicates visual creation. It is not for travel guides, itinerary planning, or ordinary city fact Q&A.
build-design-library
Build a complete product design library from approved product scope through verified application integration.
email-design
This skill should be used when user asks to "design app emails", "theme transactional emails", "fix verification emails", "build email templates", or "review…
open-design-redesign
Redesign a live website — audit it, take its brand and its real words, photos, hours and prices, and design a new home page and up to 3 inner pages as one…
figma-raw-geometry
Raw Figma node geometry for Figma-to-code work. Use when exact local bounds, page-space bounds, transforms, rotation, visibility, or effective layer opacity…
flowchad
Drop-in AI QA — walk user flows, screenshot each step, record video, generate friction reports. Activates when working with .flowchad/ directories, flow YAML…
doc-image-agent
Automatically illustrate Markdown documents by turning image markers into screenshots or generated images, then writing an image-enriched Markdown output. Use…
design
Design workflow — create design systems, DESIGN.md, and design tokens with anti-pattern enforcement and accessibility checks
oma-db
Database specialist for SQL, NoSQL, and vector database modeling, schema design, normalization, indexing, transactions, integrity, concurrency control, backup,…
oma-design
Define or review a visual system, DESIGN.md, or redesign direction. Use for typography, layout, color, motion, and interaction design decisions.
init
Create a brand new CLAUDE.md with production-grade agent directives that override Claude Code's built-in limitations. Only use when no CLAUDE.md exists in the…
electron
Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user…