portrait-clone
Turn any n reference images (with at least one person) into one exhaustively locked, always de-slopped, JSON-only AIGC image prompt whose every variable is…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-01 00:15
Design & creation
21,548 results
mistica-figma
Teaches the agent how to build Figma screens with Mistica — Telefonica's design system. Captures Mistica's library layout, component keys, text-preset scale,…
hyperframes-cli
Use the HyperFrames CLI development loop: init, add, catalog, capture, lint, check, snapshot, compare, grade-compare, preview, play, present, beats, keyframes,…
forge-polish
Designer-eye QA on a running UI — finds inconsistent spacing, weak hierarchy, generic AI-slop patterns and slow interactions, then fixes them in source with…
tushar-design
Build web interfaces with Tushar's configurable design system and interaction rules. Use when creating pages, dashboards, or components in this style.
ui-loop
Self-check iteration for page design, redesign, or visual polishing; not for read-only review, merely finding references, explaining prompts, or backend tasks. Using award-winning works as the benchmark, check and fix item by item until no visible improvement remains in any dimension.
lyt-image-to-prompt
lyt series e-commerce image prompt reverse-engineering and product replacement skill. Used when the user proactively invokes this skill and uploads a product image, product hero image, commercial advertising image, product scene image, selling point infographic, or product 3D render; based on the visible subject, composition, scene, lighting, material, color, and commercial expression in the reference image, reconstruct an executable image generation prompt; the user can also continue to upload their own product image, using their product's appearance, structure, packaging, and…
makepad-dsl
CRITICAL: Use for Makepad DSL syntax and inheritance. Triggers on: makepad dsl, live_design, makepad inheritance, makepad prototype, "<Widget>", "Foo = { }",…
makepad-shaders
CRITICAL: Use for Makepad shader system. Triggers on: makepad shader, makepad draw_bg, Sdf2d, makepad pixel, makepad glsl, makepad sdf, draw_quad, makepad…
media-use
Media processing toolkit (based on ffmpeg). Use when users need video transcoding, format conversion, compression to a specified size, adjusting resolution/frame rate, adding a logo or image watermark, setting watermark position/size/opacity, appending intro/outro, audio processing, video cropping/trimming, merging/concatenating, or repairing corrupted videos downloaded via m3u (faststart/moov atom). Supports integrated brand video generation, target...
video-downloader
Video download tool. Handles Douyin short links, Douyin post pages, WeChat Channels SPH share links, and video downloads from sites supported by yt-dlp. Trigger scenarios: - The user sends a video link and asks to "download this video" - The user asks to download a Douyin video, image post, cover, music, JSON, comments - The user asks to download from YouTube, Bilibili, X, TikTok, etc. via yt-dlp...
21st-design-sync
Look at the current project's design (its shadcn / Tailwind CSS variables and color tokens) and publish it to the 21st.dev community as a shareable theme,…
location-ar-experience
Designs location-based augmented reality experiences with geospatial anchoring, GPS integration, and real-world interactive overlays.
building-era-authentic-game-audio
Designs, implements, and validates a complete game-specific procedural audio system inspired by late-1970s to mid-1980s arcade and console hardware, including…
minimax-video
Generate MiniMax H3 videos from text and optional image, video, or audio references through AceDataCloud. Use for text-to-video, first/last-frame video,…
collage-motion
End-to-end Advibly pipeline for halftone paper-collage and stop-motion-graphic ads. Decodes a reference image into a field-editable JSON spec, generates…
infographic-generator
Generate branded infographic specifications from any content or data. Outputs structured layout, copy, data visualization, and color scheme — ready to render…
video-understand
Video understanding and transcription with intelligent multi-provider fallback. Use when: (1) Transcribing video or audio content, (2) Understanding video…
image-generation
Generate high-quality images via MCP (Gemini models or compatible services) using structured prompts, ratios, and validation for marketing, UI, or…
remotion-video-production
Produce programmable videos with Remotion using scene planning, asset orchestration, and validation gates for automated, brand-consistent video content.
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site…
architecture-designer
Use when designing new system architecture, reviewing existing designs, or making architectural decisions. Invoke for system design, architecture review,…
craft-experiment-design
Write a hypothesis, define success metrics, and plan a holdout strategy. Use when designing A/B tests or experiment plans.
changelog-collect
Collect PR information between two versions of ant-design and organize a changelog draft, used when updating CHANGELOG.zh-CN.md and CHANGELOG.en-US.md. Applicable to scenarios such as collecting changelog, generating changelog, updating changelog, and version comparison.