SuperAPI AI DirectoryFind an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
22,049 results
Convert articles into long images, infographics, posters, covers, illustrations, and other visual artifacts. HTML/CSS screenshot is the default local approach, with optional Open Design or Codex image generation. Triggers: "generate long image", "make infographic", "turn into poster", "generate cover", "make into image", "export visual", "make infographic"
Build high-fidelity HTML prototypes, design variants, slides, animation explorations, and design reviews based on Open Design (via soia-dev-open-design-ops); requires user brand input, five-category output destinations, and reproducible verification.
Apply Emil Kowalski's craft to polished, accessible web UI: forms, controls, touch, typography, stable layout, and local polish. Route deep motion work to…
Create Excalidraw diagram JSON files that make visual arguments. Use when the user wants to visualize workflows, architectures, or concepts.
Map motion videos: use AMap (real routes, administrative boundaries, standard/satellite tile base maps) to make map animations in travel and commentary videos, outputting vertical/horizontal MP4 and GIF. Fourteen shot types: Earth dive-in positioning (zoom from the Earth to a place), Vlog "I am here" targeting lock-on + coordinate card, drop-point markers, park/scenic area/campus plot outline tracing and orbiting, route line drawing (driving/walking/cycling/GPX, vehicle follows the line, odometer rolls, …
Whiteboard hand-drawn style motion graphics video: titles and text are written out one character at a time, lines are drawn stroke by stroke like a marker, a marker follows the tip, and real photos, UI screens, and video clips are cut out like clippings and taped onto the whiteboard (only titles and annotations are hand-drawn); between scenes the camera pans horizontally across the whiteboard. Ten styles: whiteboard marker (default), blackboard chalk, watercolor, blueprint, lined notebook, kraft paper crayon, comic, corkboard, ink wash, neon. Suitable for product introductions…
Comprehensive UX design guidance covering research, information architecture, interaction patterns, and accessibility. Activates on ANY UI/UX work including…
Alibaba Cloud Bailian image generation, editing, and translation. Text-to-image: generate images from text, supports complex text rendering. Image editing: single-image editing, multi-image fusion, style transfer, object addition and removal. Image translation: translate text in images while preserving the original layout, supports 11 source languages and 14 target languages. Trigger words: generate image, AI drawing, text-to-image, image editing, retouching, change background, style transfer, multi-image fusion, image translation, picture translation. Model: qwen-i…
Create a _brand.yml file for Quarto projects that captures brand colors, typography, and identity in a structured YAML format. Use this skill whenever the user…
Transcribe audio or video locally, edit recorded footage, build animated or hybrid videos with Remotion or HyperFrames, and prepare review players or final…
Create, repair, validate, preview, and package Codex-compatible animated pet spritesheets from character art, screenshots, generated images, or visual…
Create briefs for logos, favicons, social banners, README headers, and launch visuals that stay on-brand across GitHub, X, LinkedIn, product sites, and app…
Produce finished product media and design assets from a current brief and product truth. Use for screenshots, key art, store media, campaign visuals, motion,…
Add Louise's "flower transitions" to a Tella video: grainy, retro kaleidoscope motion-graphic stingers (wavy mint/purple stripes, blue flower blooms, flower…
Node-based graphical interface for Stable Diffusion workflows. Build complex image generation pipelines by connecting nodes visually. Supports custom nodes,…
Use when auditing the image pipeline, static assets in `public/`, CMS-managed media, or image CDN transforms. Separate file-size problems from dimension…
Bevy ECS skill for 2D sprite animation. Keywords: Bevy, sprite, animation, AnimationPlayer, AnimationClip, 2D.
This skill should be used when designing the tool surface behind an agent UI — action-oriented naming, descriptions that drive correct model selection, input…
This skill should be used when designing the visual and interaction layer of an agent-rendered widget — choosing among inline card, carousel, fullscreen, and…
Use MiniMax MCP for image understanding and analysis. Trigger conditions: (1) The user requests to analyze an image, understand an image, or describe image content (2) Need to recognize objects, text, or scenes in an image (3) Use MiniMax's understand_image feature
Convert voice notes, humming, and melodic audio recordings to quantized MIDI files using ML-based pitch detection and intelligent post-processing
Evaluate meeting notes, project updates, or sprint recaps against designer consulting best practices. Use this skill whenever the user pastes meeting notes,…
Express product, service, or data architectures through layered ASCII diagrams suitable for terminals, PRs, and ADRs.
Apply a UX lens to a user-facing change: whether it serves the user's real goal and whether the path through it holds together, using the Understanding,…