feature-store-readiness
Decide whether a feature store is needed and design features to avoid training-serving skew, staleness, and reuse confusion. Use when an agent needs a…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Design & creation
22,046 results
nano-banana-image-skill
Model-aware image prompting for Nano Banana Pro and Nano Banana 2. Covers generation, editing, continuity, text-in-image, style routing, and structured JSON…
cdd-design-pillars
Measures and limits cognitive load in Jakarta EE/MicroProfile code. Use when reviewing code complexity, designing services/entities, or identifying when to…
ddd-da-massa
Practical DDD patterns for Jakarta EE web applications with cognitive load distribution. Use when designing controllers, entities, services, or evaluating…
excalidraw-diagram
This skill should be used when the user needs to create a diagram using Excalidraw — a hand-drawn style whiteboard tool. Use when the user wants a sketch-style…
obsidian-canvas
This skill should be used when the user needs to create or edit an Obsidian Canvas — a freeform visual workspace that arranges notes, cards, links, images, and…
extract-design-system
Reverse-engineer a design system from a live website (public URL or localhost). Extracts colors, typography, spacing, shadows, radii, breakpoints, and…
image-edit
Edit images with GPT Image 2 on EvoLink. Use this skill when the user wants to change a product photo, replace a background, retouch a visual, expand a canvas,…
product-demo-video
Create ecommerce product demo videos, SaaS demo videos, app promo clips, and tool walkthrough-style videos with GPT Image 2 and Seedance 2 on EvoLink. Use this…
google-image-creator
Generate images using Google AI models (Imagen 4 and Gemini). Presents top 3 model options with pricing, generates images via API, tracks token usage and…
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…
blueprint-figure
Draw static SVG diagrams for the AI engineering from scratch course, README, and handbook. Use paper panels, blueprint accent color, nine diagram types, fixed semantic colors, eight arrow types, and check readability and markup. Trigger phrases: "draw a diagram", "blueprint style diagram", "sequence diagram", "state machine diagram", "diagram for this lesson", "add a diagram to the handbook".
course-style
A shared visual and writing reference for pages, diagrams, and manuals of Learning AI Engineering from Scratch. Used for light/dark theme color tokens, font stacks, FIG_ labels, card layouts, clear technical writing rules, and accessibility and reduced-motion defaults. Trigger phrases: "course style", "blueprint colors", "course tokens", "FIG labels", "check technical copy", "course fonts", "dark theme tokens".
isometric-explainer
Build an interactive isometric machine page where each machine station corresponds to one step in a process. A pure, tested state model drives motion, readouts, and copy; the page provides controls and a verification loop. Trigger phrases: "isometric explainer", "machine explainer", "explain with a machine", "isometric interactive diagram", "explorable explainer", "show how the inside works".
motion-figure
Build charts that move or respond to the reader: in-lesson SMIL animations and slider components, interactive mechanism diagrams that show real system components and compute conclusions, and ordered-dither color-graded bands in the course palette. Trigger phrases: "animated diagram", "add a slider", "interactive diagram", "show how the system works", "make the diagram move", "dithered header", "mechanism diagram", "figure fence".
canvas-design
Generates visual art as .png or .pdf from design philosophy or from WeChat public account content. Use when the user asks for a poster, cover image, piece of…
design-qa
Universal UI quality gates — accessibility, consistency, hardening, performance, responsive checks. Pre-ship checklist. Works with any AI agent, any framework.
metronome
Guides Metronome usage-based billing integration decisions — event ingestion (single and batch, idempotency, billable metrics), contract design (rate cards,…
frevana-pins
Manage the Frevana My Pins image and video library. Use when the user wants to list, upload, save, or download media, create, rename, or delete collections, or…
minimax-h3
Generate high-definition 2K videos using MiniMax H3 (minimax/hailuo-3) via Frevana's OpenRouter video endpoint, supporting text-to-video, image-to-video (first…
veo-3.1
Generate cinematic, production-grade video with synchronized audio using Google Veo 3.1 (google/veo-3.1) via Frevana's OpenRouter video endpoint, supporting…
youtube-video
Use when the user wants YouTube video details through Frevana from a video ID, including localized video data and next-page-token pagination for related…
youtube-video-transcript
Use when the user wants a YouTube video transcript through Frevana, including transcript language, title, or transcript type selection from SerpAPI.
business-model-canvas
Design and analyze business models using the Business Model Canvas framework. Use when evaluating startups, planning new products, pivoting existing…