3.7K skills · sorted by relevance
Create sparse vertical posters from themes, articles, or photos, using paper textures, generous empty space, experimental typography, and one accent color. It also analyzes visual references and produces reusable style rules and image generation prompts.
Plan and build frontend interfaces through guided questions, visual references, and agreed design choices. Define colors, typography, and layout before coding, then implement small sections for review, with optional Google Stitch prototyping.
Build visual sequences that move forward and backward with page scrolling. Use video, image frames, canvas, SVG, or HTML elements in a sticky stage, while preserving keyboard access, static alternatives, and predictable visual states.
Add a real 3D object to a web page using Three.js. Combine geometric depth, materials that respond to light, perspective, and subtle rotation or floating motion for hero sections and product visuals.
Document visual work with real screenshots captured before a change, during key interactions, and after completion. Inspect each image and share captioned files throughout the task so users can review progress and redirect the work early.
Build a globe-like 3D visual in Three.js, a library for browser graphics. Combine a dense sphere of glowing particles with a thin orbital ring, then adjust color, density, tilt, and gentle motion.
Create, edit, and analyze spreadsheets with formulas, formatting, and visualizations. Preserve existing workbook conventions, keep calculations responsive to input changes, and use formula recalculation and error checks to verify the resulting files.
Give bland interfaces more visual character through typography, color, layout, spacing, and motion. Shape a clear focal point around the brand and audience while checking readability, accessibility, performance, and ease of use.
Improve interface layouts by reviewing spacing, alignment, content density, and visual hierarchy, the cues that show what matters most. Refine repetitive card grids and crowded sections into compositions with consistent spacing and responsive structure.
Turn text or structured data into infographics with selected layouts and visual styles. The skill can refine image prompts and, across multiple generation rounds, review the images and rank the results for selection.
Create and edit visual AI agent workflows in CC Workflow Studio through conversation. Add or remove steps and connections, update individual nodes, and organize related steps into visual groups on the canvas.
Convert text into Mermaid diagrams, which describe visual structures using code. Create process flows, comparisons, mind maps, and system interactions for presentations or documentation, with adjustable layouts and checks for common syntax mistakes.
Create original posters and static artwork by first defining a visual philosophy, then expressing it through color, shapes, spacing, and minimal text. Receive the artwork as PNG or PDF alongside a Markdown design statement.
Analyze relationships between people, objects, or papers as networks in Python. Use NetworkX to find shortest paths, identify important nodes and communities, visualize connections, exchange graph data, and generate sample networks for testing.
Create Excalidraw diagram files that explain workflows, architectures, and concepts through visual relationships. Technical diagrams include concrete code or data examples, while a rendering and review process checks readability, connections, spacing, and overall composition.
Use a transaction hash, its identifying code, to retrieve records from TRES Finance. The skill draws asset movements and network fees, then explains the action, participants, amounts, and net result in plain English.
Turn a text development plan into a visual document with diagrams, file maps, annotated code, and open questions. For interface work, add wireframes or an interactive prototype so reviewers can examine screens and behavior before implementation.
Set up W&B to record machine learning metrics and settings, visualize training progress, and compare experiments. Includes automated searches for training settings, version tracking for datasets and models, and shared reports for team collaboration.
Analyze relationships between people, objects, or places using Python networks. Build connection diagrams, find shortest paths, identify important nodes and closely connected groups, visualize network structure, and save the resulting data and measurements.
Turn the subject under discussion into an HTML explanation with large visuals and minimal text. Keep essential details, explain unfamiliar ideas in plain language, and use pictures or icons selectively when they help the reader understand.
Visualize ChIP-seq data using deepTools, Gviz, and ChIPseeker. Create heatmaps, profile plots, and genome browser tracks. Visualize signal around peaks, TSS, or custom regions. Use when visualizing ChIP-seq signal and peaks.
The English summary is being prepared. Showing the original description.
Designs and directs the visual assets that carry content — carousels, infographics, quote graphics, diagrams, and social imagery — including the generation prompts where they are AI-produced. Use this to turn a written piece into a visual format, design a carousel or infographic, create social graphics, or fix visuals that are not stopping the scroll.
The English summary is being prepared. Showing the original description.
Rigorous visual validation expert specializing in UI testing, design system compliance, and accessibility verification. Masters screenshot analysis, visual regression testing, and component validation. Use PROACTIVELY to verify UI modifications have achieved their intended goals through comprehensive visual analysis.
The English summary is being prepared. Showing the original description.
Adversarial visual-layout audit of a Quarto `.qmd` or Beamer `.tex` deck. Flags overflow, font inconsistency, box fatigue, spacing, and alignment issues. Use when user says "visual audit", "check the layout", "does this overflow?", "look for visual issues", "audit the slides", or after reworking a deck's appearance. Does NOT check writing or pedagogy — pair with `/proofread` or `/pedagogy-review`.
The English summary is being prepared. Showing the original description.