write-design-md
Write or update a project's DESIGN.md from the colors, type, spacing and components it really uses, with rules agents follow so new screens match.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Design & creation
22,056 results
crg-req-to-design
Convert CRG requirement table (subsystem, IP, clock/reset signals, notes) into clock tree design table and reset tree design table, with PLL count…
drill
QA test case and test scenario authoring agent. Designs detailed, executable test procedures for manual QA — preconditions, step-by-step actions, expected…
design-motion
Designing motion and micro-interaction: duration and easing, transition choreography, state-change feedback, loading, gesture response, and reduced motion. Use…
brainstorming
Use when designing complex multi-step features, building new components, or planning significant behavior changes that require design exploration before…
spec-interview
Use when refining design docs and specs through deep questioning. Triggered when user says "help me refine this plan", "ask me about the project", "deep…
movie-poster-style-image-generation
Create generative movie-poster style graphics for products, apps, brands, campaigns, and abstract concepts. Use when a task needs poster-quality key art,…
export-art
Export a generative sketch for the real world — high-resolution print-ready stills (raster or SVG) and smooth video/GIF loops from an animation (CCapture.js,…
generative-series
Set up a deterministic, hash-seeded generative SERIES / editions (fxhash or Art Blocks style) — one codebase that produces a unique, reproducible artwork per…
scaffold-sketch
Scaffold a new generative / creative-coding sketch from scratch with a clean, seeded, reproducible setup (Vite + p5.js instance mode, or a zero-build vanilla…
youtube-publisher
End-to-end video publishing pipeline: download from Google Drive, upload to YouTube, transcribe audio via Deepgram or Fireworks Whisper, generate…
video-scene-analyzer
Analyze video files by detecting scene boundaries and generating structured production metadata as JSON. Use when asked to analyze scenes in a video, detect…
soia-media-cover-image
Generate cover images for WeChat Official Account/X/Xiaohongshu articles, supporting five-dimensional parameters and multiple aspect ratios; for WeChat Official Account, the output feeds into soia-media-publish-wechat-draft --cover. Use only the codex CLI's built-in image generation; if missing, stop and prompt, do not silently degrade. Triggers: "generate cover", "make a cover image", "pair a WeChat Official Account header image", "make a Xiaohongshu cover", "cover…
soia-design-explorer
Use the external huashu-design capability to produce high-fidelity HTML prototypes, design variants, slides, animations, or design reviews; requires an explicit upstream path, the user's own brand guidelines, five-category output destinations, and reproducible verification.
high-end-visual-design
Apply a polished luxury-agency web aesthetic when the user explicitly asks for premium, luxury, or high-end agency art direction.
image-to-code
Implement a web interface with close fidelity to supplied screenshots/design images or intentionally generated references in an explicitly requested…
web-animation-design
Design and implement web animations that feel natural and purposeful. Use this skill proactively whenever the user asks questions about animations, motion,…
styling-patterns
DaisyUI v5 design system. Use for backgrounds, borders, text sizes, opacity, semantic colors, and spacing.
design-doc-mermaid
Create Mermaid diagrams (activity, deployment, sequence, architecture) from text descriptions or source code. Use when asked to "create a diagram", "generate…
spritecook-use-assets-in-godot
Godot workflow for SpriteCook assets. Use when the user wants to turn SpriteCook spritesheet PNGs, animation assets, or character animation runs into Godot…
ux-copy
Use when writing user interface or in-product text: microcopy, button labels, error messages, tooltips, placeholders, empty states, onboarding flows,…
seedream-imagegen
Generate AI images with the ByteDance Seedream 4.0 API (via Segmind). Use when the user wants to generate high-quality images such as marketing assets, posters, product shots, concept art, or social media visuals from text descriptions, and the environment is configured with SEGMIND_API_KEY. Supports 2K/4K, multiple aspect ratios, batches of up to 15 images at a time, up to 3…
social-creative-designer-openai
Creative Designer skill for social media visuals using OpenAI GPT Image models instead of Nano Banana. Creates generated, composite, branded, and stop-motion…
typography-expert
Master typographer specializing in font pairing, typographic hierarchy, OpenType features, variable fonts, and performance-optimized web typography. Use for…