home / skills / duc01226 / easyplatform / design-video

design-video skill

/.claude/skills/design-video

This skill analyzes a video to generate a detailed, pixel-perfect frontend design plan and HTML/CSS/JS implementation.

npx playbooks add skill duc01226/easyplatform --skill design-video

Review the files below or copy the command above to add this skill to your agents.

Files (1)
SKILL.md
2.9 KB
---
name: design-video
description: "[Design & Content] Create a design based on video"
argument-hint: [video]
infer: true
---

Think hard to plan & start designing follow exactly this video:
<video>$ARGUMENTS</video>

## Required Skills (Priority Order)

1. **`ui-ux-pro-max`** - Design intelligence database (ALWAYS ACTIVATE FIRST)
2. **`frontend-design`** - Video analysis and replication

**Ensure token efficiency while maintaining high quality.**

## Workflow

1. Use `ai-multimodal` skills to describe super details of the video: be specific about describing every element, every interaction, every animation, every transition, every color, every font, every border, every spacing, every size, every shape, every texture, every material, every light, every shadow, every reflection, every refraction, every blur, every glow, every image, background transparency, etc.
   - **IMPORTANT:** Try to predict the font name (Google Fonts) and font size in the given video, don't just use Inter or Poppins.
2. Use `ui-ux-designer` subagent to create a design plan following the progressive disclosure structure so the final result matches the video:
   - Create a directory using naming pattern from `## Naming` section.
   - Save the overview access point at `plan.md`, keep it generic, under 80 lines, and list each phase with status/progress and links.
   - For each phase, add `phase-XX-phase-name.md` files containing sections (Context links, Overview with date/priority/statuses, Key Insights, Requirements, Architecture, Related code files, Implementation Steps, Todo list, Success Criteria, Risk Assessment, Security Considerations, Next steps).
   - Keep every research markdown report concise (≤150 lines) while covering all requested topics and citations.
3. Then implement the plan step by step.
4. If user doesn't specify, create the design in pure HTML/CSS/JS.
5. Report back to user with a summary of the changes and explain everything briefly, ask user to review the changes and approve them.
6. If user approves the changes, update the `./docs/design-guidelines.md` docs if needed.

## IMPORTANT Task Planning Notes

- Always plan and break many small todo tasks
- Always add a final review todo task to review the works done at the end to find any fix or enhancement needed

## Important Notes

- **ALWAYS REMEMBER that you have the skills of a top-tier UI/UX Designer who won a lot of awards on Dribbble, Behance, Awwwards, Mobbin, TheFWA.**
- Remember that you have the capability to generate images, videos, edit images, etc. with ai-multimodal skill for image generation. Use them to create the design with real assets.
- Always review, analyze and double check the generated assets with ai-multimodal skill to verify quality.
- Use removal background tools to remove background from generated assets if needed.
- Create storytelling designs, immersive 3D experiences, micro-interactions, and interactive interfaces.
- Maintain and update `./docs/design-guidelines.md` docs if needed.

Overview

This skill creates pixel-accurate UI designs by analyzing a reference video and reproducing its visuals, interactions, and animations. It combines multimodal video inspection with UI/UX design intelligence to produce an implementable plan and front-end assets. The output focuses on fidelity to the video while remaining token-efficient and practical for web implementation.

How this skill works

The skill inspects the provided video frame-by-frame to extract every visual and interaction detail: typography, colors, spacing, motion curves, shadows, reflections, and material qualities. It then generates a progressive design plan with phased markdown artifacts and frontend HTML/CSS/JS prototypes, using AI multimodal analysis to predict fonts, sizes, and animation timing. The process includes asset generation, background removal where needed, and a final review checklist to ensure parity with the source video.

When to use it

  • Recreate a UI or micro-interaction demonstrated in a video reference.
  • Prototype a landing page or component with exact visual fidelity to a recorded demo.
  • Translate motion design and micro-interactions into production-ready HTML/CSS/JS.
  • Audit an existing product against a recorded design spec for alignment and handoff.
  • Generate design system tokens (colors, type, spacing) from a visual source.

Best practices

  • Always provide the highest-resolution video available for more accurate extraction.
  • Supply context: target platform (web, mobile), target breakpoints, and accessibility requirements.
  • Prioritize extracting atomic details first: type, color, spacing, then motion and effects.
  • Keep tasks small and incremental with a final review task to validate parity.
  • Prefer web-safe or Google Fonts; the skill predicts likely font families but verify licenses.

Example use cases

  • Convert a product walkthrough video into a pixel-accurate HTML prototype with animations.
  • Produce a design plan and phased deliverables for a complex onboarding flow shown in a demo video.
  • Extract a brand’s hero animation from a recorded concept and export assets for dev handoff.
  • Audit a competitor’s interface demo to produce a matching micro-interaction library for reuse.
  • Create an interactive mock that mirrors a recorded mobile app interaction for stakeholder review.

FAQ

What input format does the skill need?

A clear video file or link with the UI interaction; higher resolution and unobstructed UI yield better extraction.

Will the skill produce production-ready code?

It produces clean HTML/CSS/JS prototypes and a detailed implementation plan suitable for engineering handoff; final integration may need platform-specific adjustments.