Design & Media Agent Skills for Claude Code

Plan user flows and screen states for a Figma design before any designing starts.

Quarterly / monthly financial report — masthead with KPIs, revenue and burn charts, P&L summary table, top-line highlights, and an outlook…

Use when reviewing image assets, markup, and CDN or build transforms related to Fix broken images.

Import UI screenshots and generate uxscii components automatically using vision analysis.

Optimize any form that is NOT signup or account registration — including lead capture, contact, demo request, application, survey, quote…

Use when asked to select a UI style, choose a design direction, pick a visual approach for a product, or match a style to an industry.

Harden designs for real-world use by systematically identifying and designing for every condition outside the happy path.

Implement Framer reference architecture with best-practice project layout.

Analyze, plan, and execute Framer SDK upgrades with breaking change

Use for new frontend applications, dashboards, games, creative websites, hero sections, and visually driven UI from scratch, or when the…

Build and maintain web frontends — component architecture, state management,

Builds sophisticated, responsive frontend interfaces within the Codex Project Autopilot framework using advanced UI/UX engineering…

Ensures stable and consistent Vue/React frontend modifications by enforcing strict layout, data-binding, and styling constraints.

Big-tech style (Stripe, Vercel, Apple) UI development.

Create distinctive, production-grade frontend interfaces with high design quality.

A multi-frame gamified mobile-app prototype — three phone frames on a dark showcase stage.

Generate from templates, retrieve exports, and manage sharing via Gamma

Generate and edit images using the Gemini API (Nano Banana Pro).

Generate a low-fidelity layout wireframe from a natural-language description, using the Smart Assets design system.

MANDATORY prerequisite — load this skill BEFORE every `generate_diagram` tool call.

Generate on-screen visuals for Ben van Sprundel's YouTube videos using Higgsfield.