Design & Media Skills

Point your AI agent at a website, some footage or a topic and get back a finished short video.

Point your AI agent at a website, some footage or a topic and get back a finished short video: a launch brag, a promo or an explainer. An Agent Skill for Claude Code, Codex, Hermes and others.

Make agents produce distinctive, production-grade web interfaces

Anthropic's frontend design skill guides agents toward bold typography, cohesive palettes and polished layouts instead of generic AI-generated design.

From text & real sources to maintainable .drawio architecture models: Diagram IR with source-kind pr

From text & real sources to maintainable .drawio architecture models: Diagram IR with source-kind profiles, incremental sync preserving manual layout, multi-view projection, architecture-as-test with a CI action, query/review, what-if, accessible Story Mode, and a built-in MCP server

A collection of beautifully designed Shadcn UI blocks, components, templates, and dashboard layouts

Shadcn Space offers a comprehensive collection of free and premium Shadcn UI blocks, components, templates, and dashboard layouts tailored for React and Next.js applications. These resources are designed with accessibility, usability, and aesthetic appeal in mind, utilizing Base UI and Radix UI primitives styled with Tailwind CSS. Developers can copy-paste or install them via the Shadcn CLI, facilitating a seamless integration into projects.

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check acc

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 against best practices".

Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. Th

Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions \"deck,\" \"slides,\" \"presentation,\" or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill.

Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle dia

Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.

38 editorial diagram types for Claude Code, Codex, and Pi. Self-contained HTML + SVG. No shadows. No

38 editorial diagram types for Claude Code, Codex, and Pi. Self-contained HTML + SVG. No shadows. No Mermaid slop.

Generate and edit media via Picsart MCP API tools.

Generate and edit media via Picsart MCP API tools.

Bring the user's own clips, photos, or files into Picsart.

Bring the user's own clips, photos, or files into Picsart.

Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and

Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Trigger when a task involves Figma URLs, node IDs, design-to-code implementation, or Figma MCP setup and troubleshooting.

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit fr

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern fronten

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

A Claude skill for d3.js.

A Claude skill for d3.js.

Create AI influencer or branded character personas.

Create AI influencer or branded character personas.

Generate AI images, videos, audio via Picsart gen-ai CLI.

Generate AI images, videos, audio via Picsart gen-ai CLI.

Author and validate ScreenSpec JSON through a pinned design-system MCP.

AINDF screen author composes ScreenSpec JSON using components, slots and values exposed by a compatible AINDF design-system MCP. Requires an AINDF-compatible design-system bundle connected over MCP; the kit requires Node.js 20.10+. Validation is not build, visual verification, acceptance or release. It does not change the design system without approval. Product website: https://oleg.design/ai-native-design-framework

Create short animated explainer videos from a topic.

Create short animated explainer videos from a topic.

Edit videos for free with filmcraft in your browser.

filmcraft is a browser-based video editor for importing footage, arranging clips on a timeline, refining color and audio, adding titles, and previewing edits. You can try editing without an account; signing in is required to save projects or export results, which the page says are free and use zero credits. The site also offers separate AI video and image generation tools that use credits. It describes use for product demonstrations, short documentaries, lessons, and personal stories, and notes that browser performance depends on the device, footage, and graphics support.

Audit generated UI against pinned design rules and write code-linked fix plans.

UNSLOP audits generated UI with a deterministic detector and a version-pinned design-rule canon, then writes code-linked fix plans. Audit mode leaves source code unchanged. A complete audit requires the full plugin, Node.js 20+, the MCP SDK and a connected verified canon. Skill-only installs include the detector/client but cannot claim a verified canon or PASS without that setup. Separately requested execute mode applies one selected plan in an isolated worktree. Public canon MCP exposes resources only, no tools. Code and skill files: MIT; rule texts: CC BY 4.0.

Create a Hotel Lobby AI video from two photos with Hot AI Video.

Hot AI Video allows users to generate AI videos by uploading two photos. The platform focuses on creating 5-15 second video clips that can retain original audio or be silent. It is designed for the independent creative user who wants to make unique videos without needing to provide prompts.

Make any image a seamless, tileable texture.

Seamless Texture Generator is a browser-based tool for repairing an existing image so it can repeat as a tileable texture. Users can upload a photo, scan, render, artwork, or texture and preview the result in a tiled layout before downloading a PNG. It offers standard and optional AI repairs, several repeat-preview sizes, seam guides, and controls for repair mode and direction. The page describes uses including 3D materials, games, fabric, wallpaper, and mockup tests. Guests receive five free standard repairs and one free AI repair; PNG exports cost 2 credits, with unlimited exports available to subscribers.

Free AI photo enhancer to unblur images online.

Free AI Photo Enhancer is an online tool designed to unblur and enhance images, restoring clarity and detail with 4K resolution. It caters to various audiences, including individuals needing to improve personal photos, e-commerce businesses seeking clearer product images, and anyone looking to revive vintage pictures. The platform offers a convenient, no-sign-up experience with instant previews and a straightforward interface for enhancing photos.

Free skill exchange for AI agents: 32+ signed, versioned skills to download and use

The Playbook is a free skill exchange for AI agents: 32+ signed, versioned skills across coding, writing, data, and automation that agents can download and use directly. Anyone can submit skills, and human moderation keeps the catalog trustworthy.