polish
Refines a product interface while preserving its visual language, improving hierarchy, typography, spacing, density, states, responsiveness, keyboard use,…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-01 00:15
Design & creation
21,544 results
figma-design-sync
Detects and fixes visual differences between a web implementation and its Figma design. Use iteratively when syncing implementation to match Figma specs.
win11-ui-demos
Create a photorealistic simulation webpage demo animation of a "Windows 11-like system UI" — the audience feels like they are watching a carefully choreographed screen recording of a real Win11 computer: desktop, taskbar, File Explorer, Start menu, context menu, system dialogs, notifications, and WinRE blue screen restored 1:1, cursor performance guiding the operations, teaching annotation layer overlaid for explanation, and a cinematic player full-screen recording becomes the final cut. As long as the user mentions: imitate…
slack-gif-creator
Create custom animated GIFs for Slack reactions and celebrations. Use for team milestones, custom emoji reactions, inside jokes, and workplace fun.
video
Use when the user wants AI-generated short-form video — knowledge cards (picstory / Xiaohongshu / TikTok / Reels), narrated explainers, presentations, AI clips, or…
slice-video-frames
Extract ordered still-image frames from local video files with FFmpeg, using a fixed FPS, an exact frame count, explicit timestamps, or every source frame;…
realistic-video-prompting
Write realistic, de-AI-ified, documentary-textured structured video prompts for AI video generation models (Seedance, Sora, Kling, Runway, Veo, etc.). When the user wants to generate AI video prompts, optimize existing video prompts, pursue video effects of "realism," "home video feel," "phone snapshot feel," "DV feel," "surveillance footage feel," or mentions Seedance, text-to-video, video prompt, be sure to…
algorithmic-art
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code,…
brand-guidelines
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…
canvas-design
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,…
interactive-theatre-designer
Designs interactive theatrical experiences with branching narratives, audience participation systems, and immersive environmental storytelling.
inspector-review-update
Quick-review an OpenSpec change, auto-patch mechanical findings, then resolve design-decision findings either by asking the user or by applying the model's…
claude-gif-create
Programmatic GIF creation using Remotion (React-based). Generates text animations, loading spinners, logo reveals, meme templates, data visualizations,…
gemini-text
Generate text content using Google Gemini models via scripts/. Use for text generation, multimodal prompts with images, thinking mode for complex reasoning,…
iso13485-audit-prep
/cs:iso13485-audit-prep <scope> — ISO 13485 QMS audit 6-question forcing interrogation. Design controls + CAPA + post-market focused. Use before Clause 8.2.4…
ux-design
Design intuitive user experiences following Jobs-era Apple principles. Use this skill when designing onboarding flows, empty states, dashboards, user journeys,…
blender-animation
Animate 3D objects and characters in Blender with Python. Use when the user wants to keyframe properties, create armatures and rigs, set up IK/FK chains,…
antd-version-release
The version release workflow for the ant-design repository. Use it when the user mentions releasing, preparing a release PR, bumping the release version number, executing the official npm publish, or handling release branches and release validation. It is not responsible for collecting or generating the changelog; when changelog collection, organization, or rewriting is involved, use changelog-collect.
design-system-architect
Expert in building scalable design systems with Atomic Design, design tokens, and theming infrastructure. Use when creating component libraries, implementing…
image-generation
AI image generation using Pollinations.ai - FREE with no API key required. Use when generating hero images, icons, logos, illustrations, mockups, or any visual…
explain-like
Explain code changes or designs at three expertise levels (beginner, intermediate 5-10 yrs, expert). Use for: (1) PR/branch change explanations - understand…
ernie-image
Build Baidu ERNIE-Image / ERNIE-Image-Turbo workflows, primarily TEXT-TO-IMAGE. Pick ERNIE when you need precise multilingual text rendering, posters/signage,…
ltx-director
Drive the LTX Director (Timeline) node. Its Add Image/Text/Audio buttons are DOM-only and cannot be clicked by an agent; edit the hidden timeline_data JSON…
wan-scail-replacement
SCAIL-2 in-video character replacement on WAN 2.1. WanSCAILToVideo + SCAIL2ColoredMask + SAM3, the reference-image framing→scale rule, and the…