sfx-picker
Pick and assign sound effects from the Cozer SFX library to motion graphics compositions, animation keyframes, and UI interactions. Reads the full catalog in…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-31 00:15
Design & creation
21,393 results
vox-explainer
Make a short Vox-style documentary explainer (30-60 seconds) entirely in code with Claude Code. Torn paper, halftone texture, bold condensed type, motion on…
frontend-impl-design-tokens
Use when structuring a design-token system for a web app or component library, authoring the JSON interchange file per the W3C Design Tokens Community Group…
ai-content-pipeline
Build multi-step AI content creation pipelines combining image, video, audio, and text. Workflow examples: generate image -> animate -> add voiceover -> merge…
background-removal
Remove backgrounds from images with BiRefNet via inference.sh CLI. Model: BiRefNet (high accuracy background removal). Use for: product photos, portraits,…
youtube-download
Use yt-dlp to download YouTube videos, audio, or subtitles. Use when user wants to 下载视频, 下载YouTube, youtube下载, 下载油管, download youtube, download video, 下载B站, bilibili下载.
web-design-guidelines
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…
video-downloader
Download videos from 1000+ websites (YouTube, Bilibili, Twitter/X, TikTok, etc.) using yt-dlp. Use this skill when users provide video URLs and want 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,…
web-design-guidelines
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…
fireflies-reference-architecture
Design a Fireflies architecture that separates identity, GraphQL reads, privileged mutations, Webhooks V2 intake, queues, sensitive data, and derived outputs.…
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,…
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with…
mc-ai-tell-audit
The post-generation AI-tell audit (AI 味诊断). Run this on every generated track before accepting it. Covers the fourteen enumerable defaults that generative…
mc-progressions
Chord progression lookup library (和弦进行速查库) - the eight famous named progressions with their variants and what each one actually does, a mood reverse-lookup,…
theme-management
Expert theming decisions for iOS/tvOS: when custom themes add value vs system colors suffice, color token architecture trade-offs, theme switching animation…
cinematic-asset-prompts
Film concept art expert & visual director skill—extract and design standardized visual asset prompts for AI video from scripts/stories/worldview text. When the user requests "extract character/scene/prop/vehicle prompts from a script", "generate character design photo prompts", "generate scene empty shot prompts", "generate prop/vehicle/mechanical asset design image prompts", "for AI...
negative-feedback
When the user observes that a certain force/trend/behavior is excessively dominant and needs a counterbalance introduced; When the system exhibits an overshoot phenomenon where "the harder you push, the worse it gets"; When a self-regulating mechanism needs to be designed to prevent the system from going to extremes; When the user says "things reverse at their extreme" or "using too much force backfires." Not applicable to: scenarios that require continuous one-directional advancement without counterbalance (such as an all-out sprint in the early stages of a startup); Scenarios where the problem itself is insufficient force rather than excessive dominance.
persona-design
Invoke this skill when it is necessary to define the core identity, role declaration, and capability boundaries for an AI product. Typical scenarios include: designing the first paragraph of the system prompt for a new AI product, creating differentiated roles for different scenarios (such as a teaching assistant vs. a coding agent), and redefining the relationship framework between the AI and the user. Not applicable to: pure personality style tuning (should use...
design-an-interface
Use parallel subagents to generate multiple distinctly different interface designs for a module. Use when the user wants to design an API, explore interface options, compare module shapes, or mentions "design twice".
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,…
slack-gif-creator
Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request…