style-library-importer
Add a named or text-defined visual style to the numbered hand-drawn style library, generating a square representative image without number badges when none is…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Design & creation
22,067 results
tweet-style-importer
Automatically scrape any X/Twitter tweet and its images, assign the next sequential style number, generate a 1024x1024 4-grid generation reference and a…
cli-anything-photoshop
A CLI harness for controlling Adobe Photoshop via COM automation. Supports project management, layer operations, selection control, text editing, image adjustments, and multi-format export.
video-to-text
Video/audio to transcript. Extract audio from video files, use whisperX for speech recognition, timestamp alignment, and speaker diarization, and output a transcript with timestamps and speaker labels. Suitable for: livestream replay transcription, meeting recording to text, podcast transcription, and any video/audio-to-transcript scenario.
audit-ui-ux
Use if auditing web or mobile UI/UX via vision-first screenshot evaluation across design precision, usability heuristics, and cognitive laws.
linggan-talking-cards
Split Chinese or English voiceover scripts and optional screenshots into 3–10 PPT-style presentation cards, and output text-accurate PNG cards, a structured manifest, and a responsive HTML preview page with per-card voiceover lines. Supports four aspect ratios: 3:4, 16:9, 9:16, and 4:3, as well as Apple white frosted glass, candy, Obsidian, neo-brutalism, and 10…
bs-article-illustrate
Use when the user asks to illustrate an article, blog post, or long-form document with diagrams, charts, conceptual illustrations, or comparison visuals. Also…
bs-social-card
Use when the user asks to generate a social media card image, OG image, Twitter card, link preview, or social share graphic. Do NOT use for full-page…
huatu-skill
Turn articles, research, notes, data, or existing drafts into clear Xiaohongshu carousel storyboards and 1080×1350 image slides. Use when Codex needs to…
figma2design
Figma design link → complete .design/ directory (DESIGN.md, PAGES.md, COMPONENTS.md, CODE_PATTERNS.md, ICONS.md, brand/, icons/, screenshots)
idea2design
Design idea or text description → complete .design/ directory (DESIGN.md, PAGES.md, COMPONENTS.md, CODE_PATTERNS.md, ICONS.md)
comic-maker
Tutorial comic "Mini Classroom": your IP becomes the teacher (if you don't have one, generate one first), 3:4 portrait format, 6–9 pages per issue by default (however many pages the user wants), always with a "Class Begins" cover and a "Class Dismissed" ending, handed to Codex's built-in imagegen for image generation and verification. Triggered when the user says "draw a comic", "make a comic set explaining XXX", "explain with comics", "mini classroom", "change the teacher / change the character".
openai-dotcom-viz
Build figures in OpenAI's blog / research / system-card "dotcom" visual style — both (a) bar charts (monochrome bars with a darker same-hue stroke, rounded…
minimalist-design
Apply a minimalist monospace design system using IBM Plex Mono at a single size with ASCII-style structure. No opacity, no weight variation, no type scale.…
skill-runway-video-gen
Generate short product videos from images using Runway Gen4 Turbo. Use for TikTok ads, UGC-style product demos, Reels, and YouTube Shorts.
pngimg-download
Search and download free transparent PNG images from pngimg.com. Use when the user wants to find or download PNG images with transparent backgrounds, clipart,…
article-illustrator
Use when illustrating a Markdown article with high-finish editorial visuals, visual-bible planning, structured prompts, optional Qiniu upload, and inserted…
atomic-design
Use when organizing interface components hierarchically. Suitable for design system creation, component library design, and improving reusability. Prefer Brad Frost's Atomic Design five-level model (atoms → molecules → organisms → templates → pages).
component-states
Use when defining all states of a UI component. Applicable to complete state coverage for components such as buttons, forms, lists, and dialogs. Prefer using 8 core states (default/hover/focus/disabled/loading/success/error/empty/permission).
customer-journey
Use when designing the complete user journey from awareness to retention. Suitable for end-to-end design of new products/features, identifying pain points and opportunities, and providing design input for UI/UX. Prefer the NNGroup customer journey mapping method.
page-structure
Used when designing single-page structure and wireframes. Suitable for functional page design, content layout, and arrangement of primary and secondary actions. Prefer the page-goal-oriented method + content hierarchy + primary/secondary action distinction.
user-flow
Use when designing the user flow from entry to task completion. Suitable for mapping functional flows, designing page transitions, and defining decision points and exception paths. Prioritize outputting a Mermaid flowchart + main path + exception paths.
visual-style
Used when defining visual styles and performing anti-AI checks. Suitable for setting the style tone before design and avoiding generalization and templating. Prioritize style library selection + explicitly disabling AI-templated effects.
image-prompt-gen
Write English image prompts for Krea 2, Qwen Image 2.1, and Anima, from a text idea or by reverse prompting an image. Use it only when the user wants a prompt…