search-video-on-web-and-gen
Search video materials on the web and generate professional videos - automated video production pipeline with yt-dlp, Doubao TTS, Remotion rendering, and…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Design & creation
22,050 results
video-transcript-downloader
Download videos, audio, subtitles, and clean paragraph-style transcripts from YouTube and any other yt-dlp supported site. Use when asked to “download this…
database-design
Database design principles and decision-making. Schema design, indexing strategy, ORM selection, serverless databases.
apple-liquid-glass
Apple's Liquid Glass design language (iOS 26 / macOS 26 HIG) made buildable on any platform: the content/chrome two-layer model, regular vs clear glass, real…
gpt-image-generation
Self-contained GPT image generation skill for creating PNG images through the ChatGPT Codex backend, including 4K outputs and prompt-file input. Use when Codex…
creating-sticker-packs
Use when creating raster sticker packs, hand-drawn character stickers, object stickers, mascot cutouts, transparent PNG assets, chroma-key cutouts, or…
make-explainer
Make a narrated explainer video about a project, feature or setup in the local explainer studio. Use when the user asks for an explainer or walkthrough video.
ip-master
Manage registered IP characters and route design requests to suitable available Skills; when several Skills fit, ask the user to choose and remember that…
baoyu-image-cards
Generates infographic image card series with 12 visual styles, 8 layouts, and 3 color palettes. Breaks content into 1-10 cartoon-style image cards optimized…
agent-entrypoint-design
Use when designing or refactoring AGENTS.md, CLAUDE.md, GEMINI.md, Cursor rules, GitHub instructions, source-of-truth navigation, or agent onboarding…
design-doc-and-task-board
Use when deciding how requirements should be captured in design docs, tasks.md, external task systems, exec plans, acceptance criteria, status updates, or…
create-design-md
Use skill if you are producing a design.md spec plus per-asset references tree from a live URL, codebase, or HTML snapshot so another agent can reproduce the…
image-render
Image rendering - Illustration for articles: define what each image conveys and the exact text on it, design the visuals for each image using your default style (the first time, choose from the style library with sample images), and hand it to Codex's built-in imagegen to render as-is, generating a comparison page where you can mark favorites. Supports exploration (try several styles on one image), mass production (produce a full set in the default style), and adding your own style. When the user says "illustrate this article", "make a few images", "use…
logo-design
Design, diagnose, and iterate product or brand logos, converge direction from positioning and aesthetic feedback, and complete app icon adaptation, brand lockups, and ready-to-use assets. Applies to "make a logo," "these versions don't look good," "refine along this direction," "export usable icons"; not for ordinary page UI, full-site design, or pure illustration. Must be used in Codex (depends on its image generation).
page-solution-design
Work with the user to lock down a full-page plan for a front-end page (three-layer method: first define what this page gives the user, then define what it contains and how it is arranged, and only last what it looks like), and finally package it into a final spec package (including high-fidelity all-states and interaction flow diagrams) to hand to development. Trigger: the user says about a page "want to redo / redesign / the whole page is off / too crowded / can't say exactly what to change", or "let's discuss how to design this page". Covers three situations: ①…
glm-image-generation
Official skill for generating high-quality images from text prompts using ZhiPu GLM-Image API. Excellent at scientific illustrations, high-quality portraits,…
brand-guidelines-builder
Help non-designers evaluate work against brand guidelines and know what to fix.
game-art-direction
Direct game art and creative vision. Turn GAME_DESIGN into ART_DIRECTION defining a recognizable visual identity, functional visual and audio feedback, and key…
game-world-design
Design game experience, systems, and levels. Converge the chosen concept into one GAME_DESIGN defining the player promise, core loop, how the world responds,…
short-drama-assets
Extract characters/looks, locations/views, props/states, and cross-scene continuity from a short-drama script, and write them into creator-readable visual settings. Use when the user says "break down characters/scenes/props," "make asset settings," "decide reuse or new variant," "update look/prop state," or when directly preparing visual assets from an existing script; do not write image prompts or generate media.
short-drama-edit
Edit the generated short-drama shots into a finished cut, recording in/out points, shot order, sound, subtitles, and delivery specs. Used for conforming cuts, adding subtitles, unifying loudness, adjusting pacing, or exporting polished material; when material needs to be added or the story changed, return to the corresponding creative stage.
short-drama-image-prompts
Write or revise Markdown image prompts for short-drama characters, styling, locations, props, and states that can be copied directly. Use when the user mentions character design sheets, three-view sheets, reference images, scene boards, prop sheets, style frames, Look Development, state variants, or local edit prompts; do not generate images or call vendors.
short-drama-review
Review the source-material analysis, story, script, visual settings, image prompts, storyboard, frozen keyframes, video prompts, and existing media in a short-drama project. Use when the user requests "review/check the script," "check assets or continuity," "check image/video prompts," "check the source-material analysis," "review template feel," or "calibrate the project based on production observations"; write only review issues, conclusions, and revision requirements, and do not modify source files on the owner's behalf.
story-cover
Novel cover generation. Automatically analyzes the genre and style based on the book title and author name, and calls GPT-Image-2 to generate a professional-grade web novel cover containing the title and byline; Codex CLI preferentially uses the built-in ImageGen, with no separate API Key required. Trigger methods: /story-cover, /封面, "help me make a cover", "generate cover image", "make a novel cover", "cover design".