proof-video
Add subtitles, captions, narration cues, or zoom to a proof video or PR recording using repo-local capture helpers and a system ffmpeg renderer.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-28 00:17
Design & creation
21,059 results
openclip-remove-background
Remove the background from an image with OpenClip and get back a transparent PNG. FREE with just an OpenClip account, no subscription. Use when asked to…
states
Design every state a screen can be in, not just the happy one. Loading with skeletons that match the layout, spinner timing, empty states that teach one…
type
Set type like it was chosen, not defaulted. Typeface selection, size scales for product versus reading UI, line height and tracking by size, measure, hierarchy…
video-prompting-guide
Best practices and techniques for writing effective AI video generation prompts. Covers: Veo, Seedance, Wan, Grok, Kling, Runway, Pika, Sora prompting…
gpt-image-prompts
Turn a visual idea into a production-ready prompt and API settings for OpenAI GPT Image models (gpt-image-2).
visualise
Render inline interactive visualizations directly in the conversation—SVG diagrams, HTML components, charts, explainer graphics. When the user asks to draw a diagram, make a chart, draw a flowchart, architecture diagram, data visualization, UI mockup, or says 'draw a picture' 'show me' 'draw' 'map…
optimize-3d-assets
Optimize and compress 3D assets for the web — shrink glTF/GLB models and textures using gltf-transform, gltfpack/meshopt, Draco, and KTX2/Basis, and optionally…
space-video-audio
Video dubbing and music. Three things—(1) Dubbing: use TTS to generate narration audio from the spoken script; (2) Music: match suitable BGM according to the video content/rhythm, find and download it from royalty-free music libraries; (3) Mixing: use ffmpeg to combine BGM + narration + video, with automatic ducking (BGM automatically lowers under the voice), loudness normalization, fade in/out, and alignment to the video length. When the user says "dubbing", "music", "add…
space-video-broll
Motion director + B-roll generator. From a piece of text/script/video, produce in one go a motion B-roll video of 30 seconds or more (HTML→deterministic MP4). No PPT-style page flipping; start from "visual metaphor + motion"; built-in multiple design styles (dark SaaS magic, black-and-white typewriter, warm editorial, minimal white, blueprint grid); output is always...
space-video-cover
Video cover/thumbnail design. Generate high-click covers for talking-head videos, Bilibili/WeChat Channels/Xiaohongshu/YouTube, maintaining the same account's "family feel" (unified layout genes, but each one redesigned rather than locked into a rigid template). Triggered when the user says "make a cover", "video thumbnail", "first image", "Bilibili cover", "Xiaohongshu cover", "cover", "make a cover". Input is a title/topic/a screenshot, output is a cover image in the corresponding platform ratio.
space-video-edit
Talking-head video editing, two stages—(1) Cut talking-head: transcribe → detect slips of the tongue/filler words/silence/repetition/stumbles/incomplete sentences → generate review page → after user confirmation, cut out a clean video → re-transcribe and AI-proofread subtitles; (2) Final cut: string the cut video + subtitles + assets into storyboards, timeline preview, export final…
video-merge
Use when user needs to merge video clips, add audio, and generate the final video
video-preview
Use when user wants to preview images or videos
video-quick-create
Quickly create videos, fully embracing Seedance 2.0. Complete in one step: story outline → asset preparation → text storyboard → i2v video generation.
take-one
Turn a short request into a finished short film rendered from code, working like a studio team of twelve jobs (strategist, creative director, writer, voice…
baoyu-compress-image
Compresses images to JPEG/WebP/PNG using an automated multi-platform CLI (sips, cwebp, sharp). Washed for Obsidian Creator Vault: defaults to JPEG at 65…
mermaid-visualizer
Transform text content into professional Mermaid diagrams for presentations and documentation. This skill MUST be used when the user names Mermaid, and SHOULD…
figma-context-mcp
Expert guide for using the Figma Context MCP (Framelink) efficiently while avoiding 429 rate-limit errors. Activate when: (1) using Framelink Figma MCP tools…
ecommerce-image-suite
E-commerce image set generation assistant. Triggered when the user explicitly requests generation of e-commerce image sets, product main images, selling point images, scene images, model images, and other image content. Supports the size specifications of domestic platforms (Taobao, JD.com, Pinduoduo, Douyin) and international cross-border platforms (Amazon, independent sites). Trigger examples: "Help me generate an e-commerce image set for this T-shirt", "Make a set of Taobao main images", "Generate Amazon listing images".…
store-screenshots-panorama
Make finished App Store screenshot sets from raw screenshots — brand-colour gradient and white (or a dark-dominant dark theme) flowing as one panorama across…
house-plan-designer
Automatically restore the floor plan provided by the user (images: Kujiale/Beike/Fang.com floor plans, sales office floor plans, hand-drawn floor plans with dimensions; CAD drawings: vector PDFs exported by design institutes/renovation companies, DXF, original structural drawings, architectural floor plans, black-background CAD screenshots) into an interactive renovation designer web page (single-file HTML, 2D plan + 3D bird's-eye/walkthrough + furniture layout +…
video-creator
Create videos with code (Remotion) — 30+ rules for animations, subtitles, 3D, audio, transitions, etc., loaded on demand
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…