Media Skills

将约 5 秒口播文稿、观点句或抽象概念做成高级 editorial halftone paper-collage / 半调纸拼贴 B-roll。用户说“collage b-roll”“纸拼贴 b-roll”“半调拼贴”“拼贴风格配画面”“用这段文稿做拼贴动画”“gbro-collage-broll”，或希望把一句文稿转成拼贴视觉隐喻时，必须使用此 skill。强制采用三阶段审批：先只提视觉隐喻，用户确认后才生成彩色拼贴静帧，静帧再次确认后才默认调用 Gemini Omni Flash 生成首尾帧组装动画。默认视频模型固定为 gemini-omni-flash-preview，不再默认使用 Veo；只有用户明确指定其他模型时才切换。

> 网站复刻 / 克隆方法论。USE WHEN 用户说 复刻网站、克隆网站、clone website、抄个站、仿站、 照着这个站做一个、reproduce site、还原某个网页效果、把这个站搬下来改成我的、 复刻某个交互/WebGL/Canvas/Three.js 效果。提供「先拿真源码 → 判路径 → 逆向拆解 → 搭工程 → 替换内容」的可移植决策树，覆盖静态站 / React-Vue-Next 内容站 / WebGL-Canvas 重前端站三大分支，并强制核对任何 AI 二手分析里的可执行代码。

Write builder-honest AI image prompts from a concrete ForgeCAD model, build brief, HLD, or LLD without hiding how the artifact is built.

Reconstruct a real parametric ForgeCAD object from reference images by using images as evidence, not as a one-view facade.

Expert guidance on using Coil for image loading in Jetpack Compose. Use this when asked about loading images from URLs, handling image states, or optimizing image performance in Compose.

Create and record scripted browser demo videos with webreel. Generates MP4, GIF, or WebM recordings with cursor animation, keystroke overlays, and sound effects from a JSON config. Use when the user wants to record a demo, create a browser video, edit a webreel config, generate a screen recording, preview a demo, or work with webreel in any way.

Generate UX microcopy (button labels, error messages, empty states, toasts) following a casual-but-polite voice and tone

> Applies motion design principles to create emotionally-driven, technically sound animations and transitions. Provides timing, easing, choreography, and Disney animation principles adapted for UI. Use when creating animations, transitions, micro-interactions, loading states, page transitions, scroll-triggered effects, or any motion work. Works with CSS, Framer Motion, GSAP, Lottie, Spring, or any animation system.

Display images and annotations for image processing, computer vision, and visual inspection. Use when displaying images with imageshow, creating image viewers with viewer2d, adding Regions of Interest (ROI) or annotations, overlaying masks or segmentations, streaming video frames, or building apps with image display.

Display 3-D image volumes, medical image volumes, surface meshes, and annotations for 3-D image processing. Use when displaying 3-D images or isosurfaces with volshow, creating volume viewers with viewer3d, adding Regions of Interest (ROI) or annotations, overlaying masks or segmentations, streaming volumetric data, or building apps with volume display.

>- Creates MATLAB interfaces to Python image processing and computer vision models from GitHub repositories or pip-installable packages using MPyReq. Use when asked to interface MATLAB with a Python CV/image model (segmentation, depth estimation, object detection, image generation, super-resolution, etc.), given a GitHub repo URL for an image/vision model, or asked to create an MPyReq demo for a deep-learning vision pipeline. Do NOT use for general-purpose Python-MATLAB interfacing, non-vision models (NLP, tabular, audio), model deployment/serving, or MATLAB-only image processing workflows.

> Normalize images to [0,1] using im2double with proper validation and edge-case detection. Use when reading images with imread and converting to double for processing, displaying images with imshow, normalizing for ML training, brightening/adjusting pixel values, or any imread→process→imwrite workflow. white, image appears all white, image appears all black, read and process images, batch normalize, brighten image, pixel value scaling.

Patterns for using blockedImage to process large images, harness parallel compute for image processing, and write custom adapters. Use when writing code that creates, processes, or visualizes blockedImage objects, when implementing images.blocked.Adapter subclasses, or when a user needs help with large image data. Always use this skill when working with TIFF,GeoTIFF, .svs, .ndpi, .czi or other WSI, satellite imagery or microscopy volume image formats.

> Read, write, and manipulate medical imaging data (DICOM, NIfTI, NRRD) in MATLAB. Covers Image Processing Toolbox functions (dicomreadVolume, niftiread, dicomContours, dicomanon) and Medical Imaging Toolbox enhanced APIs (medicalVolume, medicalImage, medicalref3d, extractSlice, updateOrientation). Use when reading medical files, listing DICOM series, extracting spatial referencing, changing orientation, working with RT structures, or anonymizing DICOM data. Some features require Medical Imaging Toolbox — see skill body and references for details.

> Extract features from 1D signals using signalTimeFeatureExtractor, signalFrequencyFeatureExtractor, and signalTimeFrequencyFeatureExtractor. Use when computing time-domain features (amplitude, energy, shape factors), frequency-domain features (spectral location, power, bandwidth, PSD), or time-frequency features (spectral shape, instantaneous, ridges, wavelet, EMD-derived) on a per-frame basis. Use when the user asks to "extract features", "compute spectral features", "build a feature table for a classifier", "get per-frame statistics", "run feature extraction on this signal", or describes a vibration / biosignal / radar / sensor signal needing features for downstream ML or analysis. Includes optional GPU acceleration via canUseGPU and gpuArray. Does not cover filter design, audio-specific feature extraction (use audioFeatureExtractor in Audio Toolbox instead), batch dataset orchestration, or 2D / image features.

Reference for MATLAB audiostreamer (Audio Toolbox R2025a+). Without this skill, agents consistently default to legacy audioDeviceWriter/audioDeviceReader or base MATLAB sound(), producing less capable code. Use when writing code for audio playback, recording, full-duplex device I/O, real-time audio measurements, or audio I/O processing with callbacks. Also use when debugging audiostreamer errors, dropouts, or latency issues, or migrating from audioDeviceReader, audioDeviceWriter, audioPlayerRecorder, or audioplayer/audiorecorder.

> Design and implement real-time audio processing chains using Audio Toolbox streaming objects. Use when building frame-based audio processing loops, multiband filters, dynamic range control, parametric EQ, level metering, loudness metering, SPL metering, octave-band analysis, sample rate conversion, frequency-domain filtering (long impulse responses, custom filter banks), or audio chains in Simulink. Covers visualization (visualize method), interactive tuning (parameterTuner), MIDI control, and Audio Toolbox Simulink blocks. Use when the user says "real-time audio", "streaming audio", "audio filter", "compressor", "equalizer", "level meter", "loudness meter", "SPL meter", "octave bands", "crossover filter", "audio chain", "MIDI control", "convolution reverb", "impulse response streaming", "frequency-domain filter", or asks to process audio frame-by-frame.

> Guide authoring of Audio Toolbox plugins (audioPlugin, audioPluginSource) that pass validateAudioPlugin and generate deployable VST/AU code. Use when creating audio effect or generator plugins, writing classdef files inheriting from audioPlugin, or troubleshooting validateAudioPlugin failures.

> Read BEFORE troubleshooting or enhancing camera image quality. Diagnoses and enhances image quality from cameras connected via Image Acquisition Toolbox or USB Webcams support package. Discovers camera capabilities at runtime, analyzes captured images for quality issues (brightness, contrast, sharpness, noise, color balance, backlighting), suggests hardware setting adjustments tailored to the specific camera, and applies Image Processing Toolbox enhancement functions. Use when a user wants to improve camera image quality, troubleshoot dark/blurry/noisy/grainy/ overexposed/washed out/color cast images, or optimize camera settings.

> Connect to and acquire images from cameras in MATLAB using Image Acquisition capture video, stream from a camera, connect to a GigE Vision camera, preview live video, list available cameras, configure camera properties, use a CoaXPress frame grabber, or use a Camera Link frame grabber. Covers USB webcams, GigE Vision, USB3 Vision, CoaXPress, Camera Link, and GenICam-compliant cameras. Always prefer videoinput from Image Acquisition Toolbox over webcam support package or gigecam.

Compose or improve a publication-grade multi-panel scientific figure from a claim, concrete data paths, or an existing image. Use for figure outlining, parallel panel rendering, exact-grid composition, visual inspection, and adversarial figure review. Use figure-style for one standalone plot and paper-narrative for whole-paper figure ordering.

Explain Wisp's current Modal boundary and migrate a requested Modal workload to a supported direct SSH Run when possible. Use when an existing workflow mentions Modal, BYOC cloud compute, provider images, or cloud GPU dispatch.

Extract text from images using a vision LLM

Extract transcripts from YouTube videos via the YouTube caption system

Integrates Amazon Location Service APIs for AWS applications. Use this skill when users want to add maps (interactive MapLibre or static images); geocode addresses to coordinates or reverse geocode coordinates to addresses; calculate routes, travel times, or service areas; find places and businesses through text search, nearby search, or autocomplete suggestions; retrieve detailed place information including hours, contacts, and addresses; monitor geographical boundaries with geofences; or track device locations. Covers authentication, SDK integration, and all Amazon Location Service capabilities.

When the user wants to plan, create, or repurpose visual content (images, infographics, social post images) across channels. Also use when the user mentions "content images," "social media images," "infographic," "visual content," "post image," "image specs," "visual repurposing," "content visuals," or "image for social post." For Pinterest, use pinterest-posts.

When the user wants to set up, optimize, or manage TikTok Ads. Also use when the user mentions "TikTok Ads," "TikTok for Business," "TikTok Pixel," "Events API," "TikTok Spark Ads," or "TikTok video ads." For organic TikTok, use tiktok-captions.

When the user wants to create TikTok video captions, scripts, or optimize for TikTok. Also use when the user mentions "TikTok post," "TikTok caption," "TikTok video," "post to TikTok," "TikTok script," "TikTok content," "TikTok copy," "TikTok hashtags," or "TikTok marketing." For TikTok ads, use tiktok-ads.

When the user wants to optimize images for search engines and performance. Also use when the user mentions "image SEO," "alt text," "image captions," "figcaption," "image optimization," "WebP," "lazy loading," "LCP," "image sitemap," "responsive images," "srcset," "image format," or "hero image optimization." For CWV, use core-web-vitals.

When the user wants to add or optimize Open Graph metadata for social sharing. Also use when the user mentions "Open Graph," "og:tags," "og:title," "og:image," "og:description," "Facebook preview," "LinkedIn preview," or "social share preview." For X (Twitter) link previews, use twitter-cards. For SERP title/description, use title-tag and meta-description.

When the user wants to add or optimize Twitter Card metadata for X (Twitter) link previews. Also use when the user mentions "Twitter Card," "twitter:card," "twitter:image," "twitter:title," "X preview," or "tweet preview." For Facebook/LinkedIn previews, use open-graph.

When the user wants to optimize videos for Google Search, video sitemap, VideoObject schema, or video SEO on websites. Also use when the user mentions "video SEO," "video sitemap," "VideoObject," "video thumbnail," "video indexing," "video preview," "key moments," "Clip schema," or "embedded video optimization." For page template, use article-page-generator.

This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.

Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy. Default to flagging; approval is earned.

Connect an MCP-capable coding agent to OpenChatCut and edit local video projects. Use when the user asks to install, connect, or set up OpenChatCut; inspect or edit an OpenChatCut project; work with its timeline, transcript, captions, media, generation, motion graphics, audio, color, or export tools; or recover from an OpenChatCut MCP error.

Use when acquiring or importing media into a OpenChatCut project asset library for video editing or creation, including local/attached videos, user-provided paths, public media URLs, web video/audio/image assets, upload fallback decisions, and deciding between import_media, download_media, or manual user action.

Create finished explainer videos from a topic, script, outline, voiceover, product logic, data, technical concept, course material, or reference assets. Use when the user wants narration, motion graphics, stock footage, generated visuals, or mixed visuals to explain an idea.

Use when a OpenChatCut video editing or creation workflow needs export, render, download, share, final delivery, subtitle-file export, render choice, local-only asset handling, or export fallback explanation.

| AI image generation via gpt-image-2, nano-banana, and MiniMax image-01. Use when the user wants to generate or create an image / picture / still.

Cut one long podcast, interview, course, livestream, or other source video into social-ready shorts, reels, highlights, or clip timelines from existing project media. Use when the user asks to cut a long video into Shorts, Reels, TikToks, Xiaohongshu posts, best moments, highlights, or multiple clips.

Add motion graphics at the right moments without blocking the story. Use when the user wants to enhance talking-head, lecture, tutorial, interview, podcast, or creator videos with motion graphics.

Turn multiple product shots, event footage, travel clips, gameplay moments, UGC/product footage, B-roll, or mixed media into social-ready reels, highlights, recaps, or montage-style short videos from existing project media.

| Music generation via Mureka and MiniMax. Use for instrumentals, songs, soundtracks, track/stem generation, or covers through `submit_music`.

Use for video editing or video creation work that should be editable in OpenChatCut, even when the user does not explicitly mention OpenChatCut. Covers local/attached video editing, captions/subtitles, transcription, trimming, talking-head cleanup, highlights, B-roll, overlays, generation, export, project/editor opening, importing, targeting, verifying, watching, and identifying the active OpenChatCut project/editor URL.

Turn a product into ad angles, hooks, scenes, and CTA.

| AI shader generator for WebGL video effects, transitions, masks, and color grading (LUT / 调色 / 电影感 / film look). Use when the user wants a video effect (滤镜 / 特效), a transition (转场 / crossfade / wipe / cube / 3d), a mask (蒙版 / 遮罩 / reveal), a zoom / push-in (推近 / 推镜头), or a color grade — try the built-in effects (zoom, builtin LUTs) before generating a new shader.

Break down each shot and turn the analysis into a storyboard reference. Use when the user wants shot-by-shot film analysis, director logic, cinematography breakdown, or a storyboard-style reference from a video.

| Guide for editing videos where the primary content is people talking — talking-head / 口播, interview / 访谈, lecture, tutorial, podcast, course content, and similar talking-driven formats. Use when the user wants speech editing on a talking video (剪口播 / 口播剪辑 / 去口癖 / clean up fillers / smooth speech), motion graphics layered onto talking video (口播加 MG / 加动画), or B-roll on a talking video (加 B-roll / add B-roll). For motion graphics specifically, use this together with the active Motion Graphics skill/workflow available in the current OpenChatCut environment — this skill adds talking-specific guidance (speech-rhythm timing, frame-aware placement, subject/caption protection, placement verification).