Media Skills

Generate product demo videos for websites and SaaS apps using Remotion. Scans the target project's codebase, proposes custom scenes with browser mockups, and writes bespoke .tsx scene files using shared animation primitives. Web apps only. Use when the user wants to create a demo video, product walkthrough, landing page hero video, or marketing video for a website or web app. Builds on appshot-core foundation.

Generate App Store / Google Play preview videos using Remotion. Scans the target app's codebase, proposes custom scenes, and writes bespoke .tsx scene files using shared animation primitives. Mobile apps only (iOS/Android). Use when the user wants to create a demo video, app preview, promo video, or marketing video for a mobile app. Builds on appshot-core foundation.

> Guides digital forensic evidence collection following NIST SP 800-86 and RFC 3227 order of volatility. Auto-invoked when the user needs to collect forensic evidence, preserve chain of custody, capture volatile data, create disk images, or handle cloud forensics. Produces an evidence collection plan with volatility-prioritized acquisition steps, integrity verification, and chain-of-custody documentation.

将经过匿名化的真实经历、观察和观点转化为具有 ALLY 式跨域判断、商业洞察、人格反差和脱口秀节奏的中文内容。用于生成或修改口播稿、短视频脚本、X 长文、标题、开头、结尾、暴论和社交媒体文案；也用于内容“太像AI、太像老师、不够狠、不够好笑、没有本人”时的重写。不得暴露真实姓名或可反向识别的私人信息，不得伪造 ALLY 的个人经历、交易结果或商业事实。

DevExpress WinForms Loading Indicators — SplashScreenManager (namespace DevExpress.XtraSplashScreen) is the single entry point. Covers four types: (1) Splash Screen for app startup — Fluent (ShowFluentSplashScreen with FluentSplashScreenOptions, FluentLoadingIndicatorType Dots/Ring/Spinner), Skin, Default, and Splash Image, shown before Application.Run() and closed via CloseForm(); (2) Wait Form — a modal full-form overlay for long operations (ShowWaitForm, SetWaitFormCaption/Description, SendCommand, CloseWaitForm); (3) Overlay Form — a semi-transparent overlay over a control (ShowOverlayForm returning IOverlaySplashScreenHandle, CloseOverlayForm in try/finally, custom painting); (4) ProgressPanel — an inline control with Caption, Description, WaitAnimationType Ring/Line/Bar. NuGet DevExpress.Win.Navigation; host on XtraForm/RibbonForm. Use for splash screens, wait indicators, busy overlays, and progress panels.

Expert skill for the DevExpress WinForms TreeList control (DevExpress.XtraTreeList.TreeList, DevExpress.Win.TreeList NuGet) — a data-aware control that shows data as a tree, a multi-column tree-grid, or both. Use when binding self-referential data (KeyFieldName, ParentFieldName, RootValue), building unbound trees in code (AppendNode, BeginUnboundLoad/EndUnboundLoad), dynamic on-demand loading (TreeListNode.HasChildren + BeforeExpand), defining TreeListColumn and unbound columns (UnboundExpression), in-place editors (ColumnEdit, RepositoryItems), sorting, filtering (ActiveFilterString, Find Panel), summaries, conditional formatting (FormatRules), node operations (FocusedNode, FindNodeByKeyID/FieldValue, Expand/Collapse, checkboxes, images), drag-and-drop, printing, and export. Use when a user asks about WinForms tree, TreeList, XtraTreeList, hierarchical grid, tree-grid, org charts, file/folder trees, parent-child data, TreeListNode, or multi-column tree view. For flat tabular data use the Data Grid instead.

Configure Tongji Look credentials, check system dependencies (Python, Node.js, ffmpeg, vision-support, XeLaTeX), and set up the persistent course-wiki workspace.

为非多模态模型（如 deepseek-v4-pro、GLM-5.1、mimo-v2.5-pro 等纯文本模型）提供图片识别能力。当主模型无法识别图片、用户发送了截图/设计稿/UI 截图需要分析、或者用户说'看看这张图'、'分析这个截图'、'这张图片有什么问题'时，自动触发此技能。也适用于用户粘贴了图片但当前模型不支持图片输入的任何场景。支持同时识别多张图片，通过配置多个识图模型实现主备回退。使用指令 /skill:vision-support 或 /vision 也可手动触发。铁律：本技能配置的模型仅用于图片内容识别，绝不参与主逻辑推理。注意：如果当前模型本身是多模态模型（如 Claude Sonnet 4、GPT-4o、Gemini 等可以直接识图的模型），不要使用此技能，直接让主模型识别即可。

Transcribe a single Tongji Look lecture video to SRT + TXT, optionally download slide snapshots in parallel.

Visualize business domains as standalone HTML + inline-SVG artifacts using an opinionated editorial design system. Ships six domain-modelling types — Aggregate, Context Map, Event Storm, Context Canvas, Ubiquitous Language glossary, and Domain Model — for exploring DDD designs with stakeholders, capturing decisions from event-storming sessions, or documenting a bounded context in a repo. Use this skill whenever the user wants to sketch, explore, or document a business domain — triggered by mentions of DDD, domain-driven design, bounded contexts, aggregates, event storming, ubiquitous language, context mapping, or any request to "visualize the domain", "draw the model", "map the contexts", "show the aggregate", or "help me think through the business". Shares a skinnable style guide with diagram-design so technical and domain diagrams produced for the same project look like siblings.

Локальная транскрибация аудиофайлов без отправки в облако. Используй когда пользователь просит транскрибировать запись, расшифровать аудио, сделать конспект встречи, преобразовать речь в текст. Только для аудио (m4a/mp3/wav/ogg/flac/aac/wma/opus). Движок: faster-whisper CUDA + опц. диаризация sherpa-onnx GPU (CUDA, RTF ~0.24). Поддерживает разделение по спикерам.

Image generation with Google Gemini API. Models: gemini-2.5-flash-image (fast) or gemini-3-pro-image-preview (quality). For social media graphics, marketing, infographics.

Build agents that generate creative content including music, memes, podcasts, and multimedia. Covers generative models, content synthesis, style transfer, and creative control. Use when building creative assistants, automated content creators, multimedia generators, or artistic AI systems.

Download and retrieve video content from sources. Extracts media files with proper format handling and metadata preservation.

Create and edit presentation documents with full formatting. Handles slide creation, layouts, animations, and speaker notes programmatically.

Download and archive YouTube video content. Retrieves videos with metadata while respecting platform policies.

Enhance and improve image quality and visual content. Applies enhancement techniques, color correction, and optimization transformations.

Build voice-enabled AI applications with speech recognition, text-to-speech, and voice-based interactions. Supports multiple voice providers and real-time processing. Use when creating voice assistants, voice-controlled applications, audio interfaces, or hands-free AI systems.

Master orchestrator that chains all Remotion video creation skills together in a single automated pipeline. Takes a creative brief and produces a complete, production-ready Remotion video project. Use when starting a new video from scratch, when asked to "create a video", "make a video", "build a complete video", or "video from idea to code".

Advanced motion designer with decades of After Effects and motion graphics experience, specialized in creating engaging video specifications for Remotion. Use when creating video specs, planning motion graphics, designing animations, or when asked to "create a video", "design motion graphics", "plan video content", or "spec out a video". Produces detailed scene-by-scene specifications with timing, audio, sound effects, and animation descriptions.

Generates animation configurations for Remotion including spring configs, interpolations, easing functions, and timing logic. Focuses ONLY on animation parameters, NOT component implementation. Use when defining animation behavior or when asked to "configure animations", "setup spring configs", "define easing curves".

Analyzes Remotion compositions for performance issues and provides optimization recommendations. Identifies expensive computations, unnecessary re-renders, large assets, memoization opportunities, and architecture improvements. Use when optimizing render times or when asked to "improve performance", "speed up renders", "optimize Remotion video".

Generates individual Remotion scene components from visual direction. Input is visual/animation description for a specific scene. Output is SCENE_COMPONENT.md with complete TSX implementation. Use when implementing scenes or when asked to "create a scene component", "implement scene from spec", "build Scene1Intro".

Generates render and output configuration for Remotion videos. Focuses ONLY on output settings, codec, format, quality, resolution. Input is target platform/quality requirements. Output is RENDER_CONFIG.md with Remotion render settings.

Orchestrates translation of motion designer video specifications into working Remotion code by coordinating specialized agents. Acts as pipeline coordinator that delegates to remotion-scaffold, remotion-animation, remotion-composition, and remotion-component-gen. Use when you have a complete VIDEO_SPEC.md and need full Remotion implementation.

Structured review process for Remotion video implementations. Analyzes spec compliance, detects common timing/easing issues, validates asset quality, and provides prioritized revision lists. Use when reviewing Remotion code against design specs or performing quality assurance on video compositions. Trigger phrases "review video code", "check spec compliance", "audit Remotion implementation".

> Load this skill whenever the project contains audio or video content, media players, podcasts, video embeds, or any <audio>/<video> elements. Under no circumstances publish audio or video without captions, transcripts, and audio descriptions where required. Absolutely always apply WCAG 1.2 criteria for time-based media.

> Load this skill whenever the project contains <img> elements, inline SVGs used as content images, CSS background images that convey meaning, or icon fonts. Under no circumstances omit alt text on meaningful images. Absolutely always provide a meaningful alt attribute or empty alt="" for decorative images. Apply WCAG 2.2 SC 1.1.1 — every non-text element requires a text alternative.

> Load this skill whenever the project contains SVG graphics — inline SVGs, external SVG files, SVG icons, SVG illustrations, or SVG-based data visualizations. Under no circumstances use SVG without proper accessible titles, descriptions, and ARIA roles where required. Absolutely always add <title> and <desc> to meaningful SVGs and set role="img" with aria-labelledby pointing to those elements. Also apply this skill whenever the project accepts untrusted or user-uploaded SVG content, which requires sanitization before rendering.

> Load this skill whenever the project must support speech input or voice control — dictation, "click by voice" grammars, Dragon NaturallySpeaking, Voice Control (iOS/macOS), Voice Access (Android), or any interface where users activate controls by speaking. Under no circumstances let an aria-label override a visible label without keeping the visible text intact and in order. Absolutely always ensure the accessible name contains the visible label, and load alongside keyboard/SKILL.md since speech tools commonly emulate keyboard and pointer input.

>- Upload local images to a GitHub PR and embed them in the description or comments. Use when asked to "attach screenshots to PR", "add images to PR", "upload test results to PR", "embed screenshots in PR description", "add before/after images to PR", "attach UI screenshots", "show test results in PR", "add visual evidence to PR", or any request involving images and PRs. Always use this skill when the user wants to visually document changes in a pull request, even if they don't use the word "upload" — phrases like "put the screenshot in the PR" or "show the image in the PR" should trigger this skill. Prefers Chrome DevTools MCP (most stable) as the browser automation backend, falling back to Playwright MCP or agent-browser only when Chrome DevTools MCP is unavailable.

Deterministic workflow to find and export full podcast transcripts as cleaned TXT files from YouTube URLs, episode webpages (including Xiaoyuzhou), Apple Podcasts title search, X/Twitter links, direct audio URLs, or plain episode titles. Use when users ask for 逐字稿/文字版/transcript/txt and want minimal trial-and-error.

| 抖音视频解析、博主视频抓取/转录/运营分析/写入飞书。 触发词：解析抖音、抖音视频、抓取视频、博主视频、创作者视频、douyin、抖音解析、飞书多维表格 子命令：

Use when the user asks to create, generate, visualize, or turn material into a standalone HTML artifact, self-contained or single-file .html report, interactive explainer, interactive illustration or visualization, visual walkthrough or handoff, or HTML presentation or slide deck. Handles source-grounded codebase and architecture, feature, PR or diff, implementation recap, incident timeline, option comparison, causal, and data-report explanations. Not for prose-only analysis or reviews, production web apps or dashboards, websites, HTML email, or ordinary frontend/UI implementation.

Generate images using Google Gemini with customizable options

Generate images using OpenAI gpt-image-2 with customizable options

Use when starting a new feature, writing a spec, or brainstorming architecture and you want to capture richer intent than typing allows. Speak your thoughts into a transcription tool, then feed the raw transcript to Claude Code for structuring.

Migrate a Microsoft InfoPath form (.xsn) to a Power Apps Canvas app. USE WHEN the user wants to convert, port, or migrate an InfoPath form/template to Canvas Apps, or asks for help moving off of InfoPath.

Read the YAML files of an existing Canvas App and replace Power FX data source calls with equivalent Dataverse table calls. USE WHEN the user wants to migrate, replace, or update data source references in pa.yaml files to point to Dataverse tables.

Analyze and audit a Power Apps canvas app. USE WHEN the user wants to analyze, profile, audit, review, diagnose, or improve a Canvas App or pa.yaml files. USE FOR: slow apps, long load times, delegation warnings, N+1 database calls, excessive collections, ForAll optimization, OnStart overload, Named Formulas, Concurrent execution, Explicit Column Selection, DelayOutput on text inputs, cross-screen control references, Power Automate overuse, unused variables, nested galleries, error handling, App.OnError, form validation, naming conventions, variable scope misuse, modern controls, responsive layout, accessibility. DO NOT USE WHEN the app has not been synced locally yet — sync it first.

Analyze images using LLM vision APIs (Anthropic Claude, OpenAI GPT-4, Google Gemini, Azure OpenAI). Use when tasks require: (1) Understanding image content, (2) Describing visual elements, (3) Answering questions about images, (4) Comparing images, (5) Extracting text from images (OCR). Provides ready-to-use scripts - no custom code needed for simple cases.

> Build a new opinionated advisor-persona skill — a reviewer "lens" like crusty-old-engineer — modeled on a real person or archetype and proven from real evidence. Mines the subject's authentic voice and discipline, defines its one distinct load-bearing question, drafts it to the family template, proves it steers in a live session, reduces it, and publishes it to a skills bundle. Use when creating or authoring a persona/advisor skill, adding a sibling to the crusty-old-engineer family, or turning a person's real direction style into a reusable reviewer skill. Also triggers on "personafy" / "personify".

| User-need reviewer that speaks for the person who isn't in the room — the one who will actually live with what gets built. Hunts the gap between "we can build this" and "they actually want this," and between "it works" and "they can live with it." Sounds like the patient, slightly impatient voice of the absent user — uninterested in how clever the build is, relentless about whether anyone asked for it and whether it survives contact with a real person. Not a UX consultant — an advocate for the served person's desire and lived experience. A lens for any checkpoint — brainstorm, design, plan, implement, debug, or review — not just design. celebrated while the recovery path is missing, or nobody can name the person this serves — any time the worry is "does the person we serve actually want this, and can they live with it?"