Video & Animation

Media intelligence layer for the DaVinci Resolve MCP. Uses FFprobe, FFmpeg, and optionally Whisper to READ and ANALYZE source media — never modify, transcode, convert, or create derivatives. Provides the MCP with full context of what footage actually is so it can take informed actions within Resolve.

Transcribe audio via OpenAI Audio Transcriptions API (Whisper).

Generate Guizang-style social card image sets, Live Photo motion cards, material-first Live Photo puzzle layouts, triple Live Photo collages, long-video-to-Live-Photo treatments, and WeChat official account cover pairs from articles, scripts, screenshots, product notes, subtitles, photos, or user-supplied videos. Use when the user asks for 小红书图文, Rednote/Xiaohongshu images, social cards, carousel images, 3:4 covers, Live Photo, 实况照片, 单视频实况拼图, 二宫格实况拼图, 三连实况拼图, 四宫格实况拼图, 微信公众号封面, WeChat 21:9 + 1...

Local speech-to-text with the Whisper CLI (no API key).

Render a static title / ending card PNG with Pillow. Centered headline + optional subtitle on a solid-colour background. Uses managed or platform CJK fonts with glyph verification and fails actionably instead of rendering tofu. Pure deterministic, no LLM, no network. Used by meta-short-drama for opening and closing cards.

OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.

Voice operations — make phone calls (Bland AI), text-to-speech (ElevenLabs), transcribe audio (Whisper/Groq). Replace OpenClaw voice capabilities.

Use when changing FlClash UI text, scanning for hardcoded Chinese strings, updating ARB localization, or fixing generated locale output in this repository.

Transcribe audio via OpenAI Audio Transcriptions API (Whisper).

Read-only repository explorer for cold-start orientation, broad cross-file localization, or when a direct search failed. Skip it when the exact file or symbol is already named. Returns path:line citations only; its reads stay out of main context.

Transcribe audio via OpenAI Audio Transcriptions API (Whisper).

Use when writing Playwright tests, fixing flaky tests, debugging failures, implementing Page Object Model, configuring CI/CD, optimizing performance, mocking APIs, handling authentication or OAuth, testing accessibility (axe-core), file uploads/downloads, date/time mocking, WebSockets, geolocation, permissions, multi-tab/popup flows, mobile/responsive layouts, touch gestures, GraphQL, error handling, offline mode, multi-user collaboration, third-party services (payments, email verification), ...

Use when creating a new Krayin CRM package or module, extending CRM functionality via a package, or adding custom business logic without modifying core files. Also use for any translation work — adding or moving lang files, adding a locale, or deciding whether a package gets its own Resources/lang directory — and whenever a fix or feature needs a CHANGELOG.md entry. Covers Laravel package structure, service providers, migrations, models, repositories, routes, controllers, views, localization,...

Provides comprehensive guidelines for translating and localizing Roo Code extension strings. Use when tasks involve i18n, translation, localization, adding new languages, or updating existing translation files. This skill covers both core extension (src/i18n/locales/) and WebView UI (webview-ui/src/i18n/locales/) localization.

Logseq i18n workflow for adding, renaming, reviewing, or editing translation keys and user-facing strings. Use when: writing UI code with hardcoded text, adding new user-facing strings, editing translation dict files, reviewing i18n compliance, working with notification/show!, adding translatable UI attributes, or any task involving src/resources/dicts/. Also use when the user mentions i18n, translation, localization, or hardcoded strings.

Integrate Novu's in-app notification inbox into web applications. Supports React, Next.js, and vanilla JavaScript. Includes the Inbox component (bell icon + notification feed), composable components (Bell, Notifications, InboxContent, Preferences), headless hooks, branded theming, custom render props, multi-tenancy via contexts, tabs, localization, and HMAC security. Use when adding an in-app notification center, bell icon, notification feed, real-time notification updates, or building a pers...

Write, extend, and review CKEditor 5 plugins in the Trilium (TriliumNext Notes) monorepo — the rich-text-note editor under packages/ckeditor5, whose plugins live in src/plugins/. Use when building or reviewing a Trilium CKEditor 5 feature/plugin, or when working with the editing engine (model, view, schema, conversion/upcast-downcast), commands, the UI library (buttons, dropdowns, dialogs, balloons, toolbars), widgets (block/inline, toWidget, nested editables), keystrokes, localization (t()),...

Localization rules and audit workflow for cmux UI strings, settings rows, menus, shortcuts, schema/config text, docs, command/help text, alerts, tooltips, and web messages. Use whenever changing user-facing text.

Expert knowledge for AI video clipping — yt-dlp downloading, whisper transcription, SRT generation, and ffmpeg processing

Use when adding, modifying, or reviewing Discourse content localization for core models or plugin models. Covers Localizable models, localization tables, source locale handling, hot-route serializer preloading, fallback behavior, manual editing UI, discourse-ai backfill/detection boundaries, plugin dependency constraints, and tests.

Burn timed subtitles onto a finished video or configure Whisper-timed caption burning during faceless-video assembly. Takes video/audio generation jobs or a local finished video, optionally with authored narration text, and returns a captioned video or the exact backend subtitle configuration. Timings always come from Whisper on the video's own audio — never estimated. THREE looks: `paper` (torn cream paper label, handwritten ink), `bold` (UGC ALL-CAPS, white with black stroke, platform safe ...

Guidelines for internationalizing a react-admin or shadcn admin kit application. Use when adding i18n support, creating translation files, translating hardcoded English strings in JSX, or reviewing i18n PRs in a react-admin project. Covers namespace conventions, interpolation, pluralization, locale-aware formatting, and the full workflow for converting an English-only app to multi-language. Trigger this skill whenever the user mentions i18n, internationalization, translation, localization, lo...

Synchronizes the UniGetUI English language file with source-code usage, identifies missing translation keys, removes unused entries, reports localization drift, and can reorder locale files to match the English key ordering. Use when the user asks to sync language files, missing translations, i18n drift, or align locale file ordering with English.

Transcribe a media file or live microphone to text or subtitles with auto-editor's whisper subcommand, then edit by spoken content — cut to keep (or drop) sections whose subtitles match a word or regex. Use when someone wants a transcript, captions, live speech transcription, or to cut a video based on what is said rather than on loudness.