Video

videodb helps you ingest video and audio from local files, URLs, RTSP/RTMP live feeds, or desktop capture; search moments with timestamps and playable evidence; and act with clips, overlays, transcription, alerts, and timeline editing. It is a practical videodb guide for VideoDB for Video Editing and live-stream analysis.

The video-editing skill helps you turn existing footage into polished, platform-ready videos faster. It focuses on cutting, structuring, captioning, reframing, and light augmentation for vlogs, tutorials, demos, short clips, and interview edits. Best when you already have raw footage and need a practical video-editing guide.

ui-demo helps you record polished web app demo videos with Playwright, visible cursor movement, and natural pacing. Use the ui-demo skill for walkthroughs, onboarding clips, feature tours, and tutorial-style recordings. Follow the discover, rehearse, then record workflow for reliable results, especially for prototypes and fast-changing UIs.

remotion-video-creation is a Remotion-focused skill for React video work. It helps reduce rendering mistakes with 29 rules covering animations, assets, audio, captions, charts, compositions, and transitions. Use it for Video Editing workflows, templated explainers, social clips, and data-driven motion graphics.

manim-video helps you plan and produce clean Manim-based explainer videos for graphs, workflows, system diagrams, product walkthroughs, and launch visuals. Use the manim-video skill when you want a precise animated explanation with a scene-first workflow, not a talking-head edit. It includes practical manim-video guide steps for install, scene planning, and rendering.

transcribe turns audio or video into text with optional diarization and known-speaker hints. It is well suited for Technical Writing, meeting notes, interviews, lectures, and content ops when you need a repeatable transcribe skill with clear output formats and less guesswork than a generic prompt.

baoyu-youtube-transcript helps extract YouTube transcripts, subtitles, and cover images from a URL or video ID. It supports language selection, translation, markdown or SRT output, cached reformatting, and a fallback from InnerTube API to yt-dlp for more reliable transcript retrieval.

Use the remotion skill to turn Stitch project screens into polished walkthrough videos with transitions, zooms, and text overlays. It includes install steps, example files, and a repeatable remotion guide for video editing and render-ready compositions.

website-to-hyperframes is a workflow skill for turning an existing website into a HyperFrames video. Use it when you have a URL and want a product tour, promo, social ad, or explainer grounded in the site’s real design, copy, and assets. The repo supports capture, design, script, storyboard, VO, build, and validation for Design Implementation work.

hyperframes is a workflow skill for building HTML-based video compositions in HyperFrames. Use it for title cards, overlays, captions, voiceovers, audio-reactive motion, and scene transitions when you need structured, code-first hyperframes for Video Editing. It favors layout, timing, and animation decisions over generic prompt-only video requests.

hyperframes-cli is the HyperFrames CLI skill for building, validating, previewing, and rendering video projects from the terminal. Use it for project scaffolding, linting compositions, previewing edits, transcription, TTS, diagnostics, and repeatable hyperframes-cli usage in AI-assisted video editing workflows.

remotion-best-practices is a Remotion skill guide for install, usage, and rule-based workflows covering animation, assets, audio, captions, FFmpeg, and calculateMetadata.

azure-ai-contentunderstanding-py is the Python skill for Azure AI Content Understanding. It extracts structured content from documents, images, audio, and video for RAG workflows and automation. Use it when you need reliable multimodal extraction, Azure authentication, and repeatable pipeline-ready output.

The youtube-clipper skill is an installable workflow for clipping YouTube videos into usable segments, subtitle variants, and short summaries. It supports youtube-clipper usage for video editing, bilingual subtitles, and export-ready clips with less manual work than a generic prompt.

app-preview-video helps you plan, script, and optimize App Store Preview videos and Google Play promo videos for product pages and landing pages. Use this app-preview-video guide to choose the right opening, fit platform specs, and turn screen recordings into a conversion-focused preview video.

The video-translation skill translates spoken content in a video into another language, generates TTS dubbing, and replaces or mixes audio while keeping the video intact. It is best for practical video-translation usage when you have a source video, subtitles, and a target language for Translation.

The speech-to-text skill transcribes supported audio files into plain text, with options for timestamps, speaker labels, and JSON output. It is designed for practical speech-to-text usage in repeatable workflows, including interviews, meetings, podcasts, lectures, and automation tasks where consistent transcription matters.

The tts skill turns text into speech audio for narration, dubbing, voiceover, and timeline-aligned playback. Use it to generate a voice file from plain text, convert articles or text files to speech, or render SRT-driven audio with timing control. It supports simple and timeline modes, plus backend-aware workflows for repeatable tts usage.

chat-with-anyone helps you clone a real person's voice from public audio or design a matching voice from an image, then generate synthetic replies with TTS. It supports practical workflows for roleplay, narration, and voice generation, with guidance on install, source selection, and safe usage.

videoagent-video-studio is a skill for generating short AI videos from text, images, and references. Use it to test text-to-video and image-to-video workflows, compare supported models, and run the hosted proxy or self-hosted setup with Node 18+.

videoagent-image-studio is a unified image generation skill for Node-based agents. It offers one CLI flow for Midjourney, Flux, Ideogram, Recraft, SDXL, and more, with proxy-backed setup, model selection guidance, and normalized outputs for automation.

pexoai-agent is a shell-backed skill for creating short videos through Pexo’s hosted AI video service. It covers setup with ~/.pexo/config, dependency checks with pexo-doctor.sh, project creation, async submission, polling, uploads, and asset retrieval for repeatable video production workflows.

veo-3.2-prompter is a prompt-design skill for Google Veo 3.x workflows. It helps turn mixed assets and rough intent into a structured JSON prompt with reference-role mapping, recommended parameters, and practical guidance for install, usage, and Veo-ready prompt writing.

seedance-2.0-prompter helps turn multimodal Seedance 2.0 assets into structured prompts with clear roles, @asset syntax, and reusable templates for install, setup, and practical usage.