Skills for your AI
Turns audience data into engagement strategies, segmentation, trend analysis, and interactive video plans for video editors. Use when analyzing engagement metrics, monitoring sentiment, segmenting audiences, identifying trends, personalizing content, planning
Mixes and masters multi-track audio into balanced, platform-optimized final mixes with documented settings. Use when balancing multiple tracks, mastering to a loudness target, setting up spatial audio, optimizing for a platform, building effects chains, layeri
Aligns audio with video for editors, covering manual lip sync fixes, sound effect and dialogue timing, music beat mapping, level balancing, and automated sync scripts. Use when an editor reports out-of-sync audio, needs timing charts or level targets, or wants
Analyzes network traffic data and drafts bandwidth optimization, QoS, shaping, allocation, and capacity plans for network administrators. Use when asked to troubleshoot congestion, prioritize VoIP or video, report bandwidth usage, throttle or shape traffic, en
Fetch any URL and convert to markdown using baoyu-fetch CLI (Chrome CDP with site-specific adapters). Built-in adapters for X/Twitter, YouTube transcripts, Hacker News threads, and generic pages via Defuddle. Handles login/CAPTCHA via interaction wait modes. U
Downloads YouTube video transcripts/subtitles and cover images by URL or video ID. Supports multiple languages, translation, chapters, and speaker identification. Caches raw data for fast re-formatting. Use when user asks to "get YouTube transcript", "download
Turns a frontend project or webpage into a cinematic product video using real screenshots, 2.5D camera moves, beat-synced cuts, and sound design. Use when the user wants a promotional product video, a template-based or free-creation video, a single shot-card m
Builds production-ready computer vision pipelines for detection, OCR, face recognition, tracking, and model optimization. Use when the user needs to detect or count objects in images or video, extract structured text from scanned documents, implement face reco
Cleans, filters, deduplicates, and redacts PII from text, image, video, and audio datasets for LLM training using NeMo Curator. Use when the user asks to quality-filter a corpus, remove exact/fuzzy/semantic duplicates, redact PII, curate multi-modal data, or s
Use when the user asks to create a demo video, product walkthrough, feature showcase, animated presentation, marketing video, or GIF from screenshots or scene descriptions. Orchestrates playwright, ffmpeg, and edge-tts MCPs to produce polished video content.
Provides dialogue audio cleanup, leveling, sync, rewriting, transcription, accent, translation, and pacing guidance for video editors. Use when an editor describes noise, sibilance, plosives, reverb, uneven volume, muddy tone, lip sync drift, pacing problems,
Turns source material into a 60-90 second explainer video with script, HyperFrames composition, captions, voiceover, and delivery cuts. Use when asked to build an explainer video, write a video script, assemble a product walkthrough composition, or trim an exi
Turns scattered feedback from audio, video, surveys, and social media into transcripts, categorized lists, summaries, reports, highlight lists, and video scripts. Use when the user needs feedback transcribed, sorted, summarized, themed, reported, or compiled i
Generates 9:16 motion-graphics shorts in Remotion from a scene catalog by selecting a scene family, building a storyboard, and triggering a render. Use when the user wants to plan, confirm, render, or check the status of a Remotion short, browse available scen
Generates a single-file 1920×1080 cyberpunk glitch title frame in HTML for video transitions or hero sections. Use when the user asks for a glitch title frame or supplies a title and subtitle for one.
Turns a topic into a 45-60 second 9:16 explainer short in the Greg Isenberg motion-graphics style, covering script, storyboard, render and approval. Use when the user gives a topic for a short, asks to script, storyboard, render or preview one, or asks whether
Provides HeyGen API guidance and code examples for authentication, avatar video generation, assets, advanced features, and status polling. Use when a user asks how to authenticate with HeyGen, generate avatar videos, upload assets, use templates or translation
Turns game footage details and key-play timestamps into structured shot lists, music cues, pacing plans, and platform-specific cuts for sports highlight videos. Use when the user wants a highlight shot list, music suggestions, pacing help, or TikTok/YouTube ve
Turns a marketing brief into a complete short-form video ad package with hook options, script, storyboard, HyperFrames composition, captions, voiceover, and platform cuts. Use when the user provides a product or offer and wants a short-form video ad written, s
Plans and scripts interactive video elements—hotspots, quizzes, menus, forms, branching narratives, 360-degree hotspots, product showcases, maps, AR, and interactive tutorials or live streams—for video editors. Use when planning clickable links, overlays, quiz
Builds 15-30 second local business promo videos from owner-supplied photos and details, delivering 9:16, 1:1 and Google Business Profile cuts with captions and a poster frame. Use when an owner wants a promo for an offer, new item, event, announcement, hiring
Plans, troubleshoots, and evaluates multimedia-rich lessons, projects, and assessments for teachers. Use when a teacher needs interactive lesson ideas, media troubleshooting, tool comparisons, multimedia assessments, accessibility adaptations, collaborative pr
Transcribes audio files to text or English translation with Whisper, including batch runs and word-level timestamps. Use when the user supplies an audio file path and wants a transcript, translation, subtitles, or word timings.
Vertical short-form video editing workflow using Palmier Pro (the local desktop NLE controlled via MCP) instead of Descript. Produces a 9:16 vertical clip for YouTube Shorts, Instagram Reels, or TikTok: imports a local video file directly (no upload step neede
