Skill UI

This utility burns an SRT subtitle track directly into an MP4 video file using ffmpeg's libass filter. It re-encodes the video (H.264) while copying the audio untouched. It supports defining custom font fallback chains (e.g., CJK fonts) and provides detailed control over font size, margins, and video encoding parameters (CRF, preset) for professional subtitling workflows.

This skill converts a single static image (PNG/JPG) into a short, animated MP4 video using the Ken-Burns zoom effect. It is specifically designed as a robust fallback mechanism for automated video workflows. If an upstream AI video generation step fails—often due to content moderation flags (e.g., facial recognition or audio safety issues)—this animator ensures a valid placeholder clip is generated. This allows downstream merging steps to complete the deliverable without interruption, maintaining the narrative flow.

This system creates and registers high-quality, reusable synthetic voices (voice clones) from local audio samples. It operates under a strict, consent-first workflow, requiring explicit speaker consent, detailed use permissions, and source verification before cloning. It is designed for professional Text-to-Speech (TTS) applications, IVR systems, or training content development where a consistent, branded voice is essential.

This tool converts local source audio recordings into a specified, authorized target voice. It manages the complex workflow, including checking source and target voice rights, handling linguistic specifics (locale, accent), and performing previews before generating final assets. It is essential for professional narration, podcasting, and content localization while adhering to strict copyright and identity policies.

A comprehensive voiceover studio that transforms written text into high-quality, professional spoken audio. It supports generating content for podcasts, IVR prompts, educational videos, and product demos. The system handles complex requirements including target locale, specific accents (e.g., British, Mandarin), desired emotion, and pacing, ensuring the resulting audio artifact is natural and contextually accurate. Ideal for content creators and developers needing reliable, multi-lingual narration.

A powerful command-line tool for recording the macOS screen and capturing system audio simultaneously. Unlike QuickTime or standard `screencapture`, this tool captures raw display and system audio directly via ScreenCaptureKit, eliminating the need for complex virtual audio drivers (like BlackHole) or elevated permissions. It is designed for scripted content creation, automated demos, and complex recording scenarios where system audio is required via the CLI.

A powerful utility that queries multiple free APIs (Pexels, Pixabay, Internet Archive, etc.) in a single query. It retrieves normalized, license-tagged results for real-world, historical, or archival images, videos, and GIFs, making it a peer to local semantic search and generative media tools. Includes specialized scripts for fetching and judging audio.

This skill automates the NotebookLM AI research tool using browser automation via the Claude Chrome extension. It allows users to programmatically create new notebooks, add multiple sources (URLs, documents, text), and trigger complex output generations, such as mindmaps, audio overviews, and briefing documents, without manual clicking. Ideal for researchers and builders managing high volumes of source material.

A comprehensive skill for generating multimodal media content using fal.ai models. It supports text-to-image (Nano Banana), text/image-to-video (Veo, Kling, Seedance), and text/video-to-audio (CSM-1B, ThinkSound). Use this tool for any creative project requiring high-quality generated images, videos, or sound effects.

A comprehensive guide covering best practices for creating videos using Remotion and React. Learn how to incorporate advanced features such as 3D rendering (Three.js), complex animations, audio synchronization, data charting, subtitles, and sophisticated scene transitions. This skill covers 29 domain-specific rules for professional video pipelines.

RouterBase acts as a unified, OpenAI-compatible API gateway, allowing applications to route requests across diverse large language models (LLMs) like GPT, Claude, and Gemini. It helps developers migrate existing OpenAI SDK calls, implement sophisticated primary/fallback model selection based on cost, latency, and quality, and manage multimodal payloads (image, audio, video) from a single, standardized endpoint.

A comprehensive skill for ingesting, analyzing, and manipulating multi-modal video and audio content. Supports real-time desktop capture, live stream monitoring (RTSP), and file uploads (URL/local). Capabilities include advanced indexing (visual, semantic, temporal), precise moment searching, professional timeline editing (subtitles, overlays, dubbing), transcoding, and generating actionable alerts. Ideal for content creators, monitoring systems, and complex media workflows.