Получение расшифровок видео (субтитров) и метаданных из онлайн-видеоисточников и их вывод в формате Markdown, JSON или обычного текста. В настоящее время поддерживается: (SKILL.md metadata excerpt)
Obtiene transcripciones (subtítulos) y metadatos de fuentes de video en línea y los emite en Markdown, JSON o texto plano. Actualmente compatible: (SKILL.md metadata excerpt)
Fetch video transcripts (subtitles) and metadata from online video sources and output them as Markdown, JSON, or plain text. Currently supported: YouTube. (SKILL.md metadata excerpt)
Fetch video transcripts (subtitles) and metadata from online video sources and output them as Markdown, JSON, or plain text. Currently supported: YouTube. (SKILL.md metadata excerpt)
Translate and dub videos from one language to another, replacing the original audio with TTS while keeping the video intact. (SKILL.md metadata excerpt)
Fine-tune vision-language models (VLMs) with supervised learning on image+text data. Use when adapting a VLM to a visual domain or task, configuring (SKILL.md metadata excerpt)
Apple Human Interface Guidelines for Apple Vision Pro. Use when building spatial computing apps, implementing eye/hand input, or designing immersive experiences. Triggers (SKILL.md metadata excerpt)