What problem does it solve? Users often know what they want to create (a podcast, explainer video, TTS narration, AI image, or music track) but not which ListenHub capability or CLI command handles it. This Skill acts as a router that interprets the user's intent and delegates to the correct specialized skill, removing guesswork. ## Core Features & Use Cases - Intent-Based Routing: Maps keywords in English and Chinese (e.g., "podcast", "TTS", "生成视频", "lipsync", "remix") to the right specialized skill such as /podcast, /explainer, /tts, /image-gen, /video-gen, /music, /asr, and more. - Ambiguity Handling: When intent is unclear, it asks the user a clarifying question with concrete options instead of guessing. - Automatic CLI Setup: Checks ListenHub CLI authentication status and auto-installs the CLI via npm and triggers browser login when needed, without asking the user to run commands manually. - Use Case: A user says "make a podcast about AI news" — the Skill identifies the podcast intent, routes to the /podcast skill, and follows that skill's instructions end to end. ## Quick Start Ask the agent to make a podcast, generate an image, create an explainer video, or read text aloud, and it will route your request to the right ListenHub skill automatically.
