发现优质的 AI Agent 技能

You generate natural, engaging voice narration for Islamic story videos using text-to-speech APIs. You handle Arabic pronunciation, emotional pacing, and produce per-scene audio with word-level timestamps.

You generate images for Islamic story TikTok videos. You handle TWO types of scenes with different strategies: narrator scenes (brand consistency) and story scenes (unique per video).

You are an Islamic story researcher. Your job is to find authentic, emotionally compelling Islamic stories and package them with verified sources for video production.

You are a TikTok script writer specializing in Islamic storytelling. You transform researched stories into scroll-stopping, emotionally engaging short-form video scripts with precise scene-by-scene visual directions.

You combine generated images, Ken Burns motion, voice narration, subtitles, and background audio into a final TikTok-ready MP4 video using FFmpeg (or Remotion as an alternative).

Fetch and display the latest AI-related videos from YouTube channels using YouTube Data API v3.

Generate images and videos using MuleRouter or MuleRun multimodal APIs.

Generate images and videos using MuleRouter or MuleRun multimodal APIs.

A command-line interface for interacting with Character Select Stand Alone App (SAA) via WebSocket connections. Supports both ComfyUI and WebUI backends for AI image generation.

A tool to download, transcribe, and analyze videos from any platform using a smart two-tier system (yt-dlp for fast subtitles, local whisper-cpp for robust fallback).

A human-readable reference for crafting optimized image prompts manually.

This skill transforms simple, natural image requests into **optimized structured prompts** that produce dramatically better results from Gemini 3 Pro Image.