Pre-Flight：多智能体AI系统，在发布前模拟观众对短视频片段的反应——基于Google ADK、Gemini 2.5 Flash、BigQuery MCP和FFmpeg.wasm构建。
Pre-Flight 是一个多智能体AI系统，专为短视频创作者设计，在正式发布前模拟目标观众对视频片段的反应。该系统基于 Google ADK 框架、Gemini 2.5 Flash 模型、BigQuery MCP 数据连接以及 FFmpeg.wasm 视频处理技术构建。它通过模拟不同观众群体的情感、兴趣和互动可能性，帮助创作者预判内容表现并优化策略。目前主要在 GitHub 上作为开源项目发布，适用于 AI Agent 平台（如 Claude Code、Cursor、Codex）的集成与扩展。其核心价值在于降低发布风险、提升内容吸引力，尤其适合对数据驱动的创意决策有高需求的团队。
npx skills add HassaanFisky/quickaishortPre-Flight: Multi-agent AI system that simulates audience reactions to short-form video clips before publishing — built on Google ADK, Gemini 2.5 Flash, BigQuery MCP, and FFmpeg.wasm
Source: https://github.com/HassaanFisky/quickaishort
Discovered during the daily awesomeskills.dev agent-skill hunt.
Extract frames or short clips from videos using ffmpeg.
Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files.
Production-ready animation patterns for React / Next.js — button, modal, toast, stagger, page transitions, exit animations, scroll, and layout — built on motion-foundations tokens and springs.
Advanced motion patterns for React / Next.js — drag & drop, gestures, text animations, SVG path drawing, custom hooks, imperative sequences (useAnimate), loaders, and the full API decision tree. Requires motion-foundations.
Production-ready UI motion system for React/Next.js. Use when implementing animations, transitions, or motion patterns.
Generates Angular code and provides architectural guidance. Trigger when creating projects, components, or services, or for best practices on reactivity (signals, linkedSignal, resource), forms, dependency injection, routing, SSR, accessibility (ARIA), animations, styling (component styles, Tailwind CSS), testing, or CLI tooling.