autoshorts

Automate long-form video repurposing into scheduled short-form social clips.

125|23|Updated May 1, 2026
One-click install
npx skills add https://github.com/Upload-Post/skill-autoshorts --skill autoshorts
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: autoshorts
Source: https://github.com/Upload-Post/skill-autoshorts/tree/main
Command: npx skills add https://github.com/Upload-Post/skill-autoshorts --skill autoshorts

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires faster-whisper, google-genai, requests, python-dotenv, Pillow, and includes scripts (resource) components.

What problem does it solve?

This skill solves the time-consuming bottleneck of manually editing long-form video content into short, viral clips for social media, while maintaining a human-in-the-loop approval process.

Core Features & Use Cases

  • AI-Driven Clipping: Uses Gemini 3 Flash to identify viral moments and Whisper for precise, word-boundary-accurate cuts.
  • Automated Hook Overlays: Automatically renders and composites TikTok-style hook text overlays onto clips using FFmpeg and Pillow.
  • Multi-Platform Scheduling: Integrates with the Upload-Post API to manage drafts and scheduling across TikTok, Instagram, and YouTube.
  • Use Case: A content creator can drop a 30-minute podcast episode into a folder, and the skill will automatically generate, hook, and queue the best 5 clips for the week.

Quick Start

Set up the autoshorts skill by running the installation protocol defined in the repository documentation to configure your environment and API keys.

Frequently Asked Questions about autoshorts

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate repurposing long-form video into short-form social media clips?

You can automate video repurposing by using a pipeline that transcribes long-form video, identifies viral moments with multimodal AI, renders hook text overlays, and schedules clips across platforms. This pipeline handles transcription, clip selection, visual rendering, and multi-platform scheduling end-to-end.

What's the best way to turn a 30-minute podcast into multiple TikTok clips?

The best way to turn a 30-minute podcast into TikTok clips is to drop the file into a watch folder, letting AI-driven clipping identify viral moments, Whisper generate word-boundary-accurate cuts, and FFmpeg composite hook text overlays automatically. The skill then queues the best clips for the week.

Do I need FFmpeg and Python 3.11 to run automated video clipping and scheduling?

Yes, you need local FFmpeg, Python 3.11+, and configured API credentials for Gemini and Upload-Post to run automated video clipping and scheduling. These dependencies are required for transcription, hook rendering, and multi-platform scheduling.

Can I schedule draft clips across TikTok, Instagram, and YouTube automatically?

Yes, you can schedule draft clips across TikTok, Instagram, and YouTube automatically via the Upload-Post API. The pipeline manages drafts and multi-platform scheduling after generating and rendering the short-form clips.

Does AI-driven content repurposing maintain a human-in-the-loop approval process?

Yes, AI-driven content repurposing maintains a human-in-the-loop approval process by queuing generated clips as drafts. You can review and approve the automatically selected, hook-overlaid short clips before they are scheduled across social media platforms.

What are the limitations of using Gemini and Whisper for automated video clip selection?

Limitations of using Gemini and Whisper for automated video clip selection include the requirement of external API credentials, local FFmpeg installation, and Python 3.11+ environment setup. The pipeline also relies on a human-in-the-loop approval process rather than fully autonomous posting.