video-edit

Transcribe footage, plan cuts, and render videos with overlays.

Updated May 3, 2026

Search Tags:#automation #transcription #ffmpeg #video editing #overlays #hybrie

Ready to run

npx skills add https://github.com/tosi-n/agentic-frame --skill video-edit-tosi-n

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: video-edit
Source: https://github.com/tosi-n/agentic-frame/tree/main/skills/video-edit
Command: npx skills add https://github.com/tosi-n/agentic-frame --skill video-edit-tosi-n

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires httpx, numpy, pillow, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

Automates complex video editing tasks by enabling precise cuts, overlays, and transcriptions, reducing manual effort and ensuring consistency.

Core Features & Use Cases

Automated Video Cutting: Uses transcripts and speech boundaries to produce accurate edits without watching footage.
Overlay and Animation Integration: Adds visual elements, subtitles, and animations in a deterministic way for polished outputs.
Use Case: A content creator rapidly assembles a tutorial with automated transcriptions, scene cuts, and synchronized overlays, saving days of editing.

Quick Start

Use the video-edit skill to transcribe footage, plan edits, and render a final video aligned with the transcript.

Frequently Asked Questions about video-edit

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

FAQPage Schema

How do I automate video editing using transcription and speech boundaries?▼

Automated video editing uses transcripts and speech boundaries to generate precise cuts without manual review. The system processes speech recognition data to determine edit points, applies deterministic rendering, and outputs a final video with synchronized overlays.

Can I add visual overlays and subtitles automatically during video rendering?▼

Yes, automated video rendering can apply visual overlays, subtitles, and animations deterministically. The system integrates these visual elements based on transcript timestamps, ensuring subtitles and overlays remain synchronized with the video footage.

What is the best way to cut video footage without watching the entire recording?▼

Cutting video footage without watching relies on transcription-based editing. By analyzing speech recognition outputs and detecting speech boundaries, the system identifies active segments and automatically removes silences, producing accurate edits with minimal manual intervention.

Does automated video editing work with Python dependencies like numpy and pillow?▼

Automated video editing workflows utilize Python dependencies including numpy and pillow for processing. These libraries support visual overlay generation, image manipulation, and array handling required for deterministic rendering and quality grading of the final video output.

How does automated transcription improve video editing workflows for content creators?▼

Automated transcription improves video editing workflows by converting speech to text for accurate scene planning. Content creators use transcripts to locate edit points, apply cuts, and generate subtitles, reducing manual effort and saving days of editing time.

What are the limitations of using AI-driven cuts for video post-production?▼

AI-driven cuts for video post-production rely on speech recognition accuracy and clear audio boundaries. Limitations include potential misalignment in noisy audio environments and the need for manual review when complex visual scene detection is required beyond speech boundaries.