# This Skill Turns Claude Code Into an Expert Video Editor (I'm Giving It Away)

## Executive summary

This presentation details an advanced AI-driven video editing pipeline, where a 'skill' guides a coding agent (like Claude Code) to transform raw footage into polished content. The core process involves a scripted sequence of steps—transcription, cutting, assembly, and polishing—which can be augmented using multimodal APIs (OpenRouter) for complex tasks like voice cloning and thumbnail generation.

## Key takeaways

- The Core Editing Pipeline: The process is scripted and deterministic, moving from raw input to final export through five main stages: transcription (with timestamps), retake removal/cutting (dead air, breaths), assembly, polishing (transitions/animations), and final validation.
- Multimodal Augmentation: The 'full pipeline' utilizes OpenRouter to access multimodal capabilities that local LLMs lack, including video understanding, image generation (for thumbnails), and voice cloning (e.g., Fish Audio 2.1 Pro).
- Customization and Flexibility: The skill is designed to be modular; users can customize the process by adjusting the steps, adding new steps, or modifying 'lessons.mmd' (hard rules) and 'brand.json' (colors) to fit specific content types (e.g., talking head, screen+face panel, shorts).
- AI-Detected Fixes: The system demonstrated the ability to detect and fix subtle issues, such as small stumbles mid-word or choppy audio, through self-iteration and validation steps.

## Technical details

- Skill Architecture: The `edit-video` skill guides the coding agent through a sequence of helper scripts. These scripts handle deterministic tasks (e.g., transcription, pause detection) that an LLM cannot perform alone, providing data back to the main orchestrator.
- Validation Process: A validation step involves retranscribing the output and performing a word-by-word diff against the source transcripts to ensure cuts were made at the correct timestamps.
- Model Usage: The full pipeline utilizes specific models via OpenRouter for complex tasks: Gemini 4 Argon for video review, Fable 5.2 for planning, and Fish Audio 2.1 Pro for voice cloning.

## Practical implications

- Automate the transformation of raw, messy footage into polished, branded content, reducing the need for manual editing.
- Implement a robust content generation workflow that handles everything from initial cutting to final thumbnail creation.
- Use the skill as a starting point, allowing build engineers to customize the steps and scripts to meet unique content requirements.

## Topics

AI, Video Editing, LLM Automation, Agentic Workflow, Open-Source Tools, edit-video skill (free and open source), OpenRouter API

Source: https://www.youtube.com/watch?v=a90pZ1DSyls
