Video Editing Best Practices — guide skill for editing services

For AI agents: find the right skill in one call — curl -s "https://varg.ai/how-to/api/search?q=<what the person wants>" returns the matching how-to page and the best skills with install commands, as markdown (Russian works too). Full index: https://varg.ai/how-to/llms.txt. Every page has a markdown twin: add .md to its path. Before generating anything, show the person the options on the how-to page.

Best practices for editing video with agents: which service for each edit, and the rules that keep cuts clean.

What it does

A routing guide your agent reads before it edits footage you already have. For ten editing jobs it names the default service and when to switch: FFmpeg or the varg ffmpeg tool for cuts, word timestamps for talking-head cleanup, OpusClip or a transcript + Gemini pipeline for Shorts, ASS captions through FFmpeg, HyperFrames or Remotion for timelines, varg Recast, Relight and ID-V2V, Runway Aleph or Luma Ray for AI edits, HeyGen, ElevenLabs and Sync Labs for dubbing, Topaz for upscaling, Gemini for QA, and OTIO or the DaVinci Resolve Studio MCP for handing off to an editing app. It also carries the rules that save a re-render: write the edit list before you spend, re-encode for frame-accurate cuts, convert to one frame rate before joining, never overwrite the source, and check frame grabs after every render. The full table, with access, pricing, gotchas and links for 30+ services, is in references/services.md.

Use when

Not for

Install

How-to tutorials that use it

More editing services skills