Menu

Individual skill

varg-video-editing

Which service to edit an existing video with, and how to edit it without breaking it. A routing guide for ten editing jobs: cut, trim, resize and join (FFmpeg, the varg ffmpeg tool, Rendi), talking-head cleanup (silence and filler cuts from word timestamps: auto-editor, Descript, ElevenLabs Scribe, Groq Whisper), long video to Shorts (OpusClip, or transcript + Gemini + FFmpeg), captions and subtitles (ASS through FFmpeg, Remotion, HyperFrames, Submagic, ZapCap), assembling from a timeline or template (HyperFrames, Remotion, Shotstack, Creatomate), AI edits that restyle, swap people, relight or extend (varg Recast/Relight/ID-V2V, Runway Aleph, Luma Ray, Wan VACE), dubbing and lip sync (HeyGen, ElevenLabs Dubbing, Sync Labs), upscaling, slow motion and background removal (Topaz, SeedVR, Bria), finding moments and QA (Gemini, varg video-analyze, Twelve Labs, VideoDB), and handing the cut to DaVinci Resolve, Premiere or Final Cut. Use when someone asks to edit, cut, trim, shorten, clip, reframe, caption, subtitle, translate, dub, lip-sync, upscale, restyle or clean up footage they already have, or asks which tool or API to edit video with. Not for making a video from a brief (varg-ai and the format skills).

plugins/vargHQ/skills/varg-video-editing/SKILL.md

Read pinned source

Source commit d780783eba4ecc7c8b9429f95c9362df95f07c61

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
No
Observed behavior
Network or broad shell
Last checked
Nov 4, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
1,532
Repository last updated
Nov 6, 2026
License
Apache-2.0

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# Video editing: which service, and how

Editing starts from footage that already exists, so the first rule is not to damage it. Work in this order, and pick the service for each step from the table below.

1. **Probe.** Run `ffprobe -v error -show_entries format=duration:stream=codec_type,codec_name,width,height,r_frame_rate,sample_rate -of json in.mp4`. Note the frame rate, whether it is variable, the sample rate and the duration.
2. **Transcribe once** if anyone speaks: word-level timestamps, saved as JSON next to the source. Every text decision reads from this file: silences, filler words, highlights, captions.
3. **Write the edit decision list** as data: source, in and out points, track, effect, the service for each step and its cost. Show it to the person and wait for a yes before any paid call. On varg, run `estimate_cost` first.
4. **Render deterministically** wherever you can (FFmpeg, HyperFrames, Remotion). Use a generative model only on the shortest span whose pixels must change. Cut that span out, edit it, and stitch it back.
5. **Verify.** ffprobe the output, grab stills at every cut point (`ffmpeg -ss <t> -i out.mp4 -frames:v 1 cut-<t>.jpg`) and look at them. Compare the duration with the edit list.

## Which service for which edit

The first service in each row is the default pick. Switch only for the reason given. The full table, with access, pricing and links, is in [references/services.md](references/services.md).