agentleFS
youneslaaroussiyouneslaaroussi/vidova-skills/skills/beat-sync-edit/SKILL.md

beat-sync-edit

Skill1 starsChanged 7 days agoMITView on GitHub

Make a beat-synced edit with Vidova, the AI video editor. Use when someone asks for an edit cut hard to a song: a fan edit, a car or bike edit, a gaming, anime or movie montage, a phonk or hype edit. Vidova cuts, captions, animates, adds music and renders the video in the cloud.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Check that the Vidova tools are available, for example with get_active_project.

    line 13
  2. Very specific:

    If the server offers a routine for a new edit from uploads, start it and follow its handoff.

    line 16
  3. Very specific:

    Call render_video, wait for it with wait_for_jobs, then give the person the project url and the link to the finished video.

    line 19
  4. Distinctive:

    Use the song they named or uploaded.

    line 24
  5. Distinctive:

    Every shot shows the subject of the edit.

    line 25
  6. Distinctive:

    Put every clip's peak on a beat: rush into it, slow hard to about quarter speed on the beat, and rush out.

    line 26

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Beat-sync edit

A song and the best few seconds of every clip, cut so each hit of the song lands on something happening.

Steps

  1. Check that the Vidova tools are available, for example with get_active_project. If they are not, follow the vidova skill to connect.
  2. Make a project with create_project. Bring the files in with import_asset_url for a link, begin_asset_upload for a local file when you can run shell commands, or upload_files to give the person the link where they add files. Call wait_for_asset until the files are ready.
  3. Call detect_beats on the song for the beats, the downbeats and the drop. Read each clip with read_asset and note its peak moment to a tenth of a second. Those peaks are what the edit is made of. Leave out clips where the subject is small or off screen.
  4. If the server offers a routine for a new edit from uploads, start it and follow its handoff. Otherwise call search_templates. When a template fits, use read_template and apply_template, then adjust it with patch_film. When none fits, build the film with patch_film.
  5. Start 4 bars before the drop, where a bar lasts 4 x 60 / bpm seconds. Use 2 to 4 slower shots for the intro, then one beat each, then half a beat in the last bar. Put the best clip on the drop, and one beat or half a beat per shot after it. End on the strongest image, slowed so it still moves.
  6. Watch the result with preview_timeline, and with preview_range across the moments that move. Call check_edit, then wait_for_jobs with its Job ID, and fix what it names.
  7. Call render_video, wait for it with wait_for_jobs, then give the person the project url and the link to the finished video.

What makes it work

  • The person's brief comes first: their order, song, length, format and rules. This skill fills in the rest.
  • Use the song they named or uploaded. Never swap it for another.
  • Every shot shows the subject of the edit.
  • Put every clip's peak on a beat: rush into it, slow hard to about quarter speed on the beat, and rush out. It never stops.
  • Frame 0 is the thumbnail: a bright, readable frame of the subject.
  • Vary the shot lengths. An even run of equal shots reads as a metronome.
  • search_effects and apply_effect put one effect on the drop. Never put effects on every cut.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.