editor-soundtrack
Skill19 starsChanged 30 days agoMITView on GitHub
Use when a recut social talking-head video in the Scrollmark editor needs a music bed, or the user asks to add, swap or remove background music. Not for seated interviews or podcasts, footage that is already a song, or when the user said no music.
In this repository23 other files it gives its agents.
- agent-interviewSkill
- audio-acquisitionSkill
- brand-kitSkill
- content-autopsySkill
- edit-handoffSkill
- editor-beat-syncSkill
- editor-camera-directingSkill
- editor-captionsSkill
- editor-motion-graphicsSkill
- editor-plan-and-checkSkill
- editor-sfx-sparseSkill
- editor-versionsSkill
- hook-anatomySkill
- media-acquisitionSkill
- platform-fluencySkill
- read-the-roomSkill
- repurpose-engineSkill
- studio-setupSkill
- subject-compositingSkill
- trend-radarSkill
- video-formatsSkill
- video-productionSkill
- voice-matchingSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 18
After the recut, add one music op to the plan with a query of the form "<vibe> background music" (instrumental, no competing vocals.
- Distinctive: line 23
default if unsure → "calm background music"
- Very specific: line 27
Add from / to (timeline seconds) only when the user wants music under part of the video, and duckDb (e.g.
- Distinctive: line 29
If the op finds nothing, retry once with a broader query.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.
Files
Editor Soundtrack
Requires
A running Scrollmark editor whose commands you can call: the SocialGPT editor chat, or scrollmark mcp from @scrollmark/cli for a coding agent. Without it the music op can't run; the when-to-skip rules and vibe queries still guide picking a bed by hand.
When to skip
Skip this skill (do not search, do not place) if the source is already a song or performance, the user said no music, or it is a seated interview or podcast. If they already placed a bed, keep it, duck it, trim it — do not add a second.
Add the bed
After the recut, add one music op to the plan with a query of the form "<vibe> background music" (instrumental, no competing vocals; a bare genre like "lo-fi" finds drum samples, not tracks):
- lifestyle / casual talking-head → "warm acoustic background music"
- product / UGC → "light pop background music"
- explainer / professional → "clean corporate background music"
- default if unsure → "calm background music"
{"op": "music", "args": {"query": "warm acoustic background music"}} searches the stock library, picks a track long enough for the video (or loops a shorter one with crossfades), fades it in and out and ducks it under speech (or sets it low when nothing speaks). Do not search first and do not build the bed from media.importFromCatalog + timeline.addMediaClip + audio.autoDuck ops; the op does all of it.
- Add
from/to(timeline seconds) only when the user wants music under part of the video, andduckDb(e.g. -18) only when they ask for it quieter or louder under speech. - For an audio file already in the project, pass
media(its handle) instead ofquery. - If the op finds nothing, retry once with a broader query; do not leave the user without music because no result was perfect.
Tell the user
The bed is new: tell the user you added music and name the track (the plan result's music[].track.title), never that you kept or reused existing music. Say they can remove or swap it. On dislike, remove the bed and run music again with a different query — do not silently keep the first pick.
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
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.

