agentleFS
timscheueraitimscheuerai/gtm-architecture-template/.agents/skills/shorts-edit/SKILL.md

shorts-edit

Skill2 starsChanged 2 months agoMITView on GitHub

Turn raw talking-head recordings into finished shorts using reviewed take selection, audio, captions, cue-based graphics and final QA.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 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.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the supplied brief and inspect the actual footage.

    line 8
  2. Very specific:

    Keep raw/, transcripts/, edit/ and renders/ inside the requested ignored output directory.

    line 10
  3. Very specific:

    Use shorts-cut for take selection, shorts-audio for audio treatment, and shorts-motion for useful graphics.

    line 12
  4. Distinctive:

    Prefer one final encode from preserved sources when practical.

    line 14
  5. Very specific:

    Run shorts-qa against the final artifact.

    line 16

≈ “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

Edit a short

Read the supplied brief and inspect the actual footage. Preserve source files. Establish the intended message, aspect ratio and target runtime; infer routine edit choices within the request.

Keep raw/, transcripts/, edit/ and renders/ inside the requested ignored output directory. Create an edit decision list with source file, start/end times, beat and reason. No prebuilt video pipeline is bundled.

Use shorts-cut for take selection, shorts-audio for audio treatment, and shorts-motion for useful graphics. Captions come from the final cut's words/timings, not stale source offsets. Keep names, numbers and units manually checked against the recording.

Prefer one final encode from preserved sources when practical. Cache generated/transcribed material with enough configuration to distinguish versions. Inspect installed tools before using their command grammar.

Run shorts-qa against the final artifact. Deliver the file, EDL/project, source-to-output map and verification results. A script that has not rendered successfully is not a completed edit.

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.