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

shorts-motion

Skill2 starsChanged 2 months agoMITView on GitHub

Add readable, cue-aligned graphics to a short without obscuring the speaker, captions or the meaning of the footage.

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

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

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep captions, face and graphics in distinct readable regions.

    line 12
  2. Distinctive:

    Use the available renderer's actual compositing model.

    line 14

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Add graphics that explain the words

Scout the final cut for moments that benefit from a number, comparison, step, label or supporting image. Read context/brand/BRAND.md. Do not add a graphic merely to satisfy an invented retention interval.

Write a motion plan with source phrase/word cue, payload, duration, screen region and reason. Resolve cues from the final transcript; if a cue occurs twice, identify the intended occurrence. A graphic's payoff must arrive with the relevant spoken fact, not just its entrance animation.

Keep captions, face and graphics in distinct readable regions. Use lower-third panels when they preserve useful footage; full-screen scenes need a narrative reason. Every displayed metric must have a supported value and unit.

Use the available renderer's actual compositing model. Check alpha, layering, text metrics and font loading. Changes to the edit require re-resolving cues.

Inspect before/during/after frames and play the sequence with audio. Return editable motion data/project and the rendered output; report uncertain timing or unrendered elements. Use shorts-qa for final checks.

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.