agentleFS
LeostrukaLeostruka/devin-bundle/skills/animation-direction/SKILL.md

animation-direction

Skill0 starsChanged 3 months agoMITView on GitHub

Use when turning narrated video/audio into synced code-rendered motion graphics — narration -> timestamped transcript -> scene plan -> approval gate -> Remotion render -> ffmpeg composite. Covers the motion vocabulary, beat-to-visual mapping, scene-plan v2 schema, and the mandatory plan gate via extensions/asr + extensions/remotion-render.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Default Remotion (this extension).

    line 52

≈ “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.

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

Animation Direction

Motion-graphics direction without a video editor: "explain X" -> synced b-roll/infographic animation. Corrections happen at the cheap plan stage, never post-render.

Pipeline

  1. Enrich — extensions/asr/transcribe.py url|file (yt-dlp + whisper.cpp, offline) -> {text, segments[{start,end,text}]}; bootstrap via extensions/asr/bootstrap.py (explicit fetch only).
  2. Analyze — keyframes (ffmpeg scene-select) + semantic beats: what concept each segment explains.
  3. Plan — scene-plan v2 per beat: {id, sync_range:[s,e], visual:{type,props}, motion_spec:{easing,enter,exit,enter_s,exit_s}, overlay?}.
  4. GATE (hard) — render nothing until the plan is approved: plan_check.py output + ask_user_question/ledger sign-off.
  5. Render — extensions/remotion-render/render.py plan.json --workdir out/ -> Remotion project -> npx remotion render.
  6. Composite — overlay on source via ffmpeg (extensions/craft-bridge filmcraft commands or media-tools path).

Motion vocabulary

  • Easings: linear (data/tickers), spring (emphasis, diagrams), easeOut (default entrances).
  • Entrances: fade (default), slideUp (titles/steps), scale (callouts), none (cuts). Exits default fade, none on cut.
  • Timing budgets: entrance <= 0.5s and <= half the beat; holds >= 1.5s for text; transitions only between narration cuts.

Beat -> visual mapping

Beatvisual.typeNotes
Claim / definitionkinetic_text<= ~12 words on screen
Process / sequencediagram_nodesstagger 6f per node
Number / metriccountercount up over ~1s + label
Screenshot / assetpan_zoomslow zoom 1.0->~1.15

Sync rules: beat duration >= read time (160 WPM); one visual on screen unless overlay: true; no motion during narration cuts.

Renderer selection

Default Remotion (this extension). Blender via operate-blender when the visual is 3D. After-Effects JSX only if the user already has AE. No paid TTS/ASR services; plan approval is a hard gate, always.

Files

  • extensions/asr/ — transcribe + bootstrap.
  • extensions/remotion-render/ — plan_check.py (pre-gate validator: sync_range vs audio, overlap collisions, read-time + budget warnings), render.py (materialize template + render), templates/remotion-project/ (Root + PlanComposition + primitives).
  • Plan contract extends craft-bridge scene_manifest v1 with motion_spec + sync_range (v2).

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.