agentleFS
Sign inStart free
danielarif26danielarif26/agentic-os-starter/skills/episode-package/SKILL.md

episode-package

Skill1 starsChanged 4 months agoMITView on GitHub

Produce a complete YouTube episode package — retention script, Remotion timelineVN.ts scene plan, and thumbnail/title brief — ready to drop into your Remotion video pipeline. Self-improving. Use when the user says "new episode", "make a video package", "script + timeline", "next video". Part of the Agentic OS (Level 1). Does NOT render.

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:

    Never invent new scene component names as if they exist — only the 8 above.

    line 35

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

episode-package

One episode → script + scene timeline + thumbnail brief, matching the existing Remotion pipeline.

Loop (every time)

  1. Before — read <vault>/agentic-os/runs/episode-package.md. Apply lesson: (hooks that landed, pacing).

Pipeline facts (from your Remotion project's CLAUDE.md — verify before writing)

  • Episode = src/data/timelineVN.ts: array of SceneSpec {type, start, end, props}.
  • Scene types: HookScene, DemoVsProdScene, LayerScene, LayerStackScene, RehookScene, InsightScene, ActionScene, OutroScene.
  • Root.tsx: register landscape <Composition> + -Vertical sibling (1080×1920). Avatar = public/heygen-avatar-0N.mp4.
  • FaceOverlay PiP persists over all scenes.

Deliverables (write to <vault>/agentic-os/outputs/<episode-slug>/)

  1. script.md — full voiceover, retention-engineered: cold-open hook (0–5s), open loop, pattern interrupts, mid-video rehook, CTA, outro. Timestamped to scenes.
  2. timeline.md — proposed SceneSpec[] mapping (type + start/end sec + props) the user pastes into timelineVN.ts. Reuse existing scene types only; flag if a new one is needed.
  3. thumbnail-brief.md — 3 title options (curiosity gap, ≤55 char), thumbnail concept (text ≤4 words, focal image, color/tone), and the hook line.

After

Append run: episode slug, hook used, scene count, PASS/FAIL, lesson:.

Output to user

Links to the 3 files + the chosen title + a one-paragraph pitch. Next step = paste timeline into timelineVN.ts, add Root.tsx compositions, npm run dev.

Never

  • Never invent new scene component names as if they exist — only the 8 above. Never render (that's npx remotion render, user's call).

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.

Check your setup, free