agentleFS
chadixearthchadixearth/graphyloop/skills/short-video-production/SKILL.md

short-video-production

Skill3 starsChanged 12 days agoMITView on GitHub

Use when turning a finished story or script into a rendered ~1-minute video: HyperFrames composition, scene timing, captions, voiceover sync, 9:16 export. Not for story writing (use story-engineering).

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

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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. Distinctive:

    Default renderer: HyperFrames (HTML→video, local, deterministic).

    line 12
  2. Distinctive:

    No flicker / animation overload — deterministic keyframes only

    line 32
  3. Distinctive:

    Prefer transform/opacity animation (60fps safe)

    line 33
  4. Distinctive:

    No TTS key available → render silent with captions, note audio step

    line 40
  5. Very specific:

    Verify composition validates (hyperframes lint / validate)

    line 44
  6. Distinctive:

    Check hook frame: first 3s must show tension text

    line 46
  7. Distinctive:

    Check captions legible on small screen

    line 47

≈ “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

Short Video Production

1. Overview

Pipeline from script to rendered MP4: script with per-scene timing → composition (HTML/CSS-keyframe, deterministic) → render → 9:16 MP4.

Default renderer: HyperFrames (HTML→video, local, deterministic). Read the hyperframes skill first — hyperframes-core for composition contract, hyperframes-cli for commands — before building.

2. 60s Scene Plan

5-6 scenes matching story-engineering beat sheet:

TimeScene
0-3sHook
3-8sContext
8-45sBody (2-3 scenes, micro-payoffs)
45-55sPayoff
55-60sCTA

3. Composition Rules

  • 9:16 (1080x1920) for Shorts/TikTok/Reels
  • One visual idea per scene
  • Captions word-synced to voiceover (show the spoken word chunk)
  • Text large and mobile-readable
  • No flicker / animation overload — deterministic keyframes only
  • Prefer transform/opacity animation (60fps safe)

4. Voiceover

  • ~150-160 words per 60s; 2.5-2.7 words/sec
  • Mark per-scene word counts in the script
  • Pause 0.3-0.5s at beat boundaries
  • No TTS key available → render silent with captions, note audio step

5. Render Checklist

  • Verify composition validates (hyperframes lint / validate)
  • Render at 1080x1920
  • Check hook frame: first 3s must show tension text
  • Check captions legible on small screen
  • Export MP4
  • Name output video.mp4

6. Common Failures

  • Bare waitForLoadState hangs on SSE pages — never use
  • Browser timeouts must be explicit (page.goto 15000ms)
  • Render fails twice → stop and report, no silent looping

7. Cross-Reference

  • story-engineering — source story
  • video-ai-automation — tool stack incl. TTS options

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.