agentleFS
vericontextvericontext/vibeframe/.agents/skills/vibe-scene/SKILL.md

vibe-scene

Skill185 starsChanged todayMITView on GitHub

Author, repair, render, and inspect VibeFrame scene projects built from STORYBOARD.md and DESIGN.md.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

12 rules. About 0 are common, 4 are distinctive, and 8 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 8

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when the user wants editable HTML-based scene composition, storyboard-to-MP4 work, or a host-agent authoring loop.

    line 16
  2. Distinctive:

    Use the top-level commands for the main project lifecycle:

    line 19
  3. Distinctive:

    Default recommendation for public demos and reproducible dogfood runs:

    line 38
  4. Very specific:

    Use --skip-backdrop when you want a low-cost composition test.

    line 52
  5. Very specific:

    Use this when Claude Code or another coding agent should be the reasoner that authors compositions/scene-*.html.

    line 58
  6. Very specific:

    If vibe build returns a needs-author plan:

    line 70
  7. Distinctive:

    Read the compose plan.

    line 72
  8. Very specific:

    Every timed element needs data-start, data-duration, and data-track-index.

    line 80
  9. Very specific:

    Do not use Date.now(), Math.random(), or network fetches in render paths.

    line 83
  10. Very specific:

    Run vibe schema scene.<subcommand> before using less common flags.

    line 99
  11. Very specific:

    Never author scene HTML before DESIGN.md exists.

    line 153
  12. Very specific:

    Run lint with --json --fix.

    line 188

≈ “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

Vibe Scene

VibeFrame scene projects are editable video projects built from:

  • STORYBOARD.md - beats, narration, backdrop cues, duration hints
  • DESIGN.md - visual identity, palette, typography, motion rules
  • compositions/scene-*.html - per-beat HTML compositions
  • index.html - root timeline that references scene compositions
  • assets/ and renders/ - generated inputs and final outputs

Use this skill when the user wants editable HTML-based scene composition, storyboard-to-MP4 work, or a host-agent authoring loop.

Use the top-level commands for the main project lifecycle:

vibe init my-video --profile agent --ratio 16:9
vibe build my-video
vibe render my-video -o renders/final.mp4

The vibe scene ... namespace is the lower-level authoring surface: install-skill, compose-prompts, list-styles, add, and lint.

Pick The Right Path

PathUse whenCommands
Host-agent authoringClaude Code/Codex/Cursor writes the scene HTML from a plan (default)vibe build, then vibe scene compose-prompts
Deterministic templateCI or a human demo should produce scene HTML without a coding agent (no LLM call)vibe build --composer template
Single-scene draftYou need a quick template scene or fallback HTMLvibe scene add

Default recommendation for public demos and reproducible dogfood runs:

vibe init my-video --profile agent --ratio 16:9
# edit DESIGN.md and STORYBOARD.md
vibe build my-video \
  --tts kokoro \
  --skip-backdrop \
  --skip-render
# (the host agent authors compositions/scene-*.html, then re-run vibe build)
vibe scene lint index.html --project my-video --fix
vibe render my-video -o renders/final.mp4 --quality standard

Use --skip-backdrop when you want a low-cost composition test. Remove it when the demo should exercise OpenAI image generation from each beat's backdrop cue.

Host-Agent Loop

Use this when Claude Code or another coding agent should be the reasoner that authors compositions/scene-*.html.

vibe build my-video \
  --tts kokoro \
  --skip-backdrop \
  --skip-render

vibe scene compose-prompts my-video --json

If vibe build returns a needs-author plan:

  1. Read the compose plan.
  2. Author each missing compositions/scene-<id>.html.
  3. Run vibe scene lint index.html --project my-video --fix.
  4. Fix remaining lint errors by editing the HTML.
  5. Run vibe render my-video.

Hard rules for authored scene HTML:

  • Every timed element needs data-start, data-duration, and data-track-index.
  • Timed elements must have class="clip".
  • GSAP timelines must be paused and registered on window.__timelines.
  • Do not use Date.now(), Math.random(), or network fetches in render paths.
  • Route final audio through root-level <audio> elements when possible.
  • For factual, typography-heavy videos, keep claims and layout in HTML/CSS/JS; treat provider assets as inputs rather than the whole product.

Low-Level Scene Commands

vibe scene install-skill my-video --host auto
vibe scene compose-prompts my-video --json
vibe scene list-styles
vibe scene add intro --project my-video --style announcement --headline "Hello"
vibe scene add badge --project my-video --style simple --lottie assets/logo.lottie --lottie-position bottom-left
vibe scene lint index.html --project my-video --json --fix

Run vibe schema scene.<subcommand> before using less common flags.

Overlay a Lottie animation (.json/.lottie) on a scene with --lottie <path>, tuned by --lottie-position (full|center|top-left|top-right|bottom-left|bottom-right), --lottie-scale, --lottie-opacity, and --lottie-no-loop. The scene timeline drives it frame by frame from a runtime copied into assets/vendor/dotlottie/ (no provider call, free).

Takes: Keeping A Generation You Liked

vibe build records every beat asset it generates (narration, backdrop, keyframe, video, music) as a take, and keeps each take's bytes. When a regeneration came out worse, put the earlier one back instead of paying again:

vibe take list --beat <id> --json       # inSlot marks what the slot holds now
vibe take promote <take id> --dry-run --json
vibe take promote <take id>

Later builds keep a promoted slot until that beat's cue is edited or vibe build --force runs. vibe take log --json totals what the project spent, split into provider billing and estimates. vibe take prune --dry-run shows media copies safe to remove (--slots-only frees more, but those takes can no longer be promoted from a copy; ask first). See docs/take-graph.md.

A beat video that is close but not right can be continued instead of regenerated: vibe take extend <take id> adds time after its last frame, vibe take edit <take id> --prompt "<the change>" revises it (Grok and Gemini Omni; Kling legacy models extend only). Both are paid: run --dry-run --json first, confirm the spend with the user, and pass --max-cost. The result is a new take for the same slot; promote it to use it.

Review reports link findings to takes: an issue about one beat lists the takes filling its slots in issues[].takes, and a finding about generated content adds take edit / take promote actions to nextActions. Use those rather than regenerating the whole beat.

Narration Word-Sync

During vibe build, generated narration is transcribed at the word level (ElevenLabs Scribe when ELEVENLABS_API_KEY is set, else OpenAI Whisper) to assets/transcript-<beat>.json whenever narration exists and one of those keys is configured. Those word timings are passed into each beat's compose prompt so captions / kinetic typography can be synced to speech.

  • On by default; pass --skip-transcript to opt out (no transcription cost).
  • Neither key → silently skipped; narration still plays, just without word-level animation timing.
  • Timings are advisory and visual-only — the composer never adds audio/SFX from them. For long narration the prompt downgrades to coarse phrase-level anchors.

STYLE And STORYBOARD Guidance

Never author scene HTML before DESIGN.md exists. Treat it as the hard gate for visual decisions:

  • palette and contrast
  • typography and hierarchy
  • layout density
  • animation timing and transition style
  • what to avoid

Scenes live in scenes/, one markdown file per scene, playing in filename order. Cues go in the frontmatter, direction in the body:

---
type: Scene
narration: "The first sentence the viewer hears."
backdrop: "Specific visual prompt for the scene backdrop"
duration: 5
---

What the scene should show.

STORYBOARD.md holds only project frontmatter and direction prose. Beat headings left in it are ignored and reported - move them into scenes/, or run vibe storyboard migrate on an older single-file project.

Lint Feedback Loop

vibe scene lint index.html --project my-video --json --fix

Recommended loop:

  1. Run lint with --json --fix.
  2. Fix any error findings in the referenced scene file.
  3. Re-run lint.
  4. Cap retries at 3; if errors persist, replace the scene with a simpler vibe scene add ... --style simple --force draft and explain the tradeoff.

Warnings can be acceptable for demos only when the final render is visually correct and deterministic.

Render Checklist

  • vibe doctor reports Chrome and FFmpeg as available.
  • vibe scene lint exits 0 or only acceptable warnings remain.
  • index.html references every compositions/scene-*.html file needed.
  • vibe render my-video -o renders/final.mp4 writes the expected MP4.
  • Final media info or ffprobe confirms the intended duration, fps, and codec shape.

Common Failures

  • Root composition not found: run vibe build once so the render scaffold is created, or use vibe init --profile full.
  • needs-author: expected when the host agent authors scenes (the default); author the listed scene files and rerun build.
  • OPENAI_API_KEY not set: use --skip-backdrop for a local composition test, or configure the key before generating backdrops.
  • Render hangs at 0%: run vibe doctor; install Chrome or set CHROME_PATH.

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.