release
Bump VibeFrame versions, regenerate release artifacts, run verification, and prepare a…
Author, repair, render, and inspect VibeFrame scene projects built from STORYBOARD.md and DESIGN.md.
$ npx -y skills add vericontext/vibeframe --skill vibe-scene --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/vibe-sceneContext preview
The summary Claude sees to decide when to auto-load this skill.
Author, repair, render, and inspect VibeFrame scene projects built from STORYBOARD.md and DESIGN.md.
name: vibe-scene description: Author, repair, render, and inspect VibeFrame scene projects built from STORYBOARD.md and DESIGN.md.
<!-- GENERATED by `pnpm agent-sync` from .agents/skills/vibe-scene/SKILL.md — DO NOT EDIT. -->
VibeFrame scene projects are editable video projects built from:
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`.
| Path | Use when | Commands | | -------------------------- | --------------------------------------------------------------------------------------- | ------------------------------------------------------------ | | Host-agent authoring | Claude Code/Codex/Cursor writes the scene HTML from a plan (default) | `vibe build`, then `vibe scene compose-prompts` | | Deterministic template | CI or a human demo should produce scene HTML without a coding agent (no LLM call) | `vibe build --composer template` | | Single-scene draft | You need a quick template scene or fallback HTML | `vibe 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.
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:
treat provider assets as inputs rather than the whole product.
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`. It renders as a `<dotlottie-wc>` overlay (no provider call — free).
During `vibe build`, generated narration is transcribed at the word level (Whisper) to `assets/transcript-<beat>.json` whenever narration exists and an OpenAI key is configured. Those word timings are passed into each beat's compose prompt so captions / kinetic typography can be synced to speech.
word-level animation timing.
them. For long narration the prompt downgrades to coarse phrase-level anchors.
Never author scene HTML before `DESIGN.md` exists. Treat it as the hard gate for visual decisions:
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.
vibe scene lint index.htm
Let your coding agent generate real video, on your own provider keys, under a spend ceiling it cannot cross. VibeFrame is a CLI and MCP server for Claude Code, Codex, Cursor, or any bash-capable agent.
Repo: vericontext/vibeframe
Bump VibeFrame versions, regenerate release artifacts, run verification, and prepare a…
Check VibeFrame SSOT consistency across package versions, generated docs, model metadata,…
Run VibeFrame tests for one package or the whole monorepo and summarize failures.
Author and run VibeFrame YAML pipelines with vibe run, checkpoints, and budget controls.