pftom
ac70719d4d
Extends Open Design from web-only to a multi-modal creation tool. The unifying contract is one code-agent loop driven by skills + project metadata + prompt constraints; for non-web surfaces the agent shells out to a single dispatcher (`od media generate`) that the daemon routes per (surface, model). - Types: new Surface union, MediaAspect / AudioKind, image/video/audio ProjectKind + ProjectMetadata fields, video/audio ProjectFileKind. - NewProjectPanel: top-level surface picker + Image / Video / Audio forms with model, aspect, length, duration, voice, audio-kind pickers. - ExamplesTab + DesignSystemsTab: surface filter row that scopes before mode / scenario / category filters. - FileViewer / FileWorkspace: native <video> and <audio> previews and matching tab icons. - Daemon: parses `od.surface` and `> Surface:` blockquotes; recognises mp4 / webm / mov / mp3 / wav / ogg / m4a / flac extensions; spawns agents with OD_BIN / OD_DAEMON_URL / OD_PROJECT_ID / OD_PROJECT_DIR env so any code-agent CLI with shell access can call the dispatcher. - daemon/media.js + daemon/media-models.js: surface-agnostic dispatcher with stub providers that emit deterministic placeholder bytes (1x1 PNG, valid mp4 ftyp, mp3 frame / silent WAV) so the framework works without API keys; real provider integrations slot in later. - daemon/cli.js: `od media generate --surface ... --model ...` subcommand routes to POST /api/projects/:id/media/generate and prints one JSON line for the agent to parse. - prompts/media-contract.ts: hard contract pinned LAST in the system prompt for image/video/audio surfaces — env vars, exact invocation, registered model IDs per surface, six workflow rules. system.ts metadata block updated to point at the contract. - Seed skills: image-poster, video-shortform, audio-jingle each ship a SKILL.md with `mode/surface: image|video|audio` and a stylized example.html preview, and instruct the agent to dispatch via the contract. Made-with: Cursor
109 lines
3.3 KiB
Markdown
109 lines
3.3 KiB
Markdown
---
|
|
name: video-shortform
|
|
description: |
|
|
Short-form video generation skill — 3-10 second clips for product
|
|
reveals, motion teasers, ambient loops. Defaults to Seedance 2 but
|
|
works the same with Kling 3 / 4, Veo 3 or Sora 2. Output is one MP4
|
|
saved to the project folder. When the workspace also ships an
|
|
interactive-video / hyperframes skill, prefer composing several short
|
|
shots into a single timeline rather than one long monolithic clip.
|
|
triggers:
|
|
- "video"
|
|
- "clip"
|
|
- "shortform"
|
|
- "reel"
|
|
- "短视频"
|
|
- "动效"
|
|
od:
|
|
mode: video
|
|
surface: video
|
|
scenario: marketing
|
|
preview:
|
|
type: html
|
|
entry: example.html
|
|
design_system:
|
|
requires: false
|
|
example_prompt: |
|
|
5-second product reveal — ceramic coffee mug rotating on a soft
|
|
paper backdrop, warm side-light from camera-left, micro dust motes
|
|
drifting through the beam. Cinematic, 16:9, slow drift on the camera.
|
|
---
|
|
|
|
# Video Shortform Skill
|
|
|
|
Short-form (≤ 10s) is the sweet spot for current text-to-video models —
|
|
they're great at one **shot** with one **idea**, weaker at multi-cut
|
|
narratives. Plan one shot per call.
|
|
|
|
## Resource map
|
|
|
|
```
|
|
video-shortform/
|
|
├── SKILL.md
|
|
└── example.html
|
|
```
|
|
|
|
## Workflow
|
|
|
|
### Step 0 — Read the project metadata
|
|
|
|
`videoModel`, `videoLength` (seconds), `videoAspect`. These are
|
|
hard-locks — clamp the prompt to whatever the chosen model supports
|
|
(Seedance 2 caps at 10s; Kling 4 supports up to 10s + image-to-video;
|
|
Veo 3 supports 8s with audio).
|
|
|
|
### Step 1 — Plan the shot
|
|
|
|
Write the shotlist BEFORE calling the model:
|
|
|
|
| Slot | Content |
|
|
|---|---|
|
|
| Subject | What's in frame? |
|
|
| Camera | Static / pan / push-in / orbit? |
|
|
| Lighting | Key direction + temperature |
|
|
| Motion | What moves, at what pace? Subject motion vs camera motion. |
|
|
| Sound | Ambient bed? (only if the model supports audio) |
|
|
|
|
Show this to the user as a one-sentence plan before dispatching — they
|
|
can redirect cheaply.
|
|
|
|
### Step 2 — Compose the prompt
|
|
|
|
Use the format the upstream model prefers (Seedance: motion + camera +
|
|
mood; Kling: subject + camera + style; Veo: subject + cinematography +
|
|
sound). Bind the project's `videoAspect` and `videoLength` directly to
|
|
the API parameters; never put them in prose.
|
|
|
|
### Step 3 — Dispatch via the media contract
|
|
|
|
Use the unified dispatcher — do **not** call provider APIs by hand:
|
|
|
|
```bash
|
|
node "$OD_BIN" media generate \
|
|
--project "$OD_PROJECT_ID" \
|
|
--surface video \
|
|
--model "<videoModel from metadata>" \
|
|
--aspect "<videoAspect from metadata>" \
|
|
--length <videoLength seconds> \
|
|
--output "<short-slug>-<seconds>s.mp4" \
|
|
--prompt "<assembled shot prompt from Step 2>"
|
|
```
|
|
|
|
The command prints one line of JSON: `{"file": {"name": "...", ...}}`.
|
|
The bytes land in the project; the FileViewer plays it automatically.
|
|
|
|
### Step 4 — Hand off
|
|
|
|
Reply with: shot summary, the filename returned by the dispatcher, and
|
|
one sentence on what to try if the user wants a variation.
|
|
|
|
## Hard rules
|
|
|
|
- One shot per turn. Multi-shot timelines belong in a hyperframes /
|
|
interactive-video skill, not here.
|
|
- Match `videoAspect` exactly — re-renders are slow.
|
|
- Never ship a video without saving the file — the user expects
|
|
something to play in the file viewer.
|
|
- When the underlying model fails (NSFW filter, content policy,
|
|
timeout), report the error verbatim. Don't silently retry.
|