LearnPrompt/awesome-seedance / agents/skills/seedance-production-workflow
seedance-production-workflow
VerifiedPlan and carry a Seedance video from brief through references, storyboard, generation handoff, shot-level review, and targeted repair. Use for an end-to-end Seedance production request; use a narrower prompt skill for a single prompt.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 5.8 KB |
| agents/openai.yaml | config | 125 B |
| references/deliverables.md | markdown | 2.5 KB |
| references/editable-template.md | markdown | 5.1 KB |
| references/provider-capabilities.md | markdown | 1.5 KB |
| references/qa-rubric.md | markdown | 1.5 KB |
| scripts/test_validate_plan.py | script | 9.2 KB |
| scripts/validate_plan.pyexecutable | script | 4.1 KB |
references/deliverables.md
View on GitHub# Deliverables and plan contract
Write only artifacts the chosen route needs. Use one project directory and preserve the source files used for each generated artifact.
| File | Purpose |
| --- | --- |
| `brief.md` | Story, audience, look, duration, aspect ratio, platform, budget, rights and unknowns |
| `reference-map.md` | Stable media IDs; source; permitted use; what each controls and must not control |
| `plan.json` | Deterministic timeline and reference IDs for preflight |
| `character-prompt.txt`, `storyboard-prompt.txt` | Image prompts when reference art must be made |
| `storyboard.png` or shot keyframes | Checked visual plan for multi-shot generation |
| `video-prompt.txt` | Copy-ready final prompt with matching shot numbering and reference IDs |
| `run-manifest.json` | Actual model, platform, date, duration, ratio, resolution, seed if available, asset paths/hashes, task ID and output path; retain the raw output and record any derived edit with its source hash and time offset; no secret values |
| `qa.md` | Observable result, failure timestamps, targeted revisions and final state |
Minimal `plan.json` shape:
```json
{
"duration_seconds": 12,
"references": [
{"id": "Image1", "role": "identity"},
{"id": "Image2", "role": "storyboard"}
],
"shots": [
{"id": 1, "start": 0, "end": 3, "action": "approach the door", "camera": "wide exterior", "audio": "footsteps", "entry_state": "outside, envelope in right hand", "exit_state": "at door, envelope in right hand", "references": ["Image1", "Image2"]},
{"id": 2, "start": 3, "end": 6, "action": "open the door", "camera": "medium threshold", "audio": "door handle", "entry_state": "at door, envelope in right hand", "exit_state": "inside, envelope in right hand", "references": ["Image1", "Image2"]},
{"id": 3, "start": 6, "end": 9, "action": "place envelope on counter", "camera": "medium interior", "audio": "paper on wood", "entry_state": "inside, envelope in right hand", "exit_state": "inside, envelope on counter", "references": ["Image1", "Image2"]},
{"id": 4, "start": 9, "end": 12, "action": "walk toward exit", "camera": "wide interior", "audio": "footsteps", "entry_state": "inside, envelope on counter", "exit_state": "at exit, envelope on counter", "references": ["Image1", "Image2"]}
]
}
```
The script checks timeline arithmetic, numbering, required fields and reference IDs. The agent must still verify semantic handoff and visual continuity. Use `audio: "silent"` when the brief calls for silence.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |