#9797th of 118 in Agent frameworks and SDKsFor image, video and design, video and animation
seedance-2.0
Agent skill that turns ideas into shot-by-shot Seedance 2.0 video prompts
- Stars
- 8.1k
- License
- MIT
- Last commit
- Sep 2026
- Last release
- Aug 2026
- Language
- Python
512 on 21 Apr 20268,148 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Seedance 2.0 Skill OS is an agent skill that plans shots, binds reference assets and continues from an accepted clip, producing structured prompts for the Seedance 2.0 video model. Each prompt is rendered from a published shot table and passes a moderation pre-screen. Generation and its costs stay with your video provider.
Who it is for: Creators prompting Seedance 2.0 for multi-shot short video through an agent
Strengths
- Prompts ship with a shot table, so camera and eye-line geometry can be checked before paying for a render
- Includes a moderation pre-screen step for prompts before submission
- Example prompts in English, Chinese, Korean, Japanese and Russian; docs in six languages
- MIT licensed, versioned (v6.7.0) with a changelog
Weaknesses
- Targets one video model, Seedance 2.0; other generators are not covered
- Needs a separate video provider account; generation costs are paid there
- Showcase clips shown are marked not rendered yet, with slates in their place
- Prompts are long and prescriptive, repeating a lock line in every shot
What it needs
- no GPU
- Needs Seedance 2.0 video provider account
- Models: Seedance 2.0
Quick answers
Is seedance-2.0 open source?
Yes. Its code is on GitHub under the MIT license.
Does seedance-2.0 need a GPU?
No, it runs without one.
Also in Agent frameworks and SDKs
See all 118| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 95 out of 100 |
| 2 | openai-agents-pythonPython SDK for multi-agent workflows with handoffs, guardrails and tracing | 91 out of 100 |
| 3 | mastraTypeScript framework for building AI agents, workflows and MCP servers | 91 out of 100 |
| #4 | browser-usePython library that lets an LLM agent control a web browser | 90 out of 100 |
| #5 | copilotkitSDK for adding agent chat, generative UI and shared state to apps | 90 out of 100 |