Seedance ShotDesign Skills
Seedance 2.5 Shot Design Skills
Install
git clone https://github.com/woodfantasy/Seedance-ShotDesign-SkillsInstall command taken from the project's README or registry entry. Always review code before running it.
README excerpt
Read full README on GitHub →English | 中文 | 日本語 | 한국어 | Español | Português | Français
Seedance 2.5 Shot Design
Mode-aware directing, prompt design, extension, and editing for Jimeng Seedance 2.5
Seedance Shot Design turns a rough video idea or an approved source clip into a production-ready Seedance 2.5 plan and copyable prompt. Version 3.0 is a capability-level rewrite for 30-second standard generation, 30–180 second ultra-long work, multimodal references, extension, precision editing, and industrial workflows.
What changed in 3.0
| Area | Seedance 2.5 behavior |
|---|---|
| Standard generation | One continuous 4–30s generation; exactly 30s stays in standard mode by default |
| Ultra-long | Continuous 30–180s stories with a continuity bible, acts, sequences, and a resolved ending |
| Extension | Source ≤30s, add 4–30s, final ≤60s; the prompt controls only the added portion |
| Multimodal input | Up to 30 images, 10 videos, and 10 audios under the documented per-type duration/file constraints |
| Editing | Smart edit, annotation-based advanced edit, local replacement/removal, and viewpoint reconstruction |
| Audio | Audio-only references, voice/timbre binding, multilingual dialogue, BGM removal with speech/ambience preservation |
| Production modes | Creative transfer, green screen, rough/fine white model, seamless transition, multi-panel storyboard |
| Validation | Mode-aware duration, asset, timeline, contract, preservation, and contradiction checks |
| Localization | Native directing language; dialogue is explicitly bound to speaker and target language |
The skill deliberately removes obsolete assumptions: no forced split above 15 seconds, no 9/3/3/12 mixed-file rule, no universal 500-character ceiling, no forced English for non-Chinese users, and no undocumented 1080p or CLI claims.
What's new in 3.1
| Area | Enhancement |
|---|---|
| First-use onboarding | Automatic quick-start guide, minimum input template, and representative examples on first invocation |
| Official examples | Curated reference examples from official ByteDance / Dreamina documentation for structure anchoring |
| One-click install | npx --yes skills@latest add support alongside manual git clone |
| Timestamp-30s routing | Dedicated routing for exact 30-second videos requiring precise per-second timeline control |
Core workflow
flowchart LR
A[Production brief] --> B{Route by intent}
B --> C[Generation or ultra-long]
B --> D[Extension]
B --> E[Editing or audio]
B --> F[Industrial workflow]
C --> G[Asset binding and continuity]
D --> G
E --> G
F --> G
G --> H[Mode-specific prompt contract]
H --> I[Mode-aware validation]
I --> J[Copyable Seedance 2.5 delivery]
The skill:
- infers the production brief;
- selects one primary Seedance mode;
- loads only the relevant reference guides;
- binds every asset to a role, scope, and exclusion;
- designs time, action causality, and continuity state;
- validates and delivers one self-contained prompt.
Supported routes
Similar plugs
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local…
Why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
Production-grade engineering skills for AI coding agents.