Skip to content

Seedance ShotDesign Skills

Seedance 2.5 Shot Design Skills

Install

$git clone https://github.com/woodfantasy/Seedance-ShotDesign-Skills

Install command taken from the project's README or registry entry. Always review code before running it.

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:

  1. infers the production brief;
  2. selects one primary Seedance mode;
  3. loads only the relevant reference guides;
  4. binds every asset to a role, scope, and exclusion;
  5. designs time, action causality, and continuity state;
  6. validates and delivers one self-contained prompt.

Supported routes

Similar plugs

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.