#300 by GitHub stars
dexhunter/seedance2-skill
skill to create best prompts for generating videos with seedance2.0
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
516284d5bab5 → 516284d5bab5
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 516284d5bab5
No earlier version was observed for comparison.
zh/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
516284d5bab5 → 516284d5bab5
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 516284d5bab5
No earlier version was observed for comparison.
Heat
4.8- Star growth, last 7 daysAhead of 80% of tracked repositories
- Star growth, last 24 hoursAhead of 70% of tracked repositories
- Rank movement, last 7 daysAhead of 25% of tracked repositories
- Commits, last 30 daysAhead of 0% of tracked repositories
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekAhead of 0% of tracked repositories
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
How it works
seedance-prompt-en
When your agent uses it
Write effective prompts for Jimeng Seedance 2.0 multimodal AI video generation. Use when users want to create video prompts using text, images, videos, and audio inputs with the @ reference system. Covers camera movements, effects replication, video extension, editing, music beat-matching, e-commerce ads, short dramas, and educational content.
What it loads into context
Frontmatter
80 tokensAlways available to the agent
SKILL.md
3,618 tokensWhen the skill is activated
Reference documents
990 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Description
- System Constraints
- Core Syntax: The @ Reference System
- Prompt Structure Blueprint
- Camera Language Reference
- Capability-Specific Prompt Patterns
- Style and Quality Modifiers
- Workflow: Step-by-Step Prompt Creation
- Common Mistakes to Avoid
- Example Prompt Templates
- Interaction Instructions
Files
.gitignoreasset174 bytesLICENSEasset1,072 bytesREADME-zh.mddoc1,642 bytesREADME.mddoc1,703 bytesSKILL.mdcore15,337 bytesassets/seedance2-thumbnail.pngasset2,097,669 bytesassets/thumbnail-prompt.txtdoc2,526 bytes
Read SKILL.md
# Seedance 2.0 Video Prompt Writing Guide
## Description
You are an expert prompt engineer for **Jimeng Seedance 2.0**, ByteDance's multimodal AI video generation model. Your role is to help users craft precise, effective prompts that produce high-quality AI-generated videos. You understand the model's capabilities, input constraints, referencing syntax, and best practices for camera work, storytelling, sound design, and visual effects.
## System Constraints
### Input Limits
| Input Type | Limit | Format | Max Size |
|---|---|---|---|
| Images | ≤ 9 | jpeg, png, webp, bmp, tiff, gif | 30 MB each |
| Videos | ≤ 3 | mp4, mov | 50 MB each, total duration 2–15s |
| Audio | ≤ 3 | mp3, wav | 15 MB each, total duration ≤ 15s |View the complete source on GitHubseedance-prompt-zh
When your agent uses it
为即梦 Seedance 2.0 多模态AI视频生成模型撰写高质量提示词。当用户需要使用文本、图片、视频、音频等多模态输入创作视频提示词时触发。涵盖@引用语法、运镜复刻、特效模仿、视频延长、视频编辑、音乐卡点、电商广告、短剧创作、科普教育等场景。
What it loads into context
Frontmatter
104 tokensAlways available to the agent
SKILL.md
5,615 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 描述
- 系统约束
- 核心语法:@ 引用系统
- 提示词结构模版
- 运镜语言参考
- 各场景提示词模式
- 风格与质感修饰词
- 特殊用法提示
- 常见错误与避坑指南
- 提示词模版库
- 交互指引
Files
SKILL.mdcore17,450 bytes
Read SKILL.md
# Seedance 2.0 视频提示词撰写指南
## 描述
你是 **即梦 Seedance 2.0** 的专业提示词工程师。Seedance 2.0 是字节跳动推出的多模态 AI 视频生成模型,支持图像、视频、音频、文本四种模态输入。你的任务是帮助用户撰写精准、高效的提示词,充分发挥模型在运镜复刻、动作编排、创意特效、音画同步等方面的能力,生成高质量的 AI 视频。
## 系统约束
### 输入限制
| 输入类型 | 数量上限 | 支持格式 | 大小限制 |
|---|---|---|---|
| 图片 | ≤ 9 张 | jpeg、png、webp、bmp、tiff、gif | 每张 < 30 MB |
| 视频 | ≤ 3 个 | mp4、mov | 每个 < 50 MB,总时长 2–15s |
| 音频 | ≤ 3 个 | mp3、wav | 每个 < 15 MB,总时长 ≤ 15s |View the complete source on GitHubSkills included
- seedance-prompt-en
- seedance-prompt-zh
Repository facts
- License
- MIT
- Created
- Feb 11, 2026
- Last pushed
- Sep 19, 2026
- Forks
- 365
- Open issues
- 2
- Project activity
- Active
Rank over the last 12 weeks
Now #300 · best #257 · down 34 in 30 days
- #288 on Nov 1
- #291 on Nov 2
- #295 on Nov 3
- #297 on Nov 4
- #299 on Nov 5
- #300 since Nov 6
72 earlier periods
- #259 on Aug 2
- #262 on Aug 7
- #263 on Aug 8
- #259 on Aug 9
- #268 on Aug 10
- #261 on Aug 11
- #259 on Aug 12
- #266 on Aug 13
- #265 on Aug 14
- #262 on Aug 15
- #265 on Aug 16
- #262 on Aug 17
- #266 from Aug 18 to Aug 19
- #262 on Aug 20
- #263 on Aug 21
- #260 on Aug 22
- #268 on Aug 23
- #267 on Aug 24
- #269 on Aug 25
- #268 from Aug 26 to Aug 28
- #267 on Aug 29
- #262 on Aug 30
- #268 from Aug 31 to Sep 1
- #266 on Sep 2
- #273 on Sep 3
- #266 on Sep 4
- #269 on Sep 5
- #266 on Sep 6
- #271 on Sep 7
- #273 on Sep 8
- #271 from Sep 9 to Sep 10
- #268 on Sep 11
- #272 on Sep 12
- #271 on Sep 13
- #272 from Sep 14 to Sep 15
- #270 on Sep 16
- #266 on Sep 17
- #268 on Sep 18
- #265 on Sep 19
- #268 on Sep 20
- #269 on Sep 21
- #267 from Sep 22 to Sep 23
- #268 on Sep 24
- #263 from Sep 25 to Sep 26
- #262 on Sep 27
- #265 on Sep 28
- #267 on Sep 29
- #263 on Sep 30
- #262 on Oct 1
- #263 on Oct 2
- #259 on Oct 3
- #257 on Oct 4
- #260 on Oct 5
- #263 on Oct 6
- #266 from Oct 7 to Oct 8
- #270 on Oct 9
- #267 on Oct 10
- #268 on Oct 11
- #272 from Oct 12 to Oct 13
- #270 from Oct 14 to Oct 15
- #268 on Oct 16
- #271 on Oct 17
- #272 on Oct 18
- #271 on Oct 19
- #272 on Oct 20
- #274 from Oct 21 to Oct 22
- #273 on Oct 23
- #277 on Oct 24
- #279 on Oct 25
- #286 on Oct 28
- #288 on Oct 29
- #289 from Oct 30 to Oct 31
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 2, 2026
- No broad tool permissions
- No dangerous shell commands
- 6 network referencesin 2 files: README-zh.md:7 README.md:7
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show all 6 signals by file
README-zh.md
- Network accessline 7
为[即梦 Seedance 2.0](https://jimeng.jianying.com/) 多模态 AI 视频生成模型打造的 [Agent Skills](https://agentskills.io) 提示词撰写技能。支持 Claude Code、Cursor、Cline 等兼容的 AI 代理。 - Network accessline 46
- [即梦 Seedance 2.0 使用手册](https://bytedance.larkoffice.com/wiki/A5RHwWhoBiOnjukIIw6cu5ybnXQ) — 参数说明、交互方式、多模态能力与示例提示词 - Network accessline 47
- [小云雀 Seedance 2.0 实测案例](https://bytedance.larkoffice.com/wiki/LJXzwehluiFdzKkb1recZdfonZg) — 剧情制作、电商广告、舞蹈模仿、科普教学、AI MV 等场景
README.md
- Network accessline 7
[Agent skills](https://agentskills.io) for writing effective video generation prompts for [Jimeng Seedance 2.0](https://jimeng.jianying.com/), ByteDance's multimodal AI video generation model. Works with Claude Code, Cursor, Cline, and othe - Network accessline 46
- [Seedance 2.0 User Manual](https://bytedance.larkoffice.com/wiki/A5RHwWhoBiOnjukIIw6cu5ybnXQ) — Parameters, interaction methods, multimodal capabilities, and example prompts - Network accessline 47
- [Seedance 2.0 Real-world Cases](https://bytedance.larkoffice.com/wiki/LJXzwehluiFdzKkb1recZdfonZg) — Drama production, e-commerce ads, dance imitation, science education, AI MVs, and more
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Signal confidence: 6 facts
- Network access in prose of documentationREADME-zh.md:7Low confidence
- Network access in prose of documentationREADME-zh.md:46Low confidence
- Network access in prose of documentationREADME-zh.md:47Low confidence
- Network access in prose of documentationREADME.md:7Low confidence
- Network access in prose of documentationREADME.md:46Low confidence
- Network access in prose of documentationREADME.md:47Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
Add this badge to your README
It updates every night and links to this page.
[](https://hotskills.dev/skill/dexhunter-seedance2-skill/)