Agent skill

Seedance

Generate AI videos using Volcengine Seedance model. An agent skill from freestylefly/wesight.

Install Seedance

skills CLI

$ npx skills add freestylefly/wesight --skill seedance -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install freestylefly/wesight seedance --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/freestylefly/wesight.git skills-src && mkdir -p .claude/skills && cp -r skills-src/SKILLs/seedance .claude/skills/seedance && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "seedance" agent skill from https://github.com/freestylefly/wesight/tree/main/SKILLs/seedance into .claude/skills/seedance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seedance", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/freestylefly/wesight/tree/main/SKILLs/seedance

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add freestylefly/wesight --skill seedance -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install freestylefly/wesight seedance --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/freestylefly/wesight.git skills-src && mkdir -p .agents/skills && cp -r skills-src/SKILLs/seedance .agents/skills/seedance && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "seedance" agent skill from https://github.com/freestylefly/wesight/tree/main/SKILLs/seedance into .agents/skills/seedance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seedance", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add freestylefly/wesight --skill seedance -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install freestylefly/wesight seedance --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/freestylefly/wesight.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/SKILLs/seedance .cursor/skills/seedance && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "seedance" agent skill from https://github.com/freestylefly/wesight/tree/main/SKILLs/seedance into .cursor/skills/seedance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seedance", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/freestylefly/wesight.git --path SKILLs/seedance

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add freestylefly/wesight --skill seedance -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install freestylefly/wesight seedance --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/freestylefly/wesight.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/SKILLs/seedance .gemini/skills/seedance && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "seedance" agent skill from https://github.com/freestylefly/wesight/tree/main/SKILLs/seedance into .gemini/skills/seedance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seedance", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install freestylefly/wesight seedance

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add freestylefly/wesight --skill seedance -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/freestylefly/wesight.git skills-src && mkdir -p .github/skills && cp -r skills-src/SKILLs/seedance .github/skills/seedance && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "seedance" agent skill from https://github.com/freestylefly/wesight/tree/main/SKILLs/seedance into .github/skills/seedance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seedance", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add freestylefly/wesight --skill seedance -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install freestylefly/wesight seedance --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/freestylefly/wesight.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/SKILLs/seedance .opencode/skills/seedance && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "seedance" agent skill from https://github.com/freestylefly/wesight/tree/main/SKILLs/seedance into .opencode/skills/seedance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seedance", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: seedance
GitHub stars: 943
Token cost: ~2.2k tokens
SKILL.md length: 492 words
Files: 4 (incl. scripts)
Skills in repo: 17
Repo updated: Oct 1, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Generate AI videos using Volcengine Seedance model. An agent skill from freestylefly/wesight.

Works in 5 steps: 文本生成视频（T2V） → 图片生成视频（I2V）- 首帧引导 → 图片生成视频（I2V）- 首尾帧引导 → …
The user wants to create
SKILL.md covers 配置, 前置检查, 工作流程 and 配额和限制, plus 5 more sections
Runs PowerShell, Shell and JavaScript scripts from its folder; calls bash; reaches ark.cn-beijing.volces.com; needs ARK_API_KEY and API_KEY

What it does

Seedance is an agent skill from freestylefly/wesight. Generate AI videos using Volcengine Seedance model. Supports text-to-video (T2V), image-to-video (I2V), and audio-synced video generation. Use this skill when the user wants to create or generate videos.

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `scripts/generate-video.sh` and `scripts/generate_video.js`).

It sits in Media & Creative, covering AI video generation. It works with Seedance and Node.js. The repository describes itself as: Open-source desktop AI agent workspace with one-click Claude Code, Codex, OpenClaw, Hermes Agent setup and custom LLM model routing. The licence is MIT.

When your agent uses it

The user wants to create
Generate videos

Example prompts

“/seedance”

Requirements

Python 3
Node.js
A Bash shell
PowerShell
A credential in ARK_API_KEY

Workflow steps

5 steps, taken from the step headings in SKILL.md.

文本生成视频（T2V）
图片生成视频（I2V）- 首帧引导
图片生成视频（I2V）- 首尾帧引导
多参考图生成视频
音画同步视频生成（仅 1.5 pro）

What it can do on your machine

Read from SKILL.md and the folder at commit c913cd9. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 3 files in scripts/ (PowerShell, Shell and JavaScript), which the agent can run.
Shell commands in SKILL.md call:
- bash
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
- ark.cn-beijing.volces.com
Also links to:
- console.volcengine.com
- volcengine.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
- ARK_API_KEY
- API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Seedance loads about 2.2k tokens when it runs. Until then it costs about 53 tokens; SKILL.md has 492 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~53
When it runs · the whole SKILL.md, loaded when a task matches: ~2.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from freestylefly/wesight at commit c913cd9, republished under its MIT licence (© freestylefly). 492 words, ~2,245 tokens.

Download SKILL.mdSave it as .claude/skills/seedance/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.

name: seedance
description: Generate AI videos using Volcengine Seedance model. Supports text-to-video (T2V), image-to-video (I2V), and audio-synced video generation. Use this skill when the user wants to create or generate videos.
official: true
version: 1.0.1

Seedance 视频生成

使用火山引擎 Seedance 模型生成高质量 AI 视频，支持文本生成视频（T2V）、图片生成视频（I2V）、音画同步等多种创作模式。

✨ Node.js 版本：此脚本使用 Node.js 实现，无需 Python 环境。通过入口脚本自动检测 Node.js 运行时（优先使用系统 node，回退到 WeSight 内置运行时），Windows 和 Mac 用户都可以开箱即用。

配置

Base URL: https://ark.cn-beijing.volces.com/api/v3
API Key: 从环境变量 ARK_API_KEY 读取
认证方式: Authorization: Bearer {API_KEY}
SDK: 兼容火山方舟 Python SDK

如何配置 API Key

方式一：通过环境变量配置（推荐）

在终端中设置环境变量：

bash

# macOS/Linux
export ARK_API_KEY="你的API密钥"

# 或者添加到 ~/.zshrc 或 ~/.bashrc 以永久生效
echo 'export ARK_API_KEY="你的API密钥"' >> ~/.zshrc
source ~/.zshrc

powershell

# Windows PowerShell
$env:ARK_API_KEY="你的API密钥"

# 或者设置系统环境变量以永久生效
[System.Environment]::SetEnvironmentVariable('ARK_API_KEY', '你的API密钥', 'User')

方式二：通过 WeSight 启动时注入

WeSight 会自动读取系统环境变量，确保在启动 WeSight 前已设置 ARK_API_KEY。

如何获取 API Key：

访问火山方舟控制台：https://console.volcengine.com/ark/region:ark+cn-beijing/apikey
创建新的 API Key
复制密钥并设置为环境变量

前置检查

无需安装任何依赖！ 该脚本已兼容 Node.js 内置模块。

WeSight 已包含 Node.js 运行时，所有必要的依赖已被自动打包。Windows 和 Mac 用户无需额外配置。

工作流程

Seedance 视频生成是一个异步过程：

提交任务 - 调用 API 创建视频生成任务，获得 task_id
轮询状态 - 每隔几秒查询任务状态，直到状态变为 succeeded
下载视频 - 从 video_url 字段下载生成的 MP4 文件

配额和限制

免费额度

所有 Seedance 模型在 **default 模式（在线推理）**下提供：

200万 token 免费额度
flex 模式（离线推理）无免费额度

注意：文档中未明确说明 200万 token 能生成多少个视频，消耗取决于视频时长、分辨率和是否使用图片/音频。建议先小批量测试。

限流限制

模型系列	RPM（每分钟请求数）	并发数	TPD（离线模式每日token）
Pro 系列	600	10	5000亿
Lite 系列	300	5	2500亿

RPM 限流：账号下同模型每分钟允许创建的任务数量上限
并发数限制：同一时刻在处理中的任务数量上限
TPD 限流：flex 模式下一天内对同一模型的总调用 token 上限

视频保存时间

⚠️ 重要提醒：

任务数据（包括视频URL）仅保留 24 小时
超时后会被自动清除
务必及时下载保存生成的视频

使用示例

路径说明：下面的示例使用 $SKILLS_ROOT 环境变量来引用脚本路径。WeSight 会自动设置这个变量，指向实际的 SKILLs 目录位置，因此无需手动修改路径。

1. 文本生成视频（T2V）

根据文字描述生成视频，适合创意激发和概念验证。

bash

bash "$SKILLS_ROOT/seedance/scripts/generate-video.sh" \
  --prompt "一只小猫在草地上玩耍，阳光明媚，镜头缓缓推进" \
  --duration 5 \
  --output generated_video.mp4

示例提示词：

"写实风格，晴朗的蓝天之下，一大片白色的雏菊花田，镜头逐渐拉近，最终定格在一朵雏菊花的特写上，花瓣上有几颗晶莹的露珠"
"一辆地铁轰隆隆驶过，书页飞扬，镜头开始环绕着女孩360度旋转"
"海边日落，海浪轻拍沙滩，宁静祥和的氛围"

2. 图片生成视频（I2V）- 首帧引导

基于首帧图片生成动态视频，支持本地图片和网络URL。

bash

# 使用本地图片
bash "$SKILLS_ROOT/seedance/scripts/generate-video.sh" \
  --prompt "女孩睁开眼，温柔地看向镜头，头发被风吹动" \
  --image "/Users/yourname/Pictures/girl.jpg" \
  --duration 5 \
  --output i2v_video.mp4

# 使用网络图片
bash "$SKILLS_ROOT/seedance/scripts/generate-video.sh" \
  --prompt "女孩睁开眼，温柔地看向镜头，头发被风吹动" \
  --image "https://example.com/first_frame.jpg" \
  --duration 5 \
  --output i2v_video.mp4

支持的图片来源：

✅ 本地文件：/path/to/image.jpg
✅ 网络URL：https://example.com/image.jpg
✅ file://协议：file:///path/to/image.jpg

支持的图片格式：

jpg, jpeg, png, gif, webp, bmp, tiff, heic

3. 图片生成视频（I2V）- 首尾帧引导

提供首帧和尾帧，生成过渡动画。支持本地图片。

bash

bash "$SKILLS_ROOT/seedance/scripts/generate-video.sh" \
  --prompt "360度环绕运镜，流畅过渡" \
  --image "/Users/yourname/Pictures/first_frame.jpg" \
  --image "/Users/yourname/Pictures/last_frame.jpg" \
  --duration 5 \
  --output transition_video.mp4

4. 多参考图生成视频

融合多张参考图的特征生成视频。支持混合使用本地图片和网络图片。

bash

bash "$SKILLS_ROOT/seedance/scripts/generate-video.sh" \
  --prompt "[图1]戴着眼镜穿着蓝色T恤的男生和[图2]的柯基小狗，坐在[图3]的草坪上，视频卡通风格" \
  --image "/Users/yourname/Pictures/person.jpg" \
  --image "https://example.com/dog.jpg" \
  --image "/Users/yourname/Pictures/grass.jpg" \
  --model "doubao-seedance-1-0-lite-i2v-250428" \
  --duration 5 \
  --output multi_ref_video.mp4

5. 音画同步视频生成（仅 1.5 pro）

生成包含音频的视频（环境音、动作音、背景音乐等）。支持本地图片。

bash

bash "$SKILLS_ROOT/seedance/scripts/generate-video.sh" \
  --prompt "镜头围绕人物推镜头拉近，特写人物面部，她正在用京剧唱腔唱'月移花影，疑是玉人来'，唱词充满情感" \
  --image "/Users/yourname/Pictures/actress.jpg" \
  --audio \
  --duration 5 \
  --model "doubao-seedance-1-5-pro-251215" \
  --output audio_video.mp4

参数说明

必需参数

参数	说明	示例
`--prompt`	视频描述提示词（必需）	"小猫在玩耍"

可选参数

参数	说明	默认值	可选值
`--image`	参考图片路径或URL（可多次使用）	无	本地文件路径或URL
`--model`	模型ID	`doubao-seedance-1-5-pro-251215`	见模型列表
`--duration`	视频时长（秒）	5	2-12（不同模型范围不同）
`--ratio`	宽高比	`adaptive`	`adaptive`, `16:9`, `9:16`, `1:1`
`--audio`	生成音频（仅1.5 pro支持）	否	标志参数
`--no-watermark`	不添加水印	否	标志参数
`--output`	输出文件路径	`generated_video.mp4`	文件路径
`--poll-interval`	状态查询间隔（秒）	5	1-10
`--timeout`	最大等待时间（秒）	300	60-600

模型选择

选择合适的模型以平衡质量、速度和成本：

Seedance 1.5 pro（推荐）

模型ID: doubao-seedance-1-5-pro-251215
特点: 音画同生，最高质量
支持: 文生视频、图生视频、首尾帧、有声视频
输出: 480p-1080p，24fps，4-12秒
限流: RPM 600，并发10

Seedance 1.0 pro

模型ID: doubao-seedance-1-0-pro-250528
特点: 高质量标准版本
支持: 文生视频、图生视频、首尾帧
输出: 480p-1080p，24fps，2-12秒
限流: RPM 600，并发10

Seedance 1.0 pro fast

模型ID: doubao-seedance-1-0-pro-fast-251015
特点: 快速生成，成本更低
支持: 文生视频、图生视频
输出: 480p-1080p，24fps，2-12秒
限流: RPM 600，并发10

Seedance 1.0 lite（轻量版）

文生视频: doubao-seedance-1-0-lite-t2v-250428
图生视频: doubao-seedance-1-0-lite-i2v-250428
特点: 更快速度，支持多参考图
限流: RPM 300，并发5

Show full SKILL.md (199 more words)Show less

Seedance 2.0（即将支持）

模型ID: doubao-seedance-2-0-260128
特点: 下一代视频生成模型，质量和性能全面提升
可用性: ⏰ 预计 2026年2月24日18点 开放 API 调用
当前状态: 仅在控制台体验中心可用

使用方式（2月24日后）：

bash

# 命令行方式
bash "$SKILLS_ROOT/seedance/scripts/generate-video.sh" \
  --prompt "你的提示词" \
  --model "doubao-seedance-2-0-260128" \
  --duration 5

或在 WeSight 对话中说："用 Seedance 2.0 生成视频..."

推荐使用场景：

追求最高质量 + 音画同步 → 1.5 pro
标准高质量视频 → 1.0 pro
快速生成预览 → 1.0 pro fast
多参考图融合 → 1.0 lite
下一代最新模型（2月24日后）→ 2.0

高级选项

自定义宽高比

根据使用场景选择合适的宽高比：

bash

# 横屏视频（适合 YouTube、B站）
--ratio "16:9"

# 竖屏视频（适合抖音、快手）
--ratio "9:16"

# 正方形视频（适合 Instagram）
--ratio "1:1"

# 自适应（根据内容自动选择）
--ratio "adaptive"

自定义视频时长

不同模型支持的时长范围不同：

bash

# 短视频（快速生成）
--duration 2

# 标准时长
--duration 5

# 长视频（内容更丰富）
--duration 10

注意：

Seedance 1.5 pro 支持 4-12 秒
Seedance 1.0 系列支持 2-12 秒
时长越长，生成时间越久

去除水印

生成无水印视频（用于商业用途）：

bash

--no-watermark

轮询和超时控制

调整轮询策略以适应不同场景：

bash

# 快速查询（适合短视频）
--poll-interval 3 --timeout 180

# 标准配置
--poll-interval 5 --timeout 300

# 耐心等待（适合长视频或高峰期）
--poll-interval 10 --timeout 600

状态说明

生成过程中可能出现的任务状态：

状态	说明	操作
`queued`	任务排队中	继续等待
`running`	正在生成视频	继续等待
`succeeded`	生成成功	下载视频
`failed`	生成失败	查看错误信息

错误处理

常见错误及解决方案

错误：未设置环境变量 ARK_API_KEY

原因：未配置 API Key
解决：按照"如何配置 API Key"部分的说明进行配置

错误：任务创建失败 (HTTP 401)

原因：API Key 无效或已过期
解决：检查 API Key 是否正确，或在控制台重新生成

错误：任务创建失败 (HTTP 400)

原因：参数错误（如 duration 超出范围）
解决：检查参数是否符合模型要求

错误：任务超时

原因：生成时间过长或 API 繁忙
解决：增加 --timeout 值，或稍后重试

错误：任务失败

原因：内容违规、提示词不清晰、图片格式错误等
解决：检查提示词内容，确保图片URL可访问

错误：限流 (HTTP 429)

原因：超过 RPM 或并发限制
解决：等待1分钟后重试，或升级配额

输出格式

生成的视频具有以下特征：

格式: MP4
编码: H.264
分辨率: 480p / 720p / 1080p（根据模型自动选择）
帧率: 24 fps
音频: AAC（如果启用 --audio）
文件大小: 约 2-5 MB/秒（1080p）

提示词最佳实践

优秀提示词的特点

清晰的场景描述 - 说明环境、时间、氛围
具体的动作细节 - 描述物体或人物的具体动作
镜头运动 - 说明推拉摇移、特写等镜头语言
风格指定 - 写实、卡通、动漫等风格说明

提示词模板

[风格]，[场景描述]，[主体动作]，[镜头运动]，[氛围/情绪]

示例：

写实风格，海边日落，一只海鸥在空中盘旋，镜头从远处缓缓推进到海鸥特写，宁静祥和的氛围

提示词注意事项

✅ 具体描述："小猫追逐蝴蝶" 而非 "小猫玩耍"
✅ 镜头语言："镜头360度环绕" 而非 "旋转"
✅ 情绪氛围："温暖明亮的阳光" 而非 "好天气"
❌ 避免模糊：过于抽象的描述会导致随机性增加
❌ 避免过长：保持在 200 字以内效果最佳
❌ 避免违规：不要包含暴力、色情等违规内容

常见使用场景

短视频创作

bash

bash "$SKILLS_ROOT/seedance/scripts/generate-video.sh" \
  --prompt "产品展示：智能手表从不同角度旋转展示" \
  --ratio "9:16" \
  --duration 5

动画短片

bash

bash "$SKILLS_ROOT/seedance/scripts/generate-video.sh" \
  --prompt "卡通风格，小兔子在森林里蹦蹦跳跳" \
  --ratio "16:9" \
  --duration 8 \
  --model "doubao-seedance-1-0-pro-250528"

社交媒体内容

bash

bash "$SKILLS_ROOT/seedance/scripts/generate-video.sh" \
  --prompt "美食特写：热气腾腾的拉面，筷子夹起面条" \
  --ratio "1:1" \
  --duration 3

教学演示

bash

bash "$SKILLS_ROOT/seedance/scripts/generate-video.sh" \
  --prompt "科普动画：地球自转，太阳光照射地球表面" \
  --ratio "16:9" \
  --duration 10

参考资料

API 参考：https://www.volcengine.com/docs/82379/1520758
控制台：https://console.volcengine.com/ark
API Key 管理：https://console.volcengine.com/ark/region:ark+cn-beijing/apikey

技术支持

如遇到问题，可以：

查看脚本输出的错误信息
检查 API Key 配置是否正确
访问火山方舟控制台查看任务详情
参考官网文档了解更多细节

Files

SKILL.md and 3 other files (scripts) in SKILLs/seedance of freestylefly/wesight.

SKILL.md
scripts/generate-video.ps1
scripts/generate-video.sh
scripts/generate_video.js

Open the folder on GitHubat commit c913cd9

Compare with similar skills

Seedance next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Seedance compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Seedance this skillfreestylefly/wesight	943	—	~2.2k	Automated safety check: Pass	MIT	7 days ago
Script To Shootable Storyboardzyz254009-crypto/script-to-shootable-storyboard	117	—	~1.9k	Automated safety check: Pass	MIT	2 mo ago
Seedance Storyboard Generatorliangdabiao/Seedance2-Storyboard-Generator	2.5k	—	~2.2k	Automated safety check: Pass	None	17 days ago
Libtv Videonexu-io/nexu	3.3k	—	~3.5k	Automated safety check: Pass	MIT	5 mo ago
Analyze Videokrusemediallc/arcads-claude-code	1.6k	—	~4.2k	Automated safety check: Pass	MIT	16 days ago
Imagesmixs/visual-skills	484	—	~2.1k	Automated safety check: Pass	CC-BY-4.0	22 days ago

Similar skills

Script To Shootable Storyboard
zyz254009-crypto/script-to-shootable-storyboard
将剧本、故事梗概、对白稿、已有分镜或视频生成提示转换、检查并优化为可拍、可剪、适合 Seedance、真人或混合制作的原子分镜。用于剧本转分镜、分镜可拍化、后续场景开发、反馈驱动迭代、不连贯诊断与修复、心理描写视觉化、单镜主导景别拆分、短剧钩子与节奏、台词和声音时长、人物道具连续性、Seedance Generation Task、生成风险与失败降级；默认忠实转换，未获授权不得改写剧情。
117 GitHub stars~1.9k tokensUpdated 2 mo ago
Media & CreativeAuto-check passed
Seedance Storyboard Generator
liangdabiao/Seedance2-Storyboard-Generator
专业的Seedance 2.0平台AI视频脚本和分镜生成器。当用户要求：(1) 将文章/故事转换为视频脚本，(2) 生成Seedance 2.0分镜提示词，(3) 规划多集AI视频系列，(4) 为GPT-Image-2、Seedream、Nano Banana…
2.5k GitHub stars~2.2k tokensUpdated 17 days ago
Media & CreativeAuto-check passed
Libtv Video
nexu-io/nexu
Seedance 2.0 video & image generation via LibTV Gateway - AI text-to-video, image-to-video, video continuation, style transfer, and text-to-image using Seedance 2.0 model.
3.3k GitHub stars~3.5k tokensUpdated 5 mo ago
Media & CreativeAuto-check passed
Analyze Video
krusemediallc/arcads-claude-code
Analyze a reference video and reverse-engineer its style into a reusable Seedance 2.0 prompting template.
1.6k GitHub stars~4.2k tokensUpdated 16 days ago
Media & CreativeAuto-check passed
Image
smixs/visual-skills
Image prompting skill for Nano Banana (NBP/NB2) and GPT Image 2.5 (Flare/Sunburst).
484 GitHub stars~2.1k tokensUpdated 22 days ago
Media & CreativeAuto-check passed
Jianying Video Gen
cclank/lanshu-waytovideo
使用剪映(Jianying/小云雀)的 Seedance 2.0 模型自动生成AI视频。支持文生视频(T2V)、图生视频(I2V)、参考视频生成(V2V)和向后延伸(Extend)四种模式。当用户需要生成AI视频、使用Seedance模型创作短片、基于参考图像/视频进行风格转换，或对已有结果继续延长时使用此技能。需要预先配置 cookies.json 登录凭证。
252 GitHub stars~760 tokensUpdated 6 mo ago
Media & CreativeAuto-check passed

Questions about Seedance

What does Seedance do?

Generate AI videos using Volcengine Seedance model. An agent skill from freestylefly/wesight. Seedance is an agent skill from freestylefly/wesight. Generate AI videos using Volcengine Seedance model.

When should I use Seedance?

Seedance fits situations like: the user wants to create; generate videos.

How do I install Seedance in Claude Code?

Run `npx skills add freestylefly/wesight --skill seedance -a claude-code`. Or copy the skill folder (SKILLs/seedance in freestylefly/wesight) into .claude/skills/seedance in your project. Claude Code loads it when a task matches its description.

How do I install Seedance in Codex?

Run `npx skills add freestylefly/wesight --skill seedance -a codex`. Or copy the skill folder (SKILLs/seedance in freestylefly/wesight) into .agents/skills/seedance in your project. Codex loads it when a task matches its description.

Can I use Seedance in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add freestylefly/wesight --skill seedance -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/seedance, .gemini/skills/seedance, .github/skills/seedance and .opencode/skills/seedance in your project.

What does Seedance need to run?

Going by SKILL.md and its folder, Seedance needs PowerShell, a shell and JavaScript for the scripts in its folder, the command-line tools its instructions call (bash) and credentials named ARK_API_KEY and API_KEY. Our summary lists: Python 3; Node.js; A Bash shell; PowerShell; A credential in ARK_API_KEY.

Does Seedance access the network?

SKILL.md names 3 domains. In commands or code: ark.cn-beijing.volces.com; the agent is likely to contact it when it follows the instructions. As links in the text: console.volcengine.com and volcengine.com. This is read from the text; nothing was executed.

Is Seedance safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Seedance use?

Seedance is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Seedance use?

About 2.2k tokens (SKILL.md is roughly 9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Seedance?

Skills that share tags, products or a category with Seedance: Script To Shootable Storyboard (zyz254009-crypto/script-to-shootable-storyboard, 117 stars), Seedance Storyboard Generator (liangdabiao/Seedance2-Storyboard-Generator, 2.5k stars), Libtv Video (nexu-io/nexu, 3.3k stars) and Analyze Video (krusemediallc/arcads-claude-code, 1.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Seedance?

freestylefly (a GitHub user) maintains it in freestylefly/wesight, which has 943 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 1, 2026.

Source: freestylefly/wesight on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Seedance

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Seedance 视频生成

配置

如何配置 API Key

前置检查

工作流程

配额和限制

免费额度

限流限制

视频保存时间

使用示例

1. 文本生成视频（T2V）

2. 图片生成视频（I2V）- 首帧引导

3. 图片生成视频（I2V）- 首尾帧引导

4. 多参考图生成视频

5. 音画同步视频生成（仅 1.5 pro）

参数说明

必需参数

可选参数

模型选择

Seedance 1.5 pro（推荐）

Seedance 1.0 pro

Seedance 1.0 pro fast

Seedance 1.0 lite（轻量版）

Seedance 2.0（即将支持）

高级选项

自定义宽高比

自定义视频时长

去除水印

轮询和超时控制

状态说明

错误处理

常见错误及解决方案

输出格式

提示词最佳实践

优秀提示词的特点

提示词模板

提示词注意事项

常见使用场景

短视频创作

动画短片

社交媒体内容

教学演示

参考资料

技术支持

Files

Compare with similar skills

Similar skills

More from freestylefly/wesight

Related

Questions about Seedance