Agent skill

Seedance Debugger

by cclank in cclank/lanshu-awesome-ai-video-kit

诊断 Seedance 2.0 生成视频时出现的常见问题（人物 ID 漂移/双胞胎/字幕/Logo/风格漂移/延长跳变/画质劣化/特效不对/中文发音/音色不准/结尾噪音等 12 类），定位根因并给出修复后的提示词。用于"我的提示词生成出来不对"、"视频里出现奇怪的字幕"、"人脸不像参考图"、"出现两个一样的人物"、"风格变了"、"怎么修这个提示词"等触发场景。

MITAuto-check passedMedia & Creative

Install Seedance Debugger

skills CLI

$ npx skills add cclank/lanshu-awesome-ai-video-kit --skill seedance-debugger -a claude-code

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

GitHub CLI

$ gh skill install cclank/lanshu-awesome-ai-video-kit seedance-debugger --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/cclank/lanshu-awesome-ai-video-kit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/seedance-debugger .claude/skills/seedance-debugger && 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-debugger" agent skill from https://github.com/cclank/lanshu-awesome-ai-video-kit/tree/main/skills/seedance-debugger into .claude/skills/seedance-debugger/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seedance-debugger", 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/cclank/lanshu-awesome-ai-video-kit/tree/main/skills/seedance-debugger

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 cclank/lanshu-awesome-ai-video-kit --skill seedance-debugger -a codex

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

GitHub CLI

$ gh skill install cclank/lanshu-awesome-ai-video-kit seedance-debugger --agent codex

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

Manual copy

$ git clone --depth 1 https://github.com/cclank/lanshu-awesome-ai-video-kit.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/seedance-debugger .agents/skills/seedance-debugger && 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-debugger" agent skill from https://github.com/cclank/lanshu-awesome-ai-video-kit/tree/main/skills/seedance-debugger into .agents/skills/seedance-debugger/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seedance-debugger", 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 cclank/lanshu-awesome-ai-video-kit --skill seedance-debugger -a cursor

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

GitHub CLI

$ gh skill install cclank/lanshu-awesome-ai-video-kit seedance-debugger --agent cursor

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

Manual copy

$ git clone --depth 1 https://github.com/cclank/lanshu-awesome-ai-video-kit.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/seedance-debugger .cursor/skills/seedance-debugger && 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-debugger" agent skill from https://github.com/cclank/lanshu-awesome-ai-video-kit/tree/main/skills/seedance-debugger into .cursor/skills/seedance-debugger/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seedance-debugger", 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/cclank/lanshu-awesome-ai-video-kit.git --path skills/seedance-debugger

--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 cclank/lanshu-awesome-ai-video-kit --skill seedance-debugger -a gemini-cli

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

GitHub CLI

$ gh skill install cclank/lanshu-awesome-ai-video-kit seedance-debugger --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/cclank/lanshu-awesome-ai-video-kit.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/seedance-debugger .gemini/skills/seedance-debugger && 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-debugger" agent skill from https://github.com/cclank/lanshu-awesome-ai-video-kit/tree/main/skills/seedance-debugger into .gemini/skills/seedance-debugger/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seedance-debugger", 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 cclank/lanshu-awesome-ai-video-kit seedance-debugger

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 cclank/lanshu-awesome-ai-video-kit --skill seedance-debugger -a github-copilot

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

Manual copy

$ git clone --depth 1 https://github.com/cclank/lanshu-awesome-ai-video-kit.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/seedance-debugger .github/skills/seedance-debugger && 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-debugger" agent skill from https://github.com/cclank/lanshu-awesome-ai-video-kit/tree/main/skills/seedance-debugger into .github/skills/seedance-debugger/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seedance-debugger", 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 cclank/lanshu-awesome-ai-video-kit --skill seedance-debugger -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 cclank/lanshu-awesome-ai-video-kit seedance-debugger --agent opencode

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

Manual copy

$ git clone --depth 1 https://github.com/cclank/lanshu-awesome-ai-video-kit.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/seedance-debugger .opencode/skills/seedance-debugger && 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-debugger" agent skill from https://github.com/cclank/lanshu-awesome-ai-video-kit/tree/main/skills/seedance-debugger into .opencode/skills/seedance-debugger/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seedance-debugger", 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-debugger
GitHub stars: 412
Token cost: ~1.5k tokens
SKILL.md length: 393 words
Files: 1
Skills in repo: 4
Repo updated: Oct 7, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Works in 12 steps: 人物 ID 漂移 → 字幕 → Logo / 水印 → …
Tasks that involve AI video generation
SKILL.md covers 何时不用此 skill, 12 类问题诊断手册, 工作流程 and 实战示例, plus 1 more section
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Seedance Debugger is an agent skill from cclank/lanshu-awesome-ai-video-kit. 诊断 Seedance 2.0 生成视频时出现的常见问题（人物 ID 漂移/双胞胎/字幕/Logo/风格漂移/延长跳变/画质劣化/特效不对/中文发音/音色不准/结尾噪音等 12 类），定位根因并给出修复后的提示词。用于"我的提示词生成出来不对"、"视频里出现奇怪的字幕"、"人脸不像参考图"、"出现两个一样的人物"、"风格变了"、"怎么修这个提示词"等触发场景。

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Media & Creative, covering AI video generation. It works with Seedance. The repository describes itself as: 做企业 AI 视频项目逼出来的工具包 · 411 prompt · 15 模型 · 7 Claude Skill · 14 篇方法论. The licence is MIT.

When your agent uses it

Tasks that involve AI video generation

Example prompts

“我的提示词生成出来不对”
“视频里出现奇怪的字幕”
“人脸不像参考图”
“/seedance-debugger”

Workflow steps

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

人物 ID 漂移
字幕
Logo / 水印
风格漂移
延长跳变
双胞胎
画质劣化
特效不对
参考人物过多
结尾噪音
中文发音
音色不准

What it can do on your machine

Read from SKILL.md and the folder at commit f4c1bbd. 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
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Seedance Debugger loads about 1.5k tokens when it runs. Until then it costs about 50 tokens; SKILL.md has 393 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~50
When it runs · the whole SKILL.md, loaded when a task matches: ~1.5k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from cclank/lanshu-awesome-ai-video-kit at commit f4c1bbd, republished under its MIT licence (© cclank). 393 words, ~1,501 tokens.

Download SKILL.mdSave it as .claude/skills/seedance-debugger/SKILL.md (or your agent's skills folder).

name: seedance-debugger
description: 诊断 Seedance 2.0 生成视频时出现的常见问题（人物 ID 漂移/双胞胎/字幕/Logo/风格漂移/延长跳变/画质劣化/特效不对/中文发音/音色不准/结尾噪音等 12 类），定位根因并给出修复后的提示词。用于"我的提示词生成出来不对"、"视频里出现奇怪的字幕"、"人脸不像参考图"、"出现两个一样的人物"、"风格变了"、"怎么修这个提示词"等触发场景。

seedance-debugger

输入：有问题的提示词 + 用户描述的症状（或视频截图）。输出：诊断（根因） + 修复后的提示词 + 解释为什么这样改。

何时不用此 skill

提示词完全没写，只是想要新提示词 → seedance-prompter
想拆复杂剧情 → seedance-storyboard

12 类问题诊断手册

详见 methodology/08-避坑12问.md。这里给出快速决策树。

症状识别 → 跳转

用户说的症状	跳转
"人脸不像 / 中途换脸 / 撞脸明星"	#1 人物-id-漂移
"莫名出现字幕 / 视频里有文字"	#2 字幕
"有水印 / 有 Logo"	#3 logo-水印
"动漫风格变成真人了 / 风格变了"	#4 风格漂移
"拼接处跳帧 / 衔接不流畅"	#5 延长跳变
"出现两个一模一样的人"	#6 双胞胎
"延长后画质变糊 / 人脸有斑驳色块"	#7 画质劣化
"特效不对 / 倒计时乱跳"	#8 特效不对
"人物多了/少了"	#9 参考人物过多
"结尾有咔哒声"	#10 结尾噪音
"中文读错字了"	#11 中文发音
"音色不像参考音频"	#12 音色不准

1. 人物 ID 漂移

根因：参考图混用（人脸 + 全身 + 服装在一张图） OR 人脸占比过小。

修复策略：

让用户额外准备一张大头照（只包含面部，无表情最佳）
提示词中明确区分：<主体1> 的面部特征参考图片1（大头照），妆造参考图片2（全身照）
重要素材前置

反例：将图1中的人物作为主角... 正例：将@图片1（大头照）的面部特征作为主角面部锚点，@图片2（全身照）作为整体妆造参考。主角...

2. 字幕

根因：参考图/视频中包含文字；竖屏更易触发。

修复策略：

加约束：保持无字幕，避免生成任何文字或字幕
如果参考素材包含文字 → 先用 Seedream 编辑去除
业务允许下，优先横屏生成

3. Logo / 水印

修复策略：在提示词末尾加 不要生成水印，不要生成Logo

4. 风格漂移

根因：参考图风格与目标风格不一致 + 提示词未强调风格。

修复策略：

在提示词中明确风格约束：2D 日漫风格 / 3D 国风漫画 / 写实电影感
更精准的做法：先把参考图变成目标风格，再生视频

5. 延长跳变

根因：模型续写帧与原视频帧对齐误差。

修复策略（后期剪辑修补）：

把视频导入剪映
前一段视频末尾删 6 帧
后一段视频开头删 1 帧
重复所有拼接点
续写时以转场切镜的时刻结尾，下一段以结尾切镜后的新场景为起始

6. 双胞胎

根因：人物三视图作参考 OR 主体定义不清晰。

修复策略：

明确人物主体关联：张三（对应图片1）将绿色存折扔向站立的李四（对应图片2）

添加全局约束：

视频全程禁止出现外形、着装、配饰完全一致的人物，
禁止生成同款分身、双胞胎效果，
同一画面中仅保留单个对应人物，不出现人物重复复刻。

优化参考素材：单人独立照片，不用三视图
精简提示词：别把完整剧本塞进去

7. 画质劣化

根因：延长续写时画质逐次衰减，尤其人脸区域。

修复策略：

白模中转法：先用 Seedance 把原视频转为白模视频，再做续写输入
- 参考提示词：将视频转为白色 3D 模型，人物统一为纯白 3D 模型，无色彩、无纹理、无阴影，纯白背景，结构稳定、运动流畅
优先选高清图片作参考
控制续写次数，避免多次叠加

8. 特效不对

根因：文字描述特效，模型理解偏差。

修复策略：用参考视频定义特效，让模型精准理解形态与运动逻辑。

例：数字"2999"出场方式参考视频1

9. 参考人物过多

根因：>4 人时输出稳定性下降。

修复策略：分步生成

把人物分组（如 6 人分成 2 组每组 3 人），分别生成图片
用第一步的分组图片作参考，生成最终视频

10. 结尾噪音

修复策略：用剪映音量包络线做音频淡出

视频导入剪映
选音轨 → 音频 → 音量包络线
视频临近结尾处，末尾音量关键点下拉至 0，形成向下斜坡

11. 中文发音

修复策略：把易读错字换成发音一致的常用同音字

例：鳞龙山 → 吃龙山

12. 音色不准

修复策略：

提示词中补充细致音色特征描述：使用@音频1低厚温润带细碎颗粒感中年男声的音色说"……"
保持台词风格与参考音频的语气、表述风格相近

工作流程

步骤 1：症状采集

如果用户只说"效果不对"，问 3 个问题（必问）：

症状是什么（看到了什么不该看的 / 没看到什么该看的）？
原始提示词是什么？
用了什么参考素材（图/视频/音频）？

步骤 2：诊断 → 输出

对照上面 12 类，给出诊断报告：

markdown

## 诊断

**症状**：[用户描述]
**对应问题类别**：第 N 类「问题名」
**根因**：[2-3 句解释]

## 修复后的提示词

\`\`\`
[修复版提示词]
\`\`\`

## 改了什么

| 原版 | 修复版 | 原因 |
|---|---|---|
| [片段] | [片段] | [说明] |

## 还可能的根因

如果上面修复还不行，可能是 [其他可能性]，可以再问我。

步骤 3：必要时升级建议

如果症状是"延长画质劣化"、"音色不准"这类靠提示词解决不了 100% 的问题，明确告诉用户：

⚠️ 这是当前 Seedance 2.0 的已知限制，提示词只能降低出现概率，无法 100% 规避。建议：[具体的后期补救方案]

Show full SKILL.md (155 more words)Show less

实战示例

示例 1：双胞胎（最常踩）

用户输入：

我让两个角色对手戏，结果生成出来画面里有四个一模一样的人，提示词是这个：
一个穿红色西装的男人和一个穿蓝色西装的男人在会议室争吵，桌上有文件散落，
他们都看起来很愤怒，镜头中景跟拍。参考图1是红西装男的三视图。
参考素材就一张三视图。

诊断

项	内容
症状	画面出现 4 个相同人物（应该 2 个）
对应类别	第 6 类「双胞胎」
根因	(1) 三视图作参考 — 模型把同一人的不同角度当成多个人。(2) 主体定义不清晰 — 提示词没有 `（对应图片X）` 明确归属。(3) 缺少全局禁分身约束。

修复版

将@图片1（三视图取正面）的男性定义为「张三」，穿红色西装；
另一名男性「李四」穿蓝色西装（无参考图，自由生成，与张三外貌差异显著）。

会议室场景。张三（红西装）与李四（蓝西装）隔着会议桌争吵，
桌面散落文件。张三右手拍桌，李四起身指向张三。中景跟拍，
镜头从张三背后绕到李四正面。

视频全程禁止出现外形、着装、配饰完全一致的人物，
禁止生成同款分身、双胞胎效果，同一画面中仅保留张三与李四两人，
不出现人物重复复刻。不要生成水印、Logo、字幕。

改了什么

原版	修复版	原因
`参考图1是红西装男的三视图`	`@图片1（三视图取正面）`	显式选单一视角，避免模型把三视图理解成三个人
`一个穿红色...一个穿蓝色...`	`「张三」（对应图片1）...「李四」（无参考图）`	明确人物-参考图归属
(无)	加禁分身约束块	全局约束兜底
(无)	`Logo / 字幕` 约束	顺手堵第 2、3 类风险

还可能的根因：如果还出现重复，把"参考图1"换成单角度独立照（不用三视图），问题解决率 > 90%。

示例 2：风格漂移

用户输入：

我想生成日漫风格的女主走路，结果出来是真人。
一个长发女孩走在樱花飘落的街道上，粉色头发，大眼睛，微笑。
参考图是这个女孩的真人照片。

诊断

项	内容
症状	目标是 2D 日漫，输出是真人
对应类别	第 4 类「风格漂移」
根因	(1) 参考图是真人照，模型默认沿用真人风格。(2) 提示词没明确风格约束，只描述了人物外观特征。

修复策略：两步走比纯改提示词更可靠。

第一步：先用 Seedream 把真人参考图转为日漫风格图（prompt 示例：将这张照片转为 2D 日漫赛璐璐风格，保留人物五官特征，大眼睛、樱花色调）。

第二步：用转好的日漫风参考图，搭配下面修复版提示词：

2D 日漫赛璐璐风格，@图片1 的粉发女孩走在樱花飘落的街道上，
微风吹动发丝，樱花瓣缓慢飘落。中景跟拍，镜头从侧面缓慢推近，
最后停在她回眸微笑的特写。柔和粉色调，边缘清晰的线稿感，
扁平上色，无写实质感，无毛孔细节。不要生成水印、Logo、字幕。

改了什么

原版	修复版	原因
(参考图：真人照)	先转日漫图再做参考	风格锚点要和目标风格一致
(无风格约束)	`2D 日漫赛璐璐风格...扁平上色，无写实质感`	显式锁死风格，正反向约束

还可能的根因：如果只改提示词不换参考图，模型仍有 50%+ 概率漂回真人 — 参考图是风格主锚点，必须先改它。

示例 3：字幕 + 水印一起出

用户输入：

视频右下角莫名出现一个商店招牌字幕，左上角还有个像水印的东西。提示词：
雨天的咖啡馆窗外，一个女人撑伞走过，镜头透过雨水模糊的玻璃拍摄。

诊断

项	内容
症状	右下角字幕 + 左上角水印
对应类别	第 2 类「字幕」 + 第 3 类「Logo/水印」
根因	提示词完全没有约束词。"咖啡馆" + "窗外"语境会让模型自动加店招/标语作为环境元素；竖屏更易触发字幕。

修复版

雨天的咖啡馆窗外，一个女人撑伞缓步走过，镜头透过雨水模糊的玻璃拍摄。
雨滴沿玻璃斜流，女人身影在水雾中朦胧，背景街道灯光晕染成暖色光斑。
中景固定机位，景深浅，玻璃前景虚化。

保持无字幕，避免生成任何文字或字幕；
不要生成水印，不要生成 Logo；
玻璃窗及背景街道不出现任何店招、标语、品牌文字。

改了什么

原版	修复版	原因
(无约束词)	`保持无字幕，避免生成任何文字或字幕`	第 2 类标准约束
(无约束词)	`不要生成水印，不要生成 Logo`	第 3 类标准约束
(无约束词)	`不出现任何店招、标语、品牌文字`	针对"咖啡馆"语境的精准补刀

还可能的根因：如果业务允许，改横屏会进一步降低字幕概率（竖屏 9:16 容易把字幕当海报排版处理）。

参考资源

Masterclass(10 YouTube 教学综合):methodology/15-seedance-masterclass.md — 实战避坑 12 条扩展(头盔消失/超 3 角色/上传失败/超字符限制/AI 乱切/音频太模糊)
12 问完整版：methodology/08-避坑12问.md
约束词清单：methodology/06-约束词清单.md
特殊字符规范：methodology/07-特殊字符规范.md

Files

Just SKILL.md in skills/seedance-debugger of cclank/lanshu-awesome-ai-video-kit.

Open the folder on GitHubat commit f4c1bbd

Compare with similar skills

Seedance Debugger 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 Debugger compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Seedance Debugger this skillcclank/lanshu-awesome-ai-video-kit	412	—	~1.5k	Automated safety check: Pass	MIT	today
Seedancesongguoxs/seedance-prompt-skill	2.9k	1 repos	~2.5k	Automated safety check: Pass	None	7 mo ago
SN Motion HTMLOpenSenseNova/SenseNova-Skills	5.7k	—	~2.2k	Automated safety check: Notes	MIT	19 days ago
Seedance Prompt Endexhunter/seedance2-skill	4.2k	—	~3.8k	Automated safety check: Pass	MIT	18 days ago
Seedance Japanese Prompt ExamplesEmily2040/seedance-2.0	7.5k	1 repos	~898	Automated safety check: Pass	MIT	4 days ago
Seedance 2 5 Video Directorliyue-aigc/seedance-2-5-video-director	546	—	~3.5k	Automated safety check: Pass	MIT	1 mo ago

Similar skills

Seedance
songguoxs/seedance-prompt-skill
This skill should be used when the user asks to "generate video prompts", "create Seedance prompts", "write video descriptions", mentions "Seedance", "seedance", "即梦", "即梦平台", "视频提示词", "视频生成"…
2.9k GitHub starsUsed in 1 repo~2.5k tokens
Media & CreativeAuto-check passed
SN Motion HTML
OpenSenseNova/SenseNova-Skills
Builds HTML stories where one continuous camera journey advances with page progress, using researched structure, AI stills, Seedance video clips and browser QA.
5.7k GitHub stars~2.2k tokensUpdated 19 days ago
Media & CreativeAuto-check: notes
Seedance Prompt En
dexhunter/seedance2-skill
Write effective prompts for Jimeng Seedance 2.0 multimodal AI video generation.
4.2k GitHub stars~3.8k tokensUpdated 18 days ago
Media & CreativeAuto-check passed
Seedance Japanese Prompt Examples
Emily2040/seedance-2.0
Provides Japanese prompt patterns and safe example rewrites for Seedance 2.0 video generation, with reference tags kept intact and each example labeled by risk.
7.5k GitHub starsUsed in 1 repo~898 tokens
Media & CreativeAuto-check passed
Seedance 2 5 Video Director
liyue-aigc/seedance-2-5-video-director
Design, derive, optimize, diagnose, and rewrite scripts or copy-ready prompts specifically for Dreamina/即梦 Seedance 2.5.
546 GitHub stars~3.5k tokensUpdated 1 mo ago
Media & CreativeAuto-check passed
Seedance Prompt Zh
dexhunter/seedance2-skill
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。
4.2k GitHub stars~1.9k tokensUpdated 18 days ago
Media & CreativeAuto-check passed

More from cclank/lanshu-awesome-ai-video-kit

Happyhorse Prompter
cclank/lanshu-awesome-ai-video-kit
生成符合 HappyHorse 1.0 严格规则的紧凑提示词（30-55 词），主体先行 + 明确镜头技术 + 音频激活路径（with X audible / speaking English at natural pace）。可选加入"8s 时序节拍"结构。用于"用 HappyHorse 生成视频"、"做个 3-15 秒短片"、"要原生带音频的视频"、"ASMR 视频提示词"等触发场景。
412 GitHub stars~1.1k tokensUpdated today
Auto-check passed
Model Selector
cclank/lanshu-awesome-ai-video-kit
根据用户的视频需求(场景、时长、音频、语言、平台限制、预算、是否需要本地部署/角色一致性等),从 16 个主流 AI 视频模型(12 商业 + 4 开源)中推荐最匹配的 1-3 个,并解释为什么。覆盖商业:Seedance 2.0、HappyHorse 1.0、Kling 3.0、Sora 2、Veo 3.1、Gemini Omni(2026-05 新)、Runway…
412 GitHub stars~1.2k tokensUpdated today
Auto-check passed
Seedance Storyboard
cclank/lanshu-awesome-ai-video-kit
把复杂剧情/故事大纲拆分为 Seedance 2.0 的"镜头1/镜头2/镜头3"多分镜结构。每个分镜按 4 维度组织（运镜 + 主体动作与表情 + 位置/空间变化 + 音频）。用于"帮我把这个故事写成 Seedance 提示词"、"分镜脚本"、"多镜头视频"、"剧情复杂的视频"、"剧本转分镜"等触发场景。
412 GitHub stars~754 tokensUpdated today
Auto-check passed

Works with

Seedance

Questions about Seedance Debugger

What does Seedance Debugger do?

When should I use Seedance Debugger?

Seedance Debugger fits situations like: tasks that involve AI video generation.

How do I install Seedance Debugger in Claude Code?

Run `npx skills add cclank/lanshu-awesome-ai-video-kit --skill seedance-debugger -a claude-code`. Or copy the skill folder (skills/seedance-debugger in cclank/lanshu-awesome-ai-video-kit) into .claude/skills/seedance-debugger in your project. Claude Code loads it when a task matches its description.

How do I install Seedance Debugger in Codex?

Run `npx skills add cclank/lanshu-awesome-ai-video-kit --skill seedance-debugger -a codex`. Or copy the skill folder (skills/seedance-debugger in cclank/lanshu-awesome-ai-video-kit) into .agents/skills/seedance-debugger in your project. Codex loads it when a task matches its description.

Can I use Seedance Debugger 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 cclank/lanshu-awesome-ai-video-kit --skill seedance-debugger -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-debugger, .gemini/skills/seedance-debugger, .github/skills/seedance-debugger and .opencode/skills/seedance-debugger in your project.

What does Seedance Debugger need to run?

SKILL.md names no scripts, command-line tools or credentials: Seedance Debugger is instructions for the agent only.

Does Seedance Debugger access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Seedance Debugger 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. Review the folder before installing.

What licence does Seedance Debugger use?

Seedance Debugger 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 Debugger use?

About 1.5k tokens (SKILL.md is roughly 6k 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 Debugger?

Skills that share tags, products or a category with Seedance Debugger: Seedance (songguoxs/seedance-prompt-skill, 2.9k stars), SN Motion HTML (OpenSenseNova/SenseNova-Skills, 5.7k stars), Seedance Prompt En (dexhunter/seedance2-skill, 4.2k stars) and Seedance Japanese Prompt Examples (Emily2040/seedance-2.0, 7.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Seedance Debugger?

cclank (a GitHub user) maintains it in cclank/lanshu-awesome-ai-video-kit, which has 412 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 7, 2026.

Source: cclank/lanshu-awesome-ai-video-kit 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 Debugger

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

seedance-debugger

何时不用此 skill

12 类问题诊断手册

症状识别 → 跳转

1. 人物 ID 漂移

2. 字幕

3. Logo / 水印

4. 风格漂移

5. 延长跳变

6. 双胞胎

7. 画质劣化

8. 特效不对

9. 参考人物过多

10. 结尾噪音

11. 中文发音

12. 音色不准

工作流程

步骤 1：症状采集

步骤 2：诊断 → 输出

步骤 3：必要时升级建议

实战示例

示例 1：双胞胎（最常踩）

示例 2：风格漂移

示例 3：字幕 + 水印一起出

参考资源

Files

Compare with similar skills

Similar skills

More from cclank/lanshu-awesome-ai-video-kit

Related

Questions about Seedance Debugger