Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add cclank/lanshu-awesome-ai-video-kit --skill seedance-debuggergit clone --depth 1 https://github.com/cclank/lanshu-awesome-ai-video-kitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cclank/lanshu-awesome-ai-video-kit/seedance-debugger)<a href="https://agentmods.dev/skills/cclank/lanshu-awesome-ai-video-kit/seedance-debugger"><img src="https://agentmods.dev/badge/skills/cclank/lanshu-awesome-ai-video-kit/seedance-debugger/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cclank/lanshu-awesome-ai-video-kit/seedance-debugger"><img src="https://agentmods.dev/badge/skills/cclank/lanshu-awesome-ai-video-kit/seedance-debugger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00146 | $0.04086 |
| Opus 5.5 | $0.00058 | $0.01634 |
| Sonnet 5.5 | $0.00029 | $0.00817 |
| Haiku 4.5 | $0.00015 | $0.00409 |
Grade A, and why
seedance-debugger scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 343 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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
- 参考提示词：
- 优先选高清图片作参考
- 控制续写次数，避免多次叠加
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 343 lines · 146 tokens per session scan A bf0d5ed0bbe0
seedance-debugger is a skill published in the GitHub repository cclank/lanshu-awesome-ai-video-kit (431 stars, last pushed 20d ago), licensed MIT. It adds 146 tokens to every session and 4,086 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
tool-calling-tutor
Use when a tool-calling agent does not call a tool, sends wrong arguments, loops without stopping, or needs a function schema. Guides a four-branch diagnosis and five-step schema repair. Do not use for framework-specific, MCP-server, or production-observability questions.
xedit-conflict-audit
Use when auditing conflicts in a Bethesda plugin set — determining for a record (or a plugin's records) which override wins, what the conflict label is, what references it, and whether the configuration is safe or breaking.
diagnosing-bgs-problems
A symptom-first guide for investigating crashes, frame-rate drops, stuttering, freezes, and startup failures in Bethesda Game Studios games with mods.
agent-debug-fixer
A Chinese-language debugging and repair workflow for software problems. It investigates errors, failed tests, broken pages, or behavior that does not match expectations, then makes a minimal fix.
codegraph
A local code-graph query tool for an existing project. It maps symbols and their relationships so you can search for definitions, callers, callees, affected files, and focused context.
error-experience-library
An error knowledge base that stores recurring error patterns, their causes, and the fixes that worked. It can search past entries and track whether each suggested fix succeeded.