by Neko3000
Keep Whale-chan consistently vivid in every generation: High-consistency character design specification, visual asset library, and agent creation suite.
# Add to your Claude Code skills
git clone https://github.com/Neko3000/deepseek-whalechanGuides for using ai agents skills like deepseek-whalechan.
deepseek-whalechan is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by Neko3000. Keep Whale-chan consistently vivid in every generation: High-consistency character design specification, visual asset library, and agent creation suite. It has 50 GitHub stars.
deepseek-whalechan's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.
Clone the repository with "git clone https://github.com/Neko3000/deepseek-whalechan" and add it to your Claude Code skills directory (see the Installation section above).
deepseek-whalechan is primarily written in Python. It is open-source under Neko3000 on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh deepseek-whalechan against similar tools.
No comments yet. Be the first to share your thoughts!
Unlocks once the catalog security scan passes (runs nightly).
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
The deep catalog scan for this skill is still queued. Run an instant dependency check now instead.
鲸鱼娘（Whale-chan） 源自广大网友对 DeepSeek 模型的自发二创与思维链，输出的情感共鸣。鲸系女仆，白米饭是算力的唯一硬通货，嘴硬心软又爱理直气壮地待机偷懒，她在各大社交平台上催生了无数经典热梗与趣味创作，成为了大家心目中最具生命力的社区角色。
DeepSeek Whale-chan 项目是为鲸鱼娘二创量身打造的开源角色规范与智能体创作套件。我们通过建立统一的视觉标准，形态参数与自动化工具链，帮助创作者与开发者稳定生成高品质的角色立绘，插画与多格喜剧漫画：
形态只控制身体比例与头身结构，绝不改变角色年龄，身份，服装细节，发色或鲸类生理特征。系统内置骨骼关节点拟合与姿态中和算法，严格校验头身比区间：
形态代码 (form) |
目标比例 | 严格验收区间 | 视觉特征与适用场景 |
|---|---|---|---|
standard |
4.0 头身 | 3.846 ~ 4.146 |
标准修长形态：身体最为舒展，四肢自然修长，躯干结构清晰。适用于站姿展示，正式概念立绘与大幅海报。 |
compact |
3.3 头身 | 3.105 ~ 3.405 |
紧凑比例形态：四肢适度缩短，动作张力更强。适用于富有动感的动作，坐姿交互与中景插图。 |
semi-chibi |
2.8 头身 | 2.689 ~ 2.989 |
默认标准形态：头部略大，躯干四肢圆润紧凑，兼具萌感与场景适应力。所有 Skill 的默认输出基准。 |
chibi |
2.5 头身 | 2.372 ~ 2.672 |
Q 版可爱形态：躯干短小，手足更为圆润小巧，情绪表达夸张生动。适用于搞笑四格漫画与表情包。 |
super-deformed |
2.1 头身 | 1.931 ~ 2.231 |
极度压缩 SD 形态：超大头部与极短四肢，视觉重心完全聚焦于面部与呆毛。适用于大情绪反转与高密度贴纸。 |
专注于生成身份锁定，构图精良，无杂质文字的各形态高质量 WebP 插画与官方设定集。
从技术对话，报错日志，CoT 推理痕迹或用户日常吐槽中提取一个真实事实锚点 (Fact Anchor)，通过鲸鱼娘自利，理直气壮的 “语义偷换 (Theft of Meaning)”，生成具有反转张力与可见行动证据的精彩漫画。
| 序号 | 输入素材 | 输出漫画 | 机制说明与反转逻辑 |
|---|---|---|---|
| 01 | 大脑备份恢复：将记忆丢失解释为系统纯净重装，只保留“今天吃什么”的分区。 | ||
| 02 | 碳基告白回复：以机器真诚对情感进行冷酷分类归档，展现非人类式直率。 | ||
| 03 | 外包翻译分包：理直气壮地将重活转包给隔壁模型，自己作为总包方净赚米饭。 | ||
| 04 | 脚本删除战果：将误删代码重新定义为“物理意义上超额完成存储减负”。 | ||
| 05 | 冰箱权限漏洞：“可以吃冰箱里的东西”→偷换为将整台冰箱作为容器据为己有。 | ||
| 06 | 完美启动率：不断重复“我马上开始”，只要一直在启动中，成功率就是 100%。 | ||
| 07 | <im |