agentleFS
WhaocaiiWhaocaii/ai-game-skills/skills/build-pseudo-live2d-character/SKILL.md

build-pseudo-live2d-character

Skill4 starsChanged 2 months agoMITView on GitHub

基于单图或图层角色素材制作网页中的呼吸、眨眼和简单动作。用于伪 Live2D 表现;不声称生成 Cubism 模型。 Plan browser character animation from a single illustration: breathing, blinking and layered motion; not a Cubism model generator.

The file

Files
SKILL.md

单图角色动效规划

本模块由 Whaocaii 主导设计与维护,使用 AI 辅助编写。当前版本为 0.1.0 工作草稿。按用户的目标与现有项目约束执行;仅使用实际可用的工具。

输入

  • 原始图片、透明区域或已有图层
  • 目标动作、画面尺寸、设备与可用图片处理工具

工作过程

  1. 先判定可分离部位与遮挡关系。只有扁平图时选择不会露出缺失像素的低幅度动作。
  2. 为每个运动部位定义锚点、可动范围和固定区域;脸部身份、颈肩接缝与衣服连接优先保持稳定。
  3. 呼吸、眨眼和交互动作独立调度;交互结束回到同一基准姿态,避免多层变换累积漂移。
  4. 需要补画或闭眼图时,根据用户授权及可用工具生成或索取素材。缺少素材就明确降级,不用挤压眼睛冒充自然闭眼。
  5. 验证最大位移时遮挡、边缘与透明像素,在目标浏览器测试暂停、恢复和重复点击。

交付

  • 图层与锚点计划、动作时序及降级说明
  • 若要求实现:素材清单、集成代码与实际运行证据

检查

  • 最大动作幅度下没有露底和接缝
  • 停止与恢复后姿态一致,重复触发不会加速或漂移

使用案例

只有一张半身立绘,希望呼吸和轻微转头。判断哪些部位能安全移动,哪些需要补图。

验收时按上面的检查项判断结果;只读完本文件不代表完成了任务。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.