Skip to main content
ZICQ

Skills ZICQ category:Agent Workflows huashu-art-motion

Huashu Art Motion

Auxiliary art animation and speech missions: 35 art style formulations, 9 interpretation syntaxes, spectrometry and certainty Canvas mapping tools. By host time axis, material and export use of host capacity。

Official URL:GitHub

What this skill does

Intro in this page language first. The official description stays in its original wording; we do not rewrite SKILL.md.

When to use it

The official description does not include a separate “Use when”. Per the spec, agents activate this skill when the task matches keywords in that description.

How agents load it

Per Agent Skills progressive disclosure: name and description load at startup (~100 tokens); the full SKILL.md body loads when the skill activates; scripts/, references/, and assets/ load only as needed. This file's sections: Open Design 宿主约定; 花叔艺术动画:Open Design 适配; 适用范围与包边界; 工作流程; 按需读取; 素材边界. It includes spec-recommended sections: edge cases.

File analysis

File analysis: besides SKILL.md, the body references references/index.md, references/craft-workflow.md, references/canvas-helpers.md, references/art-styles-1.md, references/art-styles-2.md, references/explainer-grammars.md. Those resources load on demand.

Official description (original)

辅助艺术动画与解说任务:35 种艺术风格配方、9 种解说语法、分镜与确定性 Canvas 绘制工具。按宿主时间轴实现,素材与导出使用宿主能力。

Open Design 宿主约定花叔艺术动画:Open Design 适配适用范围与包边界工作流程按需读取素材边界许可随包保留

· License:MIT

Source category:GitHub skill

SKILL.md & Agent activation

Official spec ↗
name
huashu-art-motion
description
辅助艺术动画与解说任务:35 种艺术风格配方、9 种解说语法、分镜与确定性 Canvas 绘制工具。按宿主时间轴实现,素材与导出使用宿主能力。
License
MIT
  1. DiscoverThe client exposes names and descriptions to the agent.
  2. ActivateYour request or the task context selects the skill and loads its instructions.
  3. Load resourcesReferenced scripts, documentation and assets are used when needed.
Files referenced by the instructions · 7
  • references/index.md
  • references/craft-workflow.md
  • references/canvas-helpers.md
  • references/art-styles-1.md
  • references/art-styles-2.md
  • references/explainer-grammars.md
  • references/license.md

These paths are extracted from the text. Check the upstream package to verify the files exist.

Invocation syntax and available tools depend on your Agent client. Client integration guide ↗

Install this skill

Skills CLI ↗

Choose the target agent and installation scope, keep referenced package files, then verify the skill appears in the client's catalog.

This skill references supporting files. Retrieve the complete directory from the source; copying SKILL.md alone may leave missing dependencies.

Ask your Agent to install

Copy these instructions to a compatible agent and confirm the target directory matches your client.

Install the agent skill "huashu-art-motion" into my project. The full SKILL.md and official description are at https://zicq.com/en/skills/skl-d7bd7119d8dbc4a4-Huashu-Art-Motion.html
Save it as .cursor/skills/huashu-art-motion/SKILL.md or .claude/skills/huashu-art-motion/SKILL.md and keep the frontmatter name and description exactly as-is.
This skill also ships scripts/, references/, or assets/ — fetch the whole folder from https://github.com/nexu-io/open-design/tree/HEAD/skills/huashu-art-motion instead of creating only a SKILL.md.

Full package on GitHub ↗

Install from the terminal · Skills CLI

Requires Node.js and npx. First inspect the repository's skill list to confirm the name.

npx skills add 'https://github.com/nexu-io/open-design/tree/HEAD/skills/huashu-art-motion' --list

npx skills add 'https://github.com/nexu-io/open-design/tree/HEAD/skills/huashu-art-motion' --skill 'huashu-art-motion'

The CLI lets you choose the agent interactively. The default scope is the project; use -g for user scope. Confirm package availability with the discovery command, then use npx skills list to inspect installed skills.

Readable layout

name: huashu-art-motion description: "辅助艺术动画与解说任务:35 种艺术风格配方、9 种解说语法、分镜与确定性 Canvas 绘制工具。按宿主时间轴实现,素材与导出使用宿主能力。" en_name: huashu-art-motion zh_name: "花叔 · 艺术与解说动效" zh_description: "辅助艺术动画与解说任务:35 种艺术风格配方、9 种解说语法、分镜与确定性 Canvas 绘制工具。按宿主时间轴实现,素材与导出使用宿主能力。" triggers:

  • "huashu-art-motion"
  • "动效"
  • "动画"
  • "motion"
  • "huashu"
  • "花叔"
  • "艺术动画"
  • "解说"
  • "canvas"
  • "art motion" license: MIT od: mode: utility category: animation-motion upstream: https://github.com/alchaincyf/huashu-art-motion source-commit: d861767d180008d27675819932070a670a3ae43f

Open Design 宿主约定

这是当前任务中的功能技能。保留用户选定的任务类型、品牌、技术栈、当前阶段和交付格式;不要因为 @ 选择而改成视频项目。规划阶段只规划,实现阶段才写代码。检查、渲染和导出仅在宿主当前阶段允许且工具真实可用时执行;技能不能额外开启独立 Agent、强制审批或绕过宿主交付边界。

附属文件相对当前技能包根目录读取,按当前问题选读,不把全部参考文档粘入提示词。不读取其他 Agent 的全局配置。素材优先用用户已有文件;需要新图片、视频或音频时使用当前宿主实际提供且用户允许的工具。缺少生成、测量或导出能力时说明具体缺口,交付可验证部分,不声称完成未执行的步骤。遵循当前任务的输出路径,不覆盖输入或历史产物。

花叔艺术动画:Open Design 适配

适用范围与包边界

在现有任务中拆解参考动画、选择艺术材料、设计分镜、编排画面内运动,或实现解说中的一个镜头。此包提供完整的 35 张艺术配方、9 张解说语法卡和八个通用 Canvas 工具模块源码;它不安装上游整片渲染器、35 支样片、角色帧、字体、声音克隆或独立凭据系统。选择此技能不意味着 MP4 已可导出。

工作流程

  1. 确定画面事件。 从用户题材、已有素材与接受的 brief 中写清主物、动作、视觉结果、时长、尺寸。参考片拆解看构图、运动和转场机制,不逐像素照抄。要求明确时直接执行,不强制给三个方向或按模型身份分档。
  2. 锁定表现语言。 从 references/index.md 找到最贴合内容的风格或解说语法;读取对应小节。保留用户指定的品牌色与字体,参考卡中的颜色禁忌、角色和样片参数仅作为上下文建议。新题材重新构图,不复用作者人物和示范素材。
  3. 做镜头表。 用 references/craft-workflow.md 的模板记录时间段、画面里的物、动作、镜头、屏上字和实现方式。优先让具体物体解释内容,避免连续标题卡和无意义淡入;艺术画面可以持续呼吸,解说镜头的动作跟随叙述事件。已有口播沿用真实音轨和时间点,不凭空写转录或测量结果。
  4. 一帧先行,再实现运动。 在宿主允许的设计阶段先锁定关键构图。实现时使用现有栈;Canvas 任务可从 references/canvas-helpers.md 取用 U、KIT、PAINT、MO、CAM 函数(brush/render/post 扩展 PAINT)。先加载 U,再加载需要的模块,设置实际舞台尺寸。具体 scenes、参数化 clip renderer 和原项目命令未随包提供,不能照搬调用;根据配方在当前工程实现镜头。
  5. 确定性与适配。 用种子随机;给定时间 t 应得到同一画面,时间由宿主时间轴驱动。支持当前宿主的 seek/replay 约定,处理 resize、资源就绪与减少动态效果偏好。只在需要的局部使用绘画缓存,不把字体或图片未加载的画面当验收帧。
  6. 验证当前阶段允许的结果。 检查开场、关键变形、停留、转场和收尾;可观察播放时再检查连续性、阅读时间和视觉重心。有真实素材时优先让素材当主画面,代码负责运镜与解释。报告实际看过或测过的内容,不能拿参考卡的历史帧率当作当前性能。
  7. 交付。 按宿主输出契约保存可编辑源文件及所需素材;需导出时走宿主已支持的导出路径。没有导出工具就明确说明,不启动上游 deliver/render/语音配置脚本。

按需读取

  • references/index.md:35 风格与 9 语法索引。
  • references/art-styles-1.md:前 18 张完整风格卡。
  • references/art-styles-2.md:其余 17 张完整风格卡。
  • references/explainer-grammars.md:9 张完整语法卡;其中讲解员语法是参考设计,不代表本包有人物生成能力。
  • references/craft-workflow.md:拆解、机制、分镜、一帧先行、代码绘制、配乐与角色精细度。
  • references/canvas-helpers.md:八个可复制的通用 Canvas 模块源码,按依赖顺序排列。

素材边界

不随包分发上游示范人物、角色帧、总览图、第三方字体或笔顺数据。用户要真实人物、产品或截图时,使用用户提供且可用的素材;需新素材时走宿主工具与许可。原文中的作者作品、渲染命令、全局路径、工具名和独立审片要求是来源说明,不能覆盖宿主约定。

许可随包保留

references/license.md 随会话包保留来源许可。复制参考代码到交付工程时保留上游署名及许可文本。

Related skills

Agent Workflows

Skill Creator

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that exte…

Agent Workflows

Clawdhub

Use the ClawdHub CLI to search, install, update, and publish agent skills from clawdhub.com. Use when you need to fetch new skills on the fl…

Agent Workflows

Agent Team Orchestration

Orchestrate multi-agent teams with defined roles, task lifecycles, handoff protocols, and review workflows. Use when: (1) Setting up a team …

Agent Workflows

Superpowers

Spec-first, TDD, subagent-driven software development workflow. Use when: (1) building any new feature or app — triggers brainstorm → plan →…