跳到主内容
智客 ZICQ

技能库 智客分类:Agent 工作流 chat-motion-overlay

Chat Motion Overlay

由笔录或截图来生成可配置的聊天动作覆盖,包括平面泡泡场景,应用风格的聊天容器,可选设备帧,预设或上传的相机,外号显示规则,以及透明-视频准备回放捆. 当 Codex 需要为 Douyin 创建可重复使用的短式聊天剪辑,演示视频,故事再现,社交信息证明场景,或为 Hyperframe 和 Remotion 工作流程嵌入可嵌入的 alpha 覆盖.

官方网址:GitHub

技能介绍

先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。

做什么

生成由记录或截图所覆盖的可配置的聊天动作,包括平面泡泡场景、应用风格的聊天容器、可选设备框、预设或上传的相机、昵称显示规则以及透明视频准备的回放捆绑

何时用

Codex 需要为 Douyin 创建可重复使用的短式聊天剪辑, 演示视频, 故事重现, 社会信息证明场景, 或为 Hyperframe 和 Remotion 工作流程创建可嵌入的 alpha 覆盖

代理如何加载

按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:Chat Motion Overlay、Workflow、Supported Dimensions、Output Rules、Question Policy、Resources。 其中含规范建议的小节:分步指令。

文件分析

文件分析:除 SKILL.md 外,正文引用了 references/input-format.md、references/config-schema.md、references/question-strategy.md、scripts/build_chat_overlay_spec.py、scripts/prepare_chat_overlay_bundle.py、references/output-modes.md,属于带资源的技能包,这些文件按需再读。

官方 description(原文)

Generate configurable chat motion overlays from a transcript or screenshot, including plain bubble scenes, app-style chat containers, optional device frames, preset or uploaded avatars, nickname display rules, and transparent-video-ready Remotion bundles. Use when Codex needs to create reusable short-form chat clips for Douyin, demo videos, story reenactments, social-message proof scenes, or embeddable alpha overlays for Hyperframe and Remotion workflows.

Chat Motion OverlayWorkflowSupported DimensionsOutput RulesQuestion PolicyResources

来源分类:GitHub skill

SKILL.md 与 Agent 调用

官方规范 ↗
name
chat-motion-overlay
description
Generate configurable chat motion overlays from a transcript or screenshot, including plain bubble scenes, app-style chat containers, optional device frames, preset or uploaded avatars, nickname display rules, and transparent-video-ready Remotion bundles. Use when Codex needs to create reusable short-form chat clips for Douyin, demo videos, story reenactments, social-message proof scenes, or embeddable alpha overlays for Hyperframe and Remotion workflows.
  1. 发现技能客户端向 Agent 提供名称与描述目录。
  2. 匹配与调用用户指定或任务匹配后,载入 SKILL.md 指令。
  3. 按需加载按步骤读取参考文档、使用脚本与素材。
指令中引用的文件 · 6
  • references/input-format.md
  • references/config-schema.md
  • references/question-strategy.md
  • scripts/build_chat_overlay_spec.py
  • scripts/prepare_chat_overlay_bundle.py
  • references/output-modes.md

以下路径提取自原文;文件是否齐全请以来源仓库中的完整目录为准。

具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗

安装这个技能

Skills CLI ↗

先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。

该技能引用了附属文件,请从来源获取完整目录;仅复制 SKILL.md 可能缺少依赖。

交给 Agent 安装

复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。

把 Agent Skill「chat-motion-overlay」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-5afdd34c87583ff4-%E8%81%8A%E5%A4%A9%E5%8A%A8%E4%BD%9C-%E9%87%8D%E5%8F%A0.html
请存为 .cursor/skills/chat-motion-overlay/SKILL.md 或 .claude/skills/chat-motion-overlay/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。
该技能还带 scripts/、references/、assets/ 等文件,请从 https://github.com/nexu-io/open-design/tree/HEAD/skills/chat-motion-overlay 取完整目录,不要只建一个 SKILL.md。

GitHub 完整包 ↗

终端安装 · Skills CLI

需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。

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

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

CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。

阅读排版

name: chat-motion-overlay description: Generate configurable chat motion overlays from a transcript or screenshot, including plain bubble scenes, app-style chat containers, optional device frames, preset or uploaded avatars, nickname display rules, and transparent-video-ready Remotion bundles. Use when Codex needs to create reusable short-form chat clips for Douyin, demo videos, story reenactments, social-message proof scenes, or embeddable alpha overlays for Hyperframe and Remotion workflows. triggers:

  • "chat motion overlay"
  • "animated chat"
  • "chat bubbles"
  • "message overlay"
  • "transparent chat video"
  • "微信聊天动效"
  • "聊天气泡动效"
  • "透明聊天视频" od: mode: utility category: animation-motion design_system: requires: false

Chat Motion Overlay

Turn chat content into a configurable motion overlay clip instead of a single hard-coded WeChat mock.

Workflow

  1. Normalize the chat input.

    • If the user gives a screenshot, extract the visible messages into the transcript format in references/input-format.md.
    • If the user gives plain text, keep one message per beat and preserve exact wording when authenticity matters.
    • For screenshots, use visible avatars as clues for participant count and message grouping, but do not crop or recreate avatar images by default. Infer participants and sides, then render with preset avatars unless the user provides avatar files or explicitly requests screenshot-derived avatars.
  2. Choose a scene config.

    • Read references/config-schema.md.
    • Decide container style, avatar mode, device frame, nickname mode, and delivery format before generating the bundle.
    • When the user has not provided enough information, follow the question policy in references/question-strategy.md.
  3. Build the scene spec.

    • Run scripts/build_chat_overlay_spec.py with a transcript and optional config JSON.
    • The script outputs a single JSON spec that Remotion can render directly.
  4. Prepare a renderable bundle.

    • Run scripts/prepare_chat_overlay_bundle.py.
    • It copies the Remotion template, injects src/chatSpec.ts, and copies any uploaded avatar files into public/.
  5. Render the target output.

    • Use the exact export commands in references/output-modes.md.
    • Prefer MOV(透明背景,可直接导入剪映 / PR / FCP 叠加) for editing, WebM(透明背景,适合网页 / 浏览器播放) for browsers, and editable engineering outputs when the user wants to keep composing downstream.

Supported Dimensions

  • container: none, wechat, telegram, messenger
  • avatarMode: preset, upload, mixed
  • deviceFrame: none, iphone-dynamic-island
  • nicknameMode: hidden, first-message-only, always
  • deliveryFormat:
    • mov: MOV(透明背景,可直接导入剪映 / PR / FCP 叠加)
    • webm: WebM(透明背景,适合网页 / 浏览器播放)
    • remotion: Remotion 工程(适合继续编辑和拼装)
    • hyperframe: Hyperframe 工程(适合作为模块继续复用)
    • json: JSON 数据(适合程序处理 / 自定义渲染)
    • preview: 预览图 / 预览工程(适合先确认效果)

Output Rules

  • Keep the composition root transparent for overlay outputs.
  • Use container: none for standalone bubble motion without an app shell.
  • Use container: wechat|telegram|messenger when the platform chrome is part of the story.
  • Treat uploaded avatars as content assets and copy them into public/ for the render bundle.
  • Prefer preset avatars when the user does not specify avatar files. Screenshot avatars may help identify participants, but recommend user-provided avatar files before attempting to crop or recreate avatars from screenshots.
  • Keep config-driven behavior explicit; do not silently switch style families.

Question Policy

  • Prefer inference first, questions second.
  • If the user gives enough information for a sensible default, continue and clearly state the assumptions.
  • Ask only for missing high-impact choices.
  • Keep the question set to 1-3 items.
  • Prefer user-facing wording over technical wording.
  • Ask about deliveryFormat using 格式(场景描述) labels, not internal render terms.
  • If the user says they do not care, continue with defaults and note them in the result.

Resources

  • Transcript format: references/input-format.md
  • Config fields and examples: references/config-schema.md
  • Question strategy: references/question-strategy.md
  • Output commands and targets: references/output-modes.md
  • Transcript/config to spec: scripts/build_chat_overlay_spec.py
  • Remotion bundle preparation: scripts/prepare_chat_overlay_bundle.py
  • Remotion render template: assets/remotion-template/

相关技能

Agent 工作流

Skill Creator

创造有效技能指南。 当用户想创造出新的技能(或更新现有的技能),以专业知识,工作流程,或工具集成来扩展克洛德的能力时,应该使用这种技能.

Agent 工作流

Clawdhub

使用ClawdHub CLI搜索,安装,更新并发布从taladhub.com的代理技能. 需要获取苍蝇上的新技能时使用,将安装的技能同步到最新版本或特定版本,或者发布 npm-instainddhub CLI 的新/更新的技能文件夹.

Agent 工作流

Agent Team Orchestration

管弦乐团多代理团队,任务设定周期,交接协议,审查工作流程. 使用时间: (1)建立2+特派员队伍,具有不同专业,(2)确定任务路线和生命周期(收录框_ spec_建设_审查_完成),(3)在特派员之间制定交接协议,(4)建立审查和质量关口,(5)管理特派员之间的交流和文物共享.

Agent 工作流

Superpowers

Spec-first,TDD,子代理驱动的软件开发工作流程. 当:(1)构建任何新功能或应用——触发脑暴_计划_子代理执行回路,(2)调试出一个bug或测试失败——触发系统性的根起过程,(3)用户说"让我们构建","帮助我计划","我想添加X",或"这个被打破",(4)完成一个功…