Communitygithub.com

9018/mychat

当用户需要一段以设计为主导的短片动态图形,其中动态本身即信息:动态文字排版、数字/统计数据跳动计数、图表/数据可视化效果、标志动画、品牌组合、底部三分之一、标注、社交媒体叠加、动画标题/推文/新闻、动态海报或快速捕捉的页面高亮。通常时长在10秒以内,最长约30秒,无旁白、画外音或真人出镜。可输出为MP4或透明叠加视频。

mychat 是什么?

该技能用于生成以设计为主导的短动态图形(Motion Graphics),核心特点是“动态即信息”,时长通常不超过10秒,最长约30秒,无旁白、画外音或真人表演。它支持多种视觉类别,包括动态文字排版(kinetic-type)、数字跳动/统计动画(stat)、图表/数据可视化(charts)、标志揭示(logo-reveal)、底部三分之一/标注/社交媒体叠加(lower-thirds)等用户提供内容的“表单类别”,以及需要搜索驱动的“网页动画(webpage)、新闻头条(news)、推文卡片(tweet)、图片/实体融合(asset-fusion)”等类别。技能通过一系列明确步骤执行:初始化项目、规划(判断是否需要搜索并选择类别)、资源获取(搜索/生成/获取素材)、设计(基于已有资产设计分镜)、构建(优先复用组件)、渲染(输出MP4或透明格式)和验证。它适用于需要快速、动态、视觉突出的内容场景,如社交媒体视频、数据动效、品牌标识动画等,但不适用于长篇、多场景、带旁白的视频。

兼容平台~Claude Code~Codex CLI✓Cursor✓Gemini CLI
npx skills add https://github.com/9018/mychat/tree/HEAD/OpenMontage/.agents/skills/motion-graphics

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

动态图形 — 调度入口

在步骤0之前确认路由。 此技能用于制作短篇、以设计为主导、无旁白的动态图形(动态即信息;通常10秒以内,无画外音)。较长、多场景或带旁白的视频 → /general-video;网站旁白视频 → /website-to-video;话题讲解 → /faceless-explainer;产品推广 → /product-launch-video;为现有素材添加字幕 → /embedded-captions。超出范围:渲染时的实时数据,或无法捕捉的素材。不确定是动态优先还是旁白优先?先阅读 /hyperframes。

一段以设计为主导的短动态图形。资产优先:在设计分镜之前确定资产策略并获取真实素材,然后根据已有的素材设计分镜,最后通过重用量产目录中的能力进行合成。所有产物都放在 PROJECT_DIR = videos/<project-name>/ 下(在步骤0创建);以下所有路径都相对于该目录。

阶段执行方式主要产物详细流程
initBashhyperframes.json步骤0
plan子代理 — 决定是否需要搜索? + 分类 + 资产策略shot-plan.json(草稿:类别、asset_needs查询、简要说明)agents/director.md(第一部分)
source ◇Bash — 媒体使用解析(如果 asset_needs 为空则跳过)assets/ + assets/index.mdphases/source/guide.md
design子代理 — 根据已解析的资产设计分镜shot-plan.json(最终版:分镜块 + 布局 + 动态 + 位置)agents/director.md(第二部分)
build子代理 — 优先重用的合成方法compositions/index.htmlagents/builder.md
renderBash — hyperframes render(MP4,或 --format webm/mov 用于叠加)renders/video.mp4步骤5
verifyBash — lint / inspect -> 失败时调用修复子代理(就地修复)agents/finalize.md

◇ source 仅在所选类别声明需要资源时运行。纯代码/文字类别(如 kinetic-type、大多数 charts/stat)的 asset_needs: [] 为空,直接从计划阶段跳到设计阶段。

类别 — 根据搜索决策划分

plan 的第一个决策是:是否需要搜索? 该分支将类别分为两组;然后选择具体类别 — 对于搜索驱动型,根据搜索返回的内容类型决定。每个类别对应一个 categories/<id>/module.md(其规划 + 构建规则);共享的动态词汇表位于 references/motion-vocabulary.md(→ hyperframes-animation 规则/蓝图 + 注册表块)。

表单类别 — 无需搜索;用户提供内容:

类别意图依赖
kinetic-type醒目标语/引用/标题,动态优先的文字caption-* 块 + 动画规则
stat单个主数字/跳动计费 + 环形图形apple-money-count / rules/{counting-dynamic-scale, stat-bars-and-fills}
charts基于数据的条形/折线/饼图/竞赛/百分比data-chart 块
logo-reveal标志揭示/品牌组合(用户提供标志)logo-outro / rules/svg-path-draw
lower-thirds姓名/标题栏、标注、社交媒体叠加caption-* + 注册表叠加块

搜索驱动类别 — 先搜索,然后根据内容类型动画化(RWA 路径):

返回内容类别动画
网页/链接webpage网页/UI 动画(滚动、揭示、光标、标注)
新闻文章news标题揭示 + 来源卡片 + 关键事实标注
推文tweet动画推文卡片
图片/实体asset-fusion资产的几何形状 变成 图表(RWA 故事内融合)

构建顺序:一次一个,覆盖优先(粗糙也可以)。kinetic-type 从原型移植而来;其余类别遵循此规则。

前置条件

macOS Apple Silicon 或 Linux x64。系统工具:brew install node ffmpeg。运行 npx hyperframes doctor 一次。macOS GPU 渲染:export PRODUCER_BROWSER_GPU_MODE=hardware。

可选密钥(未设置时使用本地回退)— 仅被那些通过媒体使用生成/获取资源的类别需要:

密钥用途回退
GEMINI_API_KEY / GOOGLE_API_KEY图片生成(媒体使用解析)跳过生成 / 仅搜索
(asset_scout / 搜索提供商)webpage/news/tweet + asset-fusion 真实资产搜索类别降级为无资产版

流程

步骤0 — 初始化

当前工作目录是代理工作空间根目录;所有产物写入 PROJECT_DIR = videos/<project-name>/。<project-name>:使用用户提供的目录名,否则从意图中取一个短的 kebab-case 名称(<subject>-motion)。不要使用工作空间基名或时间戳。

仅当 $PROJECT_DIR/hyperframes.json 不存在时:

PROJECT_DIR="${MOTION_GRAPHICS_DIR:-videos/<project-name>}"
mkdir -p "$(dirname "$PROJECT_DIR")"
npx hyperframes init "$PROJECT_DIR" --non-interactive --example=blank

init 检查已安装的技能与 GitHub 上最新版本,并更新全局集合(如有过时)。

限制: 永远不要在 workspace 根目录运行 hyperframes init;永远不要将另一个 hyperframes/ 嵌套在 PROJECT_DIR 内;每个 Bash 命令(主代理 + 子代理)都是 (cd "$PROJECT_DIR" && ...) 子shell — 永远不要裸 cd。

步骤1 — 规划(子代理:导演第一部分)

分发一个子代理。提示词 = 完整的 agents/director.md + ## 分发上下文(SKILL_DIR / PROJECT_DIR / 用户请求 / Schema: <SKILL_DIR>/references/shot-plan-ir.md)。它必须:

  1. 决定:是否需要搜索?(第一个分支)
    • 否 → 选择一个表单类别(kinetic-type / stat / charts / logo-reveal / lower-thirds);内容由用户提供;asset_needs: []。
    • 是 → 将搜索计划写入 asset_needs[](新闻 / 网页 / 推文 / 图片;两极查询)。具体的搜索驱动类别(webpage / news / tweet / asset-fusion)由步骤2返回的内容类型确认,并在步骤3中最终确定。
  2. 编写草稿 shot-plan.json(信封 + 选择的表单类别 或 搜索意图 + asset_needs + 一段分镜简介)。架构:references/shot-plan-ir.md。

验证:[ -s "$PROJECT_DIR/shot-plan.json" ] && echo ok || echo missing。

步骤2 — 资源获取(Bash:媒体使用,条件执行)

如果 shot-plan.json.asset_needs 非空,则解析资源(搜索 / 生成 / 获取 → 冻结的项目本地路径 + 台账)。参见 phases/source/guide.md(封装 media-use resolve;搜索驱动类别使用新闻/网页/推文/图片搜索)。如果 asset_needs 为空,则跳过到步骤3。

# 示例 — 参见 phases/source/guide.md
(cd "$PROJECT_DIR" && node <SKILL_DIR>/phases/source/resolve.mjs --plan ./shot-plan.json --out ./assets)

优雅降级:如果搜索/提供商不可用,类别回退到无资产版(在 context.log 中注明)。

步骤3 — 设计(子代理:导演第二部分)

分发一个子代理(提示词 = agents/director.md 第二部分 + 分发上下文,包括已解析的 assets/index.md(如果步骤2运行了)+ catalog-map.md)。它根据可用资源设计分镜:选择目录块 + hyperframes-animation 规则/蓝图、布局、动态、节拍,以及(对于 asset-fusion)element_positions + 吸色器调色板。最终确定 shot-plan.json(content.block + content.customize + 每个类别的内容)。

步骤4 — 构建(子代理:构建器,优先重用)

分发一个子代理。提示词 = 完整的 agents/builder.md + 分发上下文(shot-plan.json、catalog-map.md、类别的 module.md、references/motion-vocabulary.md、references/builder-contract.md)。优先重用:npx hyperframes add <block> + 就地自定义;仅手动编写缺口 + asset-fusion 支持入口。输出符合 HF 契约的 compositions/index.html(暂停的 GSAP 时间线在 window.__timelines上、class="clip" + 稳定的 id、tl.seek(0)、确定性)。

步骤5 — 渲染(Bash)

(cd "$PROJECT_DIR" && npx hyperframes render . --skill=motion-graphics -q draft -o ./renders/video.mp4)
# 透明叠加变体:--format webm(或 mov)

步骤6 — 验证(Bash → 失败时调用修复子代理)

(cd "$PROJECT_DIR" && npx hyperframes lint . && npx hyperframes inspect .)

exit 0 → 完成。如果 lint/inspect 出现错误,则分发修复子代理(agents/finalize.md:快照质量检查 + 一轮就地修复 + 重新渲染)。修复过程中永远不要改变固定时长。

报告 + 可选预览

报告最终输出(renders/video.mp4,或 .webm / .mov 叠加变体)+ 时长。运行期间不要打开预览。 仅在请求时提供,并在渲染之后启动,以提供最终文件:

(cd "$PROJECT_DIR" && npx hyperframes preview)   # Studio UI;或 `npx hyperframes play` 获取可分享链接

标志位于 hyperframes-cli 技能中(references/preview-render.md)。

恢复表

状态从中继续
没有 shot-plan.json步骤1(规划)
shot-plan.json 有 asset_needs,但没有 assets/步骤2(资源获取)
shot-plan.json 最终版,没有 compositions/index.html步骤3/4(设计+构建)
compositions/index.html 存在,没有 renders/video.mp4步骤5(渲染)+ 步骤6
renders/video.mp4 存在报告 + 停止

设计说明(维护者 — 执行时不读取此项)

  • 资产优先的理由: 资源获取前置,并指导分镜设计(RWA 流程:分析 → 搜索 → 审查 → 合成)。搜索驱动类别(webpage/news/tweet)和 asset-fusion 都依赖媒体使用的搜索(新闻/网页/推文/图片),这是媒体使用有文档记录的 RWA 路线。
  • 优先重用: 生态系统中类似 LLM 生成模板的方式是“组合目录块 + hyperframes-animation 规则”。HF 的暂停 GSAP 时间线 ≙ Remotion 的 useCurrentFrame。
  • 类别模块契约: 一个 categories/<id>/module.md(规划 + 构建),共享 references/motion-vocabulary.md(+ 可选评估)。添加类别 = 添加文件夹 + 在 agents/director.md 中注册其分类器行 + 在 catalog-map.md 中添加其行;阶段管道保持不变。
  • 目录结构:
    videos/<project-name>/
      hyperframes.json  context.log
      shot-plan.json            # IR(导演输出)
      assets/  assets/index.md  # 媒体使用输出(如果获取了资源)
      compositions/index.html   # 构建器输出
      renders/video.mp4
    
  • 注册: 在 hyperframes 路由器中 — 添加“以设计为主导的短动态图形”意图 + 工作流描述;从 /general-video 中划出动态图形触发器;添加反向“禁止使用”边。参见 motion-graphics-genre.md §5-7。

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

9018/mychat

Generate AI videos from text prompts using multiple provider gateways. Use when: (1) Generating videos from text descriptions, (2) Creating AI-generated video clips for content production, (3) Image-to-video generation with a reference image, (4) Choosing between video generation providers (VEO, Kling, Sora, Runway, Seedance, MiniMax, Gemini Omni). Supports gateways: HeyGen API, fal.ai API, Kling official direct API, and the Gemini API (Gemini Omni Flash).

9018/mychat

Create AI avatar videos with precise control over avatars, voices, scripts, scenes, and backgrounds using HeyGen's v2 API. Use when: (1) Choosing a specific avatar and voice for a video, (2) Writing exact scripts for an avatar to speak, (3) Building multi-scene videos with different backgrounds per scene, (4) Creating transparent WebM videos for compositing, (5) Using talking photos as video presenters, (6) Integrating HeyGen avatars with Remotion, (7) Batch video generation with exact specs, (8) Brand-consistent production videos with precise control.

9018/mychat

Use p5.js/canvas for local procedural character effects: particles, weather, squash/stretch, walk cycles, and environmental motion.

9018/mychat

Review local character animation with schema checks, Playwright browser previews, frame sampling, and FFmpeg/ffprobe final output checks.

9018/mychat

Create videos from a text prompt using HeyGen's Video Agent. Use when: (1) Creating a video from a description or idea, (2) Generating explainer, demo, or marketing videos from a prompt, (3) Making a video without specifying exact avatars, voices, or scenes, (4) Quick video prototyping or drafts, (5) One-shot prompt-to-video generation, (6) User says "make me a video" or "create a video about X".

9018/mychat

Generate Mandarin and multilingual narration with Volcengine Doubao Speech 2.0. Use when creating Chinese voiceovers, when the user prefers Doubao/Volcengine/火山引擎/豆包 TTS, or when narration needs character-level timestamp metadata for subtitles.

9018/mychat

Video and audio processing with FFmpeg. Use for format conversion, resizing, compression, audio extraction, and preparing assets for Remotion. Triggers include converting GIF to MP4, resizing video, extracting audio, compressing files, or any media transformation task.

9018/mychat

Use when implementing Disney's 12 animation principles with Framer Motion in React applications

9018/mychat

All animation knowledge for HyperFrames — atomic motion rules, multi-phase scene blueprints, scene transitions, broader motion-design techniques, AND the seven runtime adapters (GSAP default, plus Lottie, Three.js, Anime.js, CSS keyframes, Web Animations API, TypeGPU). Use for any motion or animation task: pick 2-4 rules and compose, or load a blueprint, or look up runtime-specific API (e.g. GSAP eases / Lottie player / Three.js mixer). HyperFrames-native: single paused timeline, seek-safe, deterministic.

9018/mychat

HyperFrames CLI dev loop. Use when running npx hyperframes init, add, catalog, capture, lint, validate, inspect, layout, snapshot, preview, play, render, publish, lambda, doctor, browser, info, upgrade, skills, compositions, docs, benchmark, telemetry, transcribe, tts, or remove-background, or when troubleshooting the HyperFrames build/render environment. Entry point for AWS Lambda cloud rendering (`hyperframes lambda deploy / render / progress / destroy / policies`).

9018/mychat

The HyperFrames composition contract — build one renderable project. Use for composition structure, the `data-*` timing attributes, `class="clip"`, tracks, sub-compositions, variables, framework-owned media playback, deterministic-render rules, and validation. Read before writing composition HTML.

9018/mychat

Non-animation creative direction for HyperFrames videos. Use for design spec (frame.md / design.md) handling, palettes, typography, narration, beat planning, audio-reactive visuals, composition patterns, and brand / style decisions. For atomic motion patterns and scene blueprints, use `hyperframes-animation`.

9018/mychat

Audio and media assets for HyperFrames compositions, produced by one shared audio engine (`scripts/audio.mjs`) — multi-provider TTS (HeyGen / ElevenLabs / Kokoro local), background music + sound effects (HeyGen audio-library retrieval by default, with local Lyria / MusicGen BGM generation and a bundled SFX library as the no-credential fallback), Whisper transcription, background removal, and caption authoring. Use for voiceover / TTS, BGM, SFX / sound effects, transcription, captions / subtitles / lyrics / karaoke / per-word styling, voice + provider selection, and music-mood prompting.

9018/mychat

Install and wire registry blocks and components into HyperFrames compositions. Use when running hyperframes add, installing a block or component, wiring an installed item into index.html, or working with hyperframes.json. Covers the add command, install locations, block sub-composition wiring, component snippet merging, registry discovery, and authoring a new block or component to contribute upstream (idea → scaffold → validate → PR).

9018/mychat

Use when the user has a music track (an audio file, or a video to pull audio from) and wants a beat-synced HyperFrames video, calm to hard-hitting. The music drives everything: one analyzer reads it once, the orchestrator lays out the frames and fills a per-frame plan, and one sub-agent builds each frame. Typography and templates are the floor — a complete video needs zero assets — but any images or videos the user supplies are cut into the frames on the same beat grid (beat-cut / ken-burns). The genre (lyric video, slideshow, kinetic promo) falls out of the per-frame choices; the pipeline never branches on it.

9018/mychat

Toolkit-specific Remotion patterns — custom transitions, shared components, and project conventions. For core Remotion framework knowledge (hooks, animations, rendering, etc.), see the `remotion-official` skill.

9018/mychat

Port an existing Remotion (React) composition to HyperFrames HTML. Use ONLY when the user explicitly asks to port/convert/migrate/translate a Remotion source. Do NOT use: (a) authoring a new HyperFrames composition; (b) Remotion mentioned in passing; (c) Remotion code shared as reference only; (d) "same video as my Remotion one" without explicit migrate request — treat as fresh build. Doubt → `/general-video`. One-way, Remotion-only: no reverse export (HyperFrames→Remotion or any framework), no non-Remotion source (After Effects, Framer Motion, plain React/CSS) → out of scope, re-create via `/general-video`. Flags unsupported patterns (useState, useEffect, async calculateMetadata, third-party React libs, `@remotion/lambda`) and recommends runtime interop over lossy translation. Unsure whether to port vs. build fresh, or only a passing Remotion mention? → /hyperframes.

9018/mychat

Animate SVG character rigs with GSAP, CSS transforms, Remotion frame control, and HyperFrames-compatible browser previews.

9018/mychat

Three.js animation - keyframe animation, skeletal animation, morph targets, animation mixing. Use when animating objects, playing GLTF animations, creating procedural motion, or blending animations.

9018/mychat

Download video and audio from YouTube and 1000+ sites using yt-dlp. No API keys needed. Use when: (1) Downloading a video from YouTube or other sites, (2) Extracting audio from a video URL, (3) Downloading subtitles/captions from a video, (4) Getting video metadata without downloading.

相关技能