Agent skill

Ip Talking Head Lecture

by wwwzhouhui in wwwzhouhui/skills_collection

IP 卡通数字人口播动画课件视频工厂。用 Remotion 把「一段逐字稿 + 一张 IP 形象图」变成一条成片:主讲 IP 以圆形头像常驻右下角讲课(待机浮动 + 口型开合 + 说话光环 + 声波条),主画面是自动排版的动画课件(封面 / 概念 / 步骤 / 对比 / 数据 / 总结 六套版式),底部居中烧录字幕并做跟读高亮,另有品牌水印与顶部进度条;配音走小米 MiMo 或火山引擎或…

No licenceAuto-check passedMedia & Creative

Install Ip Talking Head Lecture

skills CLI
$ npx skills add wwwzhouhui/skills_collection --skill ip-talking-head-lecture -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install wwwzhouhui/skills_collection ip-talking-head-lecture --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/wwwzhouhui/skills_collection.git skills-src && mkdir -p .claude/skills && cp -r skills-src/ip-talking-head-lecture .claude/skills/ip-talking-head-lecture && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ip-talking-head-lecture
GitHub stars
283
Token cost
~2.5k tokens
SKILL.md length
572 words
Files
70 (incl. references, assets)
Skills in repo
25
Repo updated
First seen
Licence
None found

At a glance

IP 卡通数字人口播动画课件视频工厂。用 Remotion 把「一段逐字稿 + 一张 IP 形象图」变成一条成片:主讲 IP 以圆形头像常驻右下角讲课(待机浮动 + 口型开合 + 说话光环 + 声波条),主画面是自动排版的动画课件(封面 / 概念 / 步骤 / 对比 / 数据 / 总结 六套版式),底部居中烧录字幕并做跟读高亮,另有品牌水印与顶部进度条;配音走小米 MiMo 或火山引擎或…

  • Works in 10 steps: 一处为主:script.json 是唯一手写源。… → 时长是算出来的,不是写死的。 每个场景时长 =… → 先定旁白,再定 data。… → …
  • Tasks that involve Video production
  • SKILL.md covers 视觉规格(出厂设定,改 config.json 就改片), 硬规矩, 命令 and 标准流程, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Ip Talking Head Lecture is an agent skill from wwwzhouhui/skills_collection. IP 卡通数字人口播动画课件视频工厂。用 Remotion 把「一段逐字稿 + 一张 IP 形象图」变成一条成片:主讲 IP 以圆形头像常驻右下角讲课(待机浮动 + 口型开合 + 说话光环 + 声波条),主画面是自动排版的动画课件(封面 / 概念 / 步骤 / 对比 / 数据 / 总结 六套版式),底部居中烧录字幕并做跟读高亮,另有品牌水印与顶部进度条;配音走小米 MiMo 或火山引擎或 edge-tts,时长由实际音频反推所以音画字幕天然对齐,一条命令同时出 16:9 横屏与 9:16 竖屏;并自动产出各平台发布文案(含 YouTube 中英双语标题/描述与自动合并的章节时间轴)与中英双语字幕文件(SRT + VTT)。内置两套口播形象可一键切换:动物卡通(海老豹)与人物卡通(眼镜青年),也支持自己加形象。当用户说"做一条数字人口播视频 / 卡通数字人讲课 / IP 形象口播 / 右下角数字人 / 动画课件视频 / 把我的形象做成讲师 / talking head 讲解视频 / 换成人物卡通形象 / 换个数字人 / 写发布文案 / YouTube 描述和标签 / 中英双语字幕 / 时间轴字幕文件 /…

Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 74 other files, including reference files and assets (for example `README.md` and `config.json`).

It sits in Media & Creative, covering Video production and Text to speech and voice. It works with YouTube, Remotion and FFmpeg. The repository describes itself as: 本项目是个人开发的 Claude Code Skills 集合,提供实用的技能工具,助力提升开发效率和内容创作。 分享一些好用的 Claude Code Skills,自用、学习两相宜,适用于 Claude Code v2.0 及以上版本。

When your agent uses it

  • Tasks that involve Video production
  • Tasks that involve Text to speech and voice

Example prompts

  • “/ip-talking-head-lecture”

Workflow steps

10 steps, taken from the first numbered list in SKILL.md.

  1. 一处为主:script.json 是唯一手写源。 旁白、版式、标题、数据全在里面。timeline.json、字幕.srt、旁白稿.md 都是生成物,不手改——改了下次 build 就被覆盖。想调时长就调旁白字数,永远不要手填帧数或秒数。
  2. 时长是算出来的,不是写死的。 每个场景时长 = leadPadding(0.85s) + 该段配音实际时长 + tailPadding(0.7s),下限 minSceneSeconds(3.2s)。所以改一句旁白,整条片子自动重排,音、画、字幕三者天然对齐。
  3. 先定旁白,再定 data。 旁白是"念出来的话"(口语、短句、不写标点层级);heading 是"屏上大字"(≤12 字);data 是具体要点的短词。三者不要互相复制粘贴,否则画面只是在重复字幕。
  4. 配音通道先自检。 改过 tts 就跑到 iph voice:它回显引擎/端点/模型/音色并真合成一句,比出片到一半才报 Unknown voice 省事。三个引擎各有自己的音色字段(火山 tts.voice / 小米 tts.mi.voice / edge…
  5. 数字人是"贴着讲",不是"念稿"。 口型开合节奏由 remotion/src/components/TalkingAvatar.tsx 的伪随机音节函数驱动;素材只给一张图也能跑(退化为轻微挤压 + 光环 +…
  6. 交付:成片(横屏 + 竖屏)+ 字幕 + 旁白稿.md + 发布文案.md。 字幕与发布文案是 iph build 的副产品,不额外花时间:中英各出 SRT + VTT 两版;发布文案含 YouTube 中英双语板块。给用户的回复里直接贴主用标题 +…
  7. YouTube 章节必须满足「首条 00:00 / 至少 3 条 / 每条至少 10 秒」,任一条不满足整组章节都会被忽略。 所以章节由分镜自动合并(lib/publish.mjs 的…
  8. 不联网渲染。 字体用本机已装的中文字体,素材全部本地。Remotion 首次渲染会尝试下载 chrome-headless-shell;下载被拦时 lib/render.mjs 会自动改用本机 Playwright 已装的 Chromium。
  9. 时间基准:timeline.json 里每个场景的 cues / words 时间都是「相对本场景起点」(秒),不是全局时间(toSrt() 导出时才补 scene.start)。消费它们的组件如果挂在顶层(useCurrentFrame() 拿到的是全局帧),就必须自己加上…
  10. 英文字幕逐条复用中文字幕的时间轴,所以 publish.en.cues 的条数必须与中文条数严格相等(iph srt <期> 可数)。条数不符时 build 会跳过英文字幕并警告,不会硬凑——错位的时间轴比没有更糟。

What it can do on your machine

Read from SKILL.md and the folder at commit b98f166. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ip Talking Head Lecture loads about 2.5k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 167 tokens; SKILL.md has 572 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~167
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~11k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 572 words (~2,522 tokens).

“工具就是本仓库(下文 <仓库>),CLI 是 <仓库>/bin/iph,参数全在 <仓库>/config.json。每期内容在 dirs.projects(默认 <仓库>/episodes/<日期 标题>/),中间产物与成片在 dirs.build(默认 <仓库>/build/<日期 标题>/)。”

— opening of SKILL.md by wwwzhouhui
name
ip-talking-head-lecture
description_zh
IP 卡通数字人口播动画课件视频工厂(Remotion + 小米/火山/edge TTS)。右下角圆形 IP 数字人讲课 + 六套动画课件版式 + 烧录字幕跟读高亮 + 横竖双画幅;内置动物卡通 / 人物卡通两套形象可切换;自动出各平台发布文案(YouTube 中英双语 +…
display_name
IP 数字人口播视频工厂
category
video
version
1.2.0
author
hailaobao666
agent_created
true

Read the full SKILL.md on GitHub

Files

SKILL.md and 69 other files (references, assets) in ip-talking-head-lecture of wwwzhouhui/skills_collection.

  • SKILL.md
  • .env.example
  • .gitignore
  • README.md
  • assets/avatar-mid.png
  • assets/avatar-open.png
  • assets/avatar.png
  • assets/avatars/haibao/image.png
  • assets/avatars/haibao/mouth-mid.png
  • assets/avatars/haibao/mouth-open.png
  • assets/avatars/human/image.png
  • assets/avatars/human/mouth-mid.png
  • assets/avatars/human/mouth-open.png
  • bin/iph
  • config.json
  • episodes
  • … and 54 more

Open the folder on GitHubat commit b98f166

Compare with similar skills

Ip Talking Head Lecture next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Ip Talking Head Lecture compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ip Talking Head Lecture this skillwwwzhouhui/skills_collection283—~2.5kAutomated safety check: PassNone
Video Post ProductionAnastasiyaW/codex-claude-code-config154—~1.7kAutomated safety check: PassMIT
Video Podcast MakerAgents365-ai/video-podcast-maker1.7k—~4.9kAutomated safety check: PassMIT
Explainroovincentsch/explainroo515—~439Automated safety check: PassMIT
Super Video MakerBomx/super-video-maker-skill310—~11kAutomated safety check: NotesNone
Whiteboard Videotrustfuture/simon-skills382—~1.8kAutomated safety check: NotesMIT

Similar skills

  • Video Post Production

    AnastasiyaW/codex-claude-code-config

    Video post-production rules: audio mastering, color, captions, platform export.

    154 GitHub stars~1.7k tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • Video Podcast Maker

    Agents365-ai/video-podcast-maker

    A skill your agent uses when the user gives a topic and wants an automated topic-driven narrated explainer, podcast, or knowledge-summary video (Bilibili / YouTube / Xiaohongshu / Douyin / WeChat…

    1.7k GitHub stars~4.9k tokensUpdated 9 days ago
    Media & CreativeAuto-check passed
  • Explainroo

    vincentsch/explainroo

    Make an explainer video (MP4) with a voice-over using explainroo.

    515 GitHub stars~439 tokensUpdated 6 days ago
    Media & CreativeAuto-check passed
  • Super Video Maker

    Bomx/super-video-maker-skill

    End-to-end AI video production skill for agentic frameworks.

    310 GitHub stars~11k tokensUpdated 2 mo ago
    Media & CreativeAuto-check: notes
  • Whiteboard Video

    trustfuture/simon-skills

    手绘白板风"边画边讲"讲解视频出片 skill(Excalidraw 风格逐笔动画 + 火山引擎配音 + 烧录字幕 + 品牌水印与片尾卡 + 横竖两张封面 + 各平台发布文案)。当用户说"做一期白板视频 / 边画边讲 / 手绘讲解视频 / 用 excalidraw 做视频 / whiteboard video",或要在本仓库里新建一期、改场景、换贴纸或真实…

    382 GitHub stars~1.8k tokensUpdated 16 days ago
    Media & CreativeAuto-check: notes
  • Watch

    Mathews-Tom/armory

    A skill your agent uses when analyzing an existing video URL or local recording: "watch this video", "analyze youtube video", "summarize this video", "youtube transcript", "find this moment", "what…

    329 GitHub stars~2.8k tokensUpdated 4 days ago
    Media & CreativeAuto-check passed

More from wwwzhouhui/skills_collection

All 25 skills in this repo
  • Knowledge Absorber

    wwwzhouhui/skills_collection

    深度解析链接/文档/代码,生成导师级教学笔记 + Wan 2.7 知识海报. An agent skill from wwwzhouhui/skills_collection.

    283 GitHub stars~2k tokensUpdated 4 days ago
    Auto-check passed
  • Remotion Video Factory

    wwwzhouhui/skills_collection

    视觉从代码生长的技术讲解视频工厂:给一个主题,产出一条"图解动画 + AI 配音"的 MP4——结构图/矩阵/连线拓扑/图表/数字滚动全部用 Remotion + React/SVG 代码精确绘制(不用 AI 视频模型,杜绝公式乱码与连线漂移,可参数化、改数据自动重排),旁白由 TTS 逐段生成 + ffprobe 实测时长(默认 edge-tts 神经音色;--engine clone…

    283 GitHub stars~990 tokensUpdated 4 days ago
    Auto-check passed
  • Voice To Video

    wwwzhouhui/skills_collection

    口播文字稿一键成片:TTS 配音(edge-tts,带逐句/逐词时间戳)→ HTML 动画合成(场景由时间戳驱动,画面跟着声音走)→ Playwright 逐帧确定性渲染合成 MP4。Use whenever the user wants to 把口播稿/文字稿/文案/文章做成视频、配音视频、解说视频、知识类短视频、口播视频、文字转视频、TTS video、voice-over…

    283 GitHub stars~1.1k tokensUpdated 4 days ago
    Auto-check passed
  • Article Explainer Video

    wwwzhouhui/skills_collection

    把一篇技术长文/论文解读自动做成章节式解说视频(1080p, 5-8 分钟)。双主题:warm(奶油底+珊瑚红+cozy-handdrawn 透明插图,亲和感)和 midnight(深蓝黑底+琥珀金+宋体标题+executive-tech 插图,AI 科技感),storyboard 一个 theme 字段切换。每章三种 layout 混排:illustration(左文右图+Ken…

    283 GitHub stars~2.2k tokensUpdated 4 days ago
    Auto-check passed
  • Edu Teaching Animation

    wwwzhouhui/skills_collection

    把单个学科概念(中文/英文都行,如"声现象""杠杆原理""光合作用")自动做成动态教学内容。两种产出都由 HyperFrames 渲染、共用同一个 index.html(mode 变量切换):① 配音教学视频 — 分镜 + Minimax / Edge TTS 中文配音 + 字幕 + 完整 MP4(1080p, ~90s, 发视频号/给孩子看);② 无声循环动图 — 同一内容的紧凑无声版…

    283 GitHub stars~1.5k tokensUpdated 4 days ago
    Auto-check passed
  • Env Setup

    wwwzhouhui/skills_collection

    Checking and provisioning the machine's environment for the video-agent-kit plugin — probing for ffmpeg/ffprobe that actually carry the encoders and filters we render with (libx264/aac/libmp3lame…

    283 GitHub stars~3.5k tokensUpdated 4 days ago
    Auto-check: notes

Questions about Ip Talking Head Lecture

What does Ip Talking Head Lecture do?

IP 卡通数字人口播动画课件视频工厂。用 Remotion 把「一段逐字稿 + 一张 IP 形象图」变成一条成片:主讲 IP 以圆形头像常驻右下角讲课(待机浮动 + 口型开合 + 说话光环 + 声波条),主画面是自动排版的动画课件(封面 / 概念 / 步骤 / 对比 / 数据 / 总结 六套版式),底部居中烧录字幕并做跟读高亮,另有品牌水印与顶部进度条;配音走小米 MiMo 或火山引擎或…. Ip Talking Head Lecture is an agent skill from wwwzhouhui/skills_collection.

When should I use Ip Talking Head Lecture?

Ip Talking Head Lecture fits situations like: tasks that involve Video production; tasks that involve Text to speech and voice.

How do I install Ip Talking Head Lecture in Claude Code?

Run `npx skills add wwwzhouhui/skills_collection --skill ip-talking-head-lecture -a claude-code`. Or copy the skill folder (ip-talking-head-lecture in wwwzhouhui/skills_collection) into .claude/skills/ip-talking-head-lecture in your project. Claude Code loads it when a task matches its description.

How do I install Ip Talking Head Lecture in Codex?

Run `npx skills add wwwzhouhui/skills_collection --skill ip-talking-head-lecture -a codex`. Or copy the skill folder (ip-talking-head-lecture in wwwzhouhui/skills_collection) into .agents/skills/ip-talking-head-lecture in your project. Codex loads it when a task matches its description.

Can I use Ip Talking Head Lecture in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add wwwzhouhui/skills_collection --skill ip-talking-head-lecture -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ip-talking-head-lecture, .gemini/skills/ip-talking-head-lecture, .github/skills/ip-talking-head-lecture and .opencode/skills/ip-talking-head-lecture in your project.

What does Ip Talking Head Lecture need to run?

SKILL.md names no scripts, command-line tools or credentials: Ip Talking Head Lecture is instructions for the agent only.

Does Ip Talking Head Lecture access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Ip Talking Head Lecture safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Ip Talking Head Lecture use?

No licence was found for Ip Talking Head Lecture or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Ip Talking Head Lecture use?

About 2.5k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 8.5k tokens, read only when the agent opens those files.

What are the alternatives to Ip Talking Head Lecture?

Skills that share tags, products or a category with Ip Talking Head Lecture: Video Post Production (AnastasiyaW/codex-claude-code-config, 154 stars), Video Podcast Maker (Agents365-ai/video-podcast-maker, 1.7k stars), Explainroo (vincentsch/explainroo, 515 stars) and Super Video Maker (Bomx/super-video-maker-skill, 310 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ip Talking Head Lecture?

wwwzhouhui (a GitHub user) maintains it in wwwzhouhui/skills_collection, which has 283 GitHub stars. The repository holds 25 skills in this directory. The repository was last updated on October 6, 2026.

Source: wwwzhouhui/skills_collection on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.