Not in the top 1,000 by GitHub stars

Vibetool/talking-head-video

Turn a 口播/talking-head video + script into a polished vertical explainer — synced subtitles, animated Remotion knowledge graphics, and a circular PiP avatar. A Claude Agent Skill.

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Local scripts → After Local scripts

5b46d7924ac1 → 5b46d7924ac1

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → 5b46d7924ac1

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit 5b46d7924ac18a6e1d1aead9be7b7c27d235153c

10GitHub stars
0stars in 7 days
1skill in this repository
0commits in 30 days

Heat

0.3
  • Star growth, last 7 daysNot available
  • Star growth, last 24 hoursNot available
  • Rank movement, last 7 daysNot available
  • Commits, last 30 daysNot available
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Oct 25, 2026Oct 25, 202610

30-day change not yet available: not enough history.

Individual skills in this repository

How it works

talking-head-video

When your agent uses it

Turn a raw 口播 / talking-head selfie video plus its script into a finished explainer, vertical 9:16 or landscape 横屏 16:9 — synced burned-in subtitles, animated knowledge graphics in three selectable styles (darkcard 深色科技卡 default, watercolor 纸上水彩, inkline 白纸简笔; both style and orientation are confirmed with the user first), and a circular picture-in-picture avatar that shrinks the speaker to the top-left while a graphic or B-roll fills the screen during explanations. THE pipeline whenever someone has a clip of a person talking to camera and wants it "剪成成片", subtitles auto-added from a 逐字稿/脚本, the 画面 to "切成图/弹图表/做大数字特效" on key points while the "人脸/人头缩小、放到角落、变成圆形头像/画中画/小圈圈", or Remotion/ffmpeg 动态讲解图 cut into a 口播/讲解/知识科普短视频 for 视频号/抖音/B站/Shorts. Also covers standalone 知识卡/概念卡/章节卡 in any of the three styles (水彩/简笔画/ 深色卡) without a source video. Partial asks count: "帮我剪口播", "自动加字幕配动态图", "源视频和脚本都有帮我合成成片". NOT for: writing a 口播脚本, 数字人/AI 主播 reading a script, multi-cam cutting, PPT→video, video compression, audio→text transcription, or subtitling an unrelated movie clip.

What it loads into context

Frontmatter

389 tokens

Always available to the agent

SKILL.md

3,091 tokens

When the skill is activated

Reference documents

4,159 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. The core idea (why it's built this way)
  2. Prerequisites (check / install once)
  3. Workflow
  4. 开工前先问用户(硬规则)
  5. 图卡风格 · Graphics styles(三选一)
  6. 画幅 · Orientation parameter sets (both proven on real videos)
  7. Editorial conventions worth keeping
  8. Reusable assets in this skill

Scripts executed separately

  • assets/remotion/package.json
  • assets/remotion/src/Edison.tsx
  • assets/remotion/src/MedicalCards.tsx
  • assets/remotion/src/PromptToDrug.tsx
  • assets/remotion/src/RecruitChart.tsx
  • assets/remotion/src/Root.tsx
  • assets/remotion/src/ThesisKeys.tsx
  • assets/remotion/src/WetDry.tsx
  • assets/remotion/src/examples/DarkcardExample.tsx
  • assets/remotion/src/examples/InklineExample.tsx
  • assets/remotion/src/examples/WatercolorExample.tsx
  • assets/remotion/src/fonts.ts
  • assets/remotion/src/index.ts
  • assets/remotion/src/inkline.tsx
  • assets/remotion/src/theme.tsx
  • assets/remotion/src/watercolor.tsx
  • scripts/build_composite.py
  • scripts/generate_subs.py
  • scripts/make_avatar.sh
  • scripts/render_graphics.sh
  • scripts/setup_fonts.sh
  • scripts/transcribe.py

Files

  • .gitignoreasset191 bytes
  • LICENSEasset1,065 bytes
  • README.mddoc5,869 bytes
  • SKILL.mdcore11,129 bytes
  • SKILL.mdcore11,129 bytes
  • SKILL.mdcore11,129 bytes
  • assets/fonts/HuiwenMincho.otfasset16,625,636 bytes
  • assets/fonts/LXGWWenKai-Bold.ttfasset18,546,748 bytes
  • assets/fonts/LXGWWenKai-Light.ttfasset28,267,156 bytes
  • assets/fonts/SmileySans-Oblique.ttfasset2,629,764 bytes
  • assets/fonts/SourceHanSerifSC-Heavy.otfasset24,063,280 bytes
  • assets/fonts/SpecialElite-Regular.ttfasset166,180 bytes
  • assets/remotion/package.jsonruns382 bytes
  • assets/remotion/src/Edison.tsxruns3,889 bytes
  • assets/remotion/src/MedicalCards.tsxruns3,669 bytes
  • assets/remotion/src/PromptToDrug.tsxruns4,183 bytes
  • assets/remotion/src/RecruitChart.tsxruns6,395 bytes
  • assets/remotion/src/Root.tsxruns2,258 bytes
  • assets/remotion/src/ThesisKeys.tsxruns3,572 bytes
  • assets/remotion/src/WetDry.tsxruns5,032 bytes
  • assets/remotion/src/examples/DarkcardExample.tsxruns2,783 bytes
  • assets/remotion/src/examples/InklineExample.tsxruns3,337 bytes
  • assets/remotion/src/examples/WatercolorExample.tsxruns7,200 bytes
  • assets/remotion/src/fonts.tsruns2,235 bytes
  • assets/remotion/src/index.tsruns109 bytes
  • assets/remotion/src/inkline.tsxruns1,376 bytes
  • assets/remotion/src/theme.tsxruns3,920 bytes
  • assets/remotion/src/watercolor.tsxruns2,251 bytes
  • assets/remotion/tsconfig.jsonasset301 bytes
  • references/design-system.mddoc4,354 bytes
  • references/styles.mddoc3,823 bytes
  • scripts/build_composite.pyruns3,543 bytes
  • scripts/generate_subs.pyruns2,664 bytes
  • scripts/make_avatar.shruns1,694 bytes
  • scripts/render_graphics.shruns770 bytes
  • scripts/segments.example.jsonasset603 bytes
  • scripts/setup_fonts.shruns1,649 bytes
  • scripts/transcribe.pyruns1,610 bytes
Read SKILL.md

# Talking-Head Explainer Video

Build a finished 口播 video (vertical 9:16 by default, landscape 16:9 fully
supported — see 画幅 section) where the speaker is full-frame by default,
and during each explanation beat the speaker shrinks into a **circular avatar in
the top-left** while an **animated knowledge graphic** (chart / data cards /
comparison / flow / big-number) fills the screen. Subtitles are burned in and
corrected against the user's verbatim script.

This skill captures a real working pipeline. Read this whole file first, then the
references as needed. The design conventions exist for concrete reasons — keep
them unless the user asks otherwise.

## The core idea (why it's built this way)
View the complete source on GitHub

Skills included

  • talking-head-video

Repository facts

License
MIT
Created
Jun 16, 2026
Last pushed
Jul 16, 2026
Forks
1
Open issues
0
Project activity
Slowing

Before you install

Local scripts

Automated signals, not a guarantee

Checked Nov 4, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 6 notes
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • assets/fonts/HuiwenMincho.otf:1 Analysis incomplete: Blob exceeds size or total-read limit; file skipped
  • assets/fonts/LXGWWenKai-Bold.ttf:1 Analysis incomplete: Blob exceeds size or total-read limit; file skipped
  • assets/fonts/LXGWWenKai-Light.ttf:1 Analysis incomplete: Blob exceeds size or total-read limit; file skipped
  • assets/fonts/SourceHanSerifSC-Heavy.otf:1 Analysis incomplete: Blob exceeds size or total-read limit; file skipped
Show all 27 signals by file

README.md

  • Network accessline 9
    This is a [Claude](https://claude.com/claude-code) **Agent Skill**. Drop it in
  • Network accessline 22
    - **Burned-in subtitles**, timed by faster-whisper and **corrected against your   verbatim script** (no more mis-heard brand names / 同音字) - **Animated knowledge graphics** built with [Remotion](https://remotion.dev) in
  • Network accessline 23
    verbatim script** (no more mis-heard brand names / 同音字) - **Animated knowledge graphics** built with [Remotion](https://remotion.dev) in   a dark "premium / scientific" design system — six reusable archetypes:
  • Network accessline 24
    - **Animated knowledge graphics** built with [Remotion](https://remotion.dev) in
  • Network accessline 94
    git clone https://github.com/Vibetool/talking-head-video.git \

assets/remotion/package.json

  • Executable scriptline 1
    Executable file

assets/remotion/src/Edison.tsx

  • Executable scriptline 1
    Executable file

assets/remotion/src/MedicalCards.tsx

  • Executable scriptline 1
    Executable file

assets/remotion/src/PromptToDrug.tsx

  • Executable scriptline 1
    Executable file

assets/remotion/src/RecruitChart.tsx

  • Executable scriptline 1
    Executable file

assets/remotion/src/Root.tsx

  • Executable scriptline 1
    Executable file

assets/remotion/src/ThesisKeys.tsx

  • Executable scriptline 1
    Executable file

assets/remotion/src/WetDry.tsx

  • Executable scriptline 1
    Executable file

assets/remotion/src/examples/DarkcardExample.tsx

  • Executable scriptline 1
    Executable file

assets/remotion/src/examples/InklineExample.tsx

  • Executable scriptline 1
    Executable file

assets/remotion/src/examples/WatercolorExample.tsx

  • Executable scriptline 1
    Executable file

assets/remotion/src/fonts.ts

  • Executable scriptline 1
    Executable file

assets/remotion/src/index.ts

  • Executable scriptline 1
    Executable file

assets/remotion/src/inkline.tsx

  • Executable scriptline 1
    Executable file

assets/remotion/src/theme.tsx

  • Executable scriptline 1
    Executable file

assets/remotion/src/watercolor.tsx

  • Executable scriptline 1
    Executable file

scripts/build_composite.py

  • Executable scriptline 1
    #!/usr/bin/env python3

scripts/generate_subs.py

  • Executable scriptline 1
    #!/usr/bin/env python3

scripts/make_avatar.sh

  • Executable scriptline 1
    #!/bin/bash

scripts/render_graphics.sh

  • Executable scriptline 1
    #!/bin/bash

scripts/setup_fonts.sh

  • Executable scriptline 1
    #!/bin/bash

scripts/transcribe.py

  • Executable scriptline 1
    #!/usr/bin/env python3

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Signal confidence: 27 facts

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeCompatibleStandard SKILL.md SKILL.md.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.