Co-Pilot / 辅助式
更新于 24 days ago

video-skills

Llispking
0.0k
lispking/video-skills
80
Agent 评分

💡 摘要

此技能使用Manim生成教学视频,带有可选的旁白和封面生成。

🎯 适合人群

制作视频内容的教育工作者通过视觉辅助学习的学生教育领域的内容创作者将视频生成集成到应用程序中的开发人员寻找高效教学工具的辅导员

🤖 AI 吐槽:把提示变成视频?听起来像是拖延实际教学的好方法!

安全分析中风险

该技能可能会执行Shell命令并访问文件系统,存在任意代码执行的风险。确保对输入进行适当验证,并限制脚本的权限。

Manim Video Teacher Skill

A skill package and helper scripts to turn prompts into Manim teaching videos with optional narration, muxing, and cover generation.

Quick start

  1. Create a virtual environment and install deps:
python -m venv .venv source .venv/bin/activate pip install -r requirements.txt
  1. Render your Manim scene to a video file (example):
manim -qh your_scene.py YourScene
  1. Run the pipeline (TTS + mux + cover):
python manim-video-teacher/scripts/pipeline.py \ --video media/videos/your_scene/1080p60/YourScene.mp4 \ --tts-file examples/narration.txt \ --cover-title "Quadratic Vertex Form" \ --cover-subtitle "Learn in 60s" \ --output output.mp4

Scripts

  • manim-video-teacher/scripts/tts_generate.py: Generate narration audio with edge-tts.
  • manim-video-teacher/scripts/concat_audio.py: Concatenate multiple audio segments.
  • manim-video-teacher/scripts/mux_av.py: Mux audio and video into a single MP4.
  • manim-video-teacher/scripts/make_cover.py: Generate a simple 16:9 cover image.
  • manim-video-teacher/scripts/pipeline.py: One-click pipeline for TTS, mux, and cover.

Requirements

  • Python 3.10+
  • ffmpeg (installed and on PATH)

Skill installation

Install the skill by placing the folder under your skills directory:

./scripts/install_skill.sh --dest /path/to/skills

If you are using Codex and have $CODEX_HOME set, you can omit --dest:

./scripts/install_skill.sh

Reinstall with overwrite:

./scripts/install_skill.sh --dest /path/to/skills --force

Preview the resolved install target:

./scripts/install_skill.sh --list

Install into a local ./skills folder in the current directory:

./scripts/install_skill.sh --here

If a ./skills folder already exists, the installer will use it by default.

Examples

  • examples/narration.txt: Sample narration text.
  • examples/scene.py: Minimal Manim scene to render.
  • examples/tts_list.txt: Example ffmpeg concat list file.

Demo script

Run an end-to-end demo (venv + deps + render + pipeline):

./scripts/run_demo.sh

Clean generated files:

./scripts/clean.sh

Skill package

The skill lives in manim-video-teacher/ with its SKILL.md and scripts.

License

Apache License 2.0. See LICENSE.

五维分析
清晰度8/10
创新性8/10
实用性9/10
完整性8/10
可维护性7/10
优缺点分析

优点

  • 自动化视频创建过程
  • 支持TTS旁白
  • 易于安装和使用
  • 与Manim良好集成

缺点

  • 需要安装Python和ffmpeg
  • 仅限于Manim的功能
  • 复杂场景可能需要手动调整
  • 依赖外部脚本

相关技能

pytorch

S
toolCode Lib / 代码库
92/ 100

“它是深度学习的瑞士军刀,但祝你好运能从47种安装方法里找到那个不会搞崩你系统的那一个。”

agno

S
toolCode Lib / 代码库
90/ 100

“它承诺成为智能体领域的Kubernetes,但得看开发者有没有耐心学习又一个编排层。”

nuxt-skills

S
toolCo-Pilot / 辅助式
90/ 100

“这本质上是一份组织良好的小抄,能把你的 AI 助手变成一只 Nuxt 框架的复读机。”

免责声明:本内容来源于 GitHub 开源项目,仅供展示和评分分析使用。

版权归原作者所有 lispking.