Udemy video pipeline
Skill mustafayilmazart/kesif-claude-skills/skills/udemy-video-pipeline
14 production-ready Claude Code skill — TTS, video, NotebookLM, YouTube, token optimization, prompt engineering
npx -y skills add mustafayilmazart/kesif-claude-skills --skill udemy-video-pipelineAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Udemy/eğitim videosu üretim pipeline'i. NotebookLM araştırma → Türkçe ders scripti → ElevenLabs seslendirme → video montaj. Udemy, ders videosu, kurs videosu, eğitim videosu, ders/kurs oluştur dediğinizde çağrılır. Bölüm-bazlı organizasyon ve altyazı desteği.
SKILL.md
3.0 KB, 883 tokens by cl100k_base, as published. Nobody here has run it
Udemy Video Pipeline
NotebookLM ile arastirma yapip, Turkce ders scripti uretip, ElevenLabs ile seslendiren tam otomasyon pipeline'i.
Pipeline Asamalari
1. Konu Arastirma (NotebookLM)
- YouTube'dan kaynak videolar bulunur
- NotebookLM'e kaynak olarak yuklenir
- Detayli Turkce analiz uretilir
2. Script Uretimi (Claude)
- NotebookLM analizinden ders scripti yazilir
- Slayt icerikleri cikarilir
- Zamanlama ve bolum planlanir
3. Seslendirme (ElevenLabs)
- Script bolum bolum seslendirilir
- Kullanicinin "Kesif -TR" sesi kullanilir
- MP3 dosyalari uretilir
4. Video Birleştirme (opsiyonel)
- Ses + slayt birlestirilir
- SRT altyazi eklenir
Kullanim
Tam Pipeline
python ~/.claude/skills/udemy-video-pipeline/scripts/create_course.py \
"Bagimlilik Norobiyolojisi" \
--sections 5 \
--voice "Kesif -TR" \
--output-dir <workspace>/udemy-courses/bagimlilik
Sadece Script Uret
python ~/.claude/skills/udemy-video-pipeline/scripts/generate_script.py \
--topic "Bagimlilik Norobiyolojisi" \
--analysis <workspace>/notebooklm/output/bagimlilik-analysis.md \
--sections 5 \
--output <workspace>/udemy-courses/bagimlilik/script.json
Script'ten Seslendirme
python ~/.claude/skills/udemy-video-pipeline/scripts/narrate_script.py \
--script <workspace>/udemy-courses/bagimlilik/script.json \
--voice "Kesif -TR" \
--output-dir <workspace>/udemy-courses/bagimlilik/audio
Script Formati (JSON)
{
"title": "Bagimlilik Norobiyolojisi",
"language": "tr",
"sections": [
{
"id": 1,
"title": "Giris: Bagimlilik Nedir?",
"duration_estimate": "5 min",
"narration": "Merhaba, bu derste bagimlilik norobiyolojisini...",
"slides": [
{ "type": "title", "content": "Bagimlilik Norobiyolojisi" },
{ "type": "bullet", "content": ["Tanimlama", "Beyin mekanizmalari"] }
],
"notes": "Ogrencilere kendi deneyimlerini dusunmelerini soyle"
}
]
}
Ses Ayarlari (Udemy Optimum)
- Model: eleven_multilingual_v2
- Stability: 0.65 (dogal ama tutarli)
- Similarity: 0.80 (sese sadik)
- Style: 0.15 (hafif vurgulu, monoton degil)
- Format: mp3_44100_128 (Udemy uyumlu)
Dizin Yapisi
output-dir/
script.json # Tam ders scripti
audio/
section_01.mp3 # Bolum seslendirmeleri
section_02.mp3
...
slides/
section_01.md # Slayt icerikleri
section_02.md
subtitles/
section_01.srt # Altyazilar
metadata.json # Kurs bilgileri
What ships with it: 3 files
20.4 KB alongside SKILL.md, 3 of them executable
scripts/
- create_course.pyruns4.7 KB
- generate_script.pyruns8.1 KB
- narrate_script.pyruns7.6 KB
Gives 0 of the 12 instructions most video audio skills give in 883 tokens
Counted across 622 of the 795 authors here whose files we hold, read 2026-08-07
- Read individual rule files for detailed explanationsin 21 of 622, across 10 files
- Render final videoin 13 of 622, across 6 files
- Use WAV PCM 16kHz mono audio formatin 12 of 622, across 3 files
- Use this skill when dealing with Remotion codein 11 of 622, across 4 files
- Save generated audio to a WAV filein 11 of 622, across 4 files
- Handle conversion errors gracefullyin 10 of 622, across 6 files
- Add captions to videos alwaysin 10 of 622, across 4 files
- Generate music from text descriptions using MusicGenin 9 of 622, across 2 files
- Do not skip pipeline layersin 9 of 622, across 3 files
- Do not make one tool do everythingin 9 of 622, across 3 files
- Use Azure Document Intelligence for complex PDFsin 9 of 622, across 4 files
- Never ask the user to paste their full API keyin 9 of 622, across 3 files
Said here and by no other author read
- load source videos into NotebookLM
- generate Turkish analysis from sources
- write lesson scripts from analysis
- extract slide contents from scripts
- plan timings and sections
- narrate scripts section by section
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.