youtube-harvester

Name: youtube-harvester
Availability: InStock
Author: mindmorass

Extract YouTube transcripts and metadata for RAG indexing.

2|Updated Jan 2, 2026

Search Tags:#rag #youtube #metadata #ingestion #transcripts #chunking #harvesting

Ready to run

npx skills add https://github.com/mindmorass/reflex --skill youtube-harvester

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: youtube-harvester
Source: https://github.com/mindmorass/reflex/tree/main/plugins/reflex/skills/youtube-harvester
Command: npx skills add https://github.com/mindmorass/reflex --skill youtube-harvester

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

YouTube hosts a wealth of tutorials and lectures, but transcripts and metadata are often scattered or hard to index. This Skill provides end-to-end extraction, chunking, and enrichment to enable efficient retrieval and reasoning over video content.

Core Features & Use Cases

Transcript extraction from manual captions or auto-generated transcripts.
Timestamp-aware chunking for precise retrieval and context preservation.
Harvesting playlists and channels with workflows to ingest into a RAG collection.
Metadata enrichment (title, channel, upload date, duration, tags) to improve search and relevance.

Quick Start

Use the YouTube Harvester to ingest a video by URL into your RAG collection: harvest_youtube_video(url='https://youtube.com/watch?v=VIDEO_ID', collection='my_rag', chunk_strategy='time', chunk_size=300)

Frequently Asked Questions about youtube-harvester

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I extract YouTube transcripts for RAG indexing?▼

Extract YouTube transcripts using yt-dlp and youtube-transcript-api libraries to pull manual or auto-generated captions from videos. The Skill applies timestamp-aware chunking and ingests transcripts directly into your RAG collection for retrieval and reasoning over video content.

Can I harvest entire YouTube playlists and channels into a RAG collection?▼

Yes, the Skill supports harvesting playlists and channels with workflows that extract transcripts and metadata from multiple videos and ingest them into a target RAG collection in a single operation.

What chunking strategies are available for YouTube transcripts?▼

Time-based, topic-based, and semantic chunking strategies are supported. Time-based preserves timestamp context for precise retrieval, while topic and semantic approaches organize content by meaning for improved relevance in RAG queries.

Does YouTube harvesting include metadata enrichment?▼

Yes, metadata enrichment captures title, channel name, upload date, duration, and tags alongside transcripts. This enriched metadata improves search relevance and context preservation when indexing into your RAG collection.

Can I use audio transcription if YouTube captions aren't available?▼

Optional openai-whisper integration enables audio transcription when manual or auto-generated captions are unavailable, ensuring transcript extraction is possible across all video types in your harvesting workflow.

What are the Python dependencies required for YouTube transcript ingestion?▼

Core dependencies are yt-dlp and youtube-transcript-api for extraction. Optional openai-whisper adds audio transcription capability. Python environment with these libraries installed is the entry requirement before using the Skill.