A complete pipeline to convert YouTube videos into high-quality, SEO-optimized guide pages using Gemini AI.
npx skills add https://github.com/kennyzir/7deer_skills --skill youtube-content-gen
A "video-to-page" pipeline that automates the creation of high-quality guide pages from YouTube videos. It extracts transcripts, analyzes content with Gemini AI, and generates Next.js pages with SEO best practices.
resources/scripts/)video_processor.py: The main entry point. Orchestrates the flow.transcript_extractor.py: Wraps youtube-transcript-api to get subtitles.content_analyzer.py: Uses Gemini API to understand video content and structure the page.page_generator.py: Renders Jinja2 templates into .tsx and .module.css files.image_handler.py: Downloads and optimizes video thumbnails.resources/templates/)page.tsx.j2: Next.js page template with built-in Schema.org, responsive video embed, and SEO metadata.page.module.css.j2: Matching CSS module for the generated page.Install the required Python dependencies:
pip install -r resources/requirements.txt
Set your Gemini API key:
$env:GEMINI_API_KEY = "your_api_key_here"
From a YouTube URL:
python resources/scripts/video_processor.py --url "https://www.youtube.com/watch?v=VIDEO_ID"
From a Keyword (Auto-Search):
python resources/scripts/video_processor.py --keyword "game topic to search"
The script will:
app/guides/[topic-slug]/.public/images/guides/[topic-slug]/.Run the build to ensure everything is correct:
npm run build
Take kennyzir/youtube-content-gen from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.
The instructions reference pip.
Without those the skill loads but fails at the first command.