Skip to content
youtube-to-slides logo

Youtube To Slides

youtube-to-slides

Convert a YouTube video into infographic slides. Extracts transcript, segments into sections, summarizes, and generates stylized infographic images using Gemini AI. 7 styles: davinci, magazine, comic, geek, chalkboard, collage, newspaper. Use when user wants slide summaries from YouTube.

NeverSight/skills_feed0installs215stars

SKILL.md

Full skill instructions

youtube-to-slides

Convert YouTube videos into beautiful infographic slide decks.

Natural Language Examples

Users can invoke this skill with natural language. Here are examples of what they might say and how to handle each:

Setup and troubleshooting:

  • "Set up youtube-to-slides" → Run setup.sh
  • "Check if youtube-to-slides is ready" → Run check-env.sh
  • "I need to configure my API keys" → Guide to .env setup
  • "It's not working" → Run check-env.sh, read diagnostics, consult references/​TROUBLESHOOTING.md

Generate slides:

Choose a style:

  • "Use the davinci style" → --style davinci
  • "Make it look like a magazine" → --style magazine
  • "Comic book style please" → --style comic
  • "Geek / bulletin board style" → --style geek
  • "Chalkboard style" → --style chalkboard
  • "Collage / dreamcore style" → --style collage
  • "Newspaper style" → --style newspaper

Control slide count:

  • "Just give me 4 slides" → --max-sections 4
  • "Make as many slides as needed" → --max-sections 0

Preview without generating images:

  • "Do a dry run first"
  • "Just show me the prompts, don't generate images yet"

Argument Parsing

Parse $ARGUMENTS to extract:

  • url (required) — YouTube video URL. Supports formats: https://youtu.be/​ID, https://www.youtube.com/​watch?v=ID, https://youtube.com/​watch?v=ID
  • --style (optional, default: davinci) — One of: davinci, magazine, comic, geek, chalkboard, collage, newspaper
  • --max-sections (optional, default: 8) — Maximum number of slide sections to generate. Use 0 for unlimited.
  • --dry-run (optional) — Show prompts without generating images
  • --ar (optional, default: 16:9) — Aspect ratio: 16:9, 4:3, or 1:1

If no URL is provided, ask the user for one. If the URL looks invalid (not a YouTube URL), tell the user and ask for a valid one.

For style guidance, read references/​STYLES.md in this skill directory.

Execution Steps

Step 1: Pre-flight Check

Run the environment check script:

bash "$SKILL_DIR/​scripts/​check-env.sh"
  • If it exits 0, proceed to Step 2.
  • If it exits non-zero, read its output for diagnostics:
    • Missing virtual environment or package — Run the setup script:
      bash "$SKILL_DIR/​scripts/​setup.sh"
      
      Then re-run check-env.sh to confirm.
    • Missing API keys — Tell the user:
      1. Copy the example env file: cp "$SKILL_DIR/​.env.example" "$SKILL_DIR/​.env"
      2. Add their Gemini API key (get one free at https://aistudio.google.com/apikey)
      3. Add their YouTube Data API key (get one at https://console.cloud.google.com/apis/credentials — enable YouTube Data API v3 first)
      4. See references/​TROUBLESHOOTING.md for detailed setup steps.
    • After fixing, re-run check-env.sh to confirm everything passes.

If the user just asks to "set up" or "install" the skill, run both setup.sh and check-env.sh, then report the result.

Step 2: Run the Pipeline

Build the command from parsed arguments and run:

bash "$SKILL_DIR/​scripts/​run.sh" "<url>" --style <style> --max-sections <max_sections> --ar <ar>

Add --dry-run flag if requested.

This takes 3-5 minutes for a full run. Inform the user that generation is in progress and what style/​settings are being used.

Step 3: Present Results

After successful completion:

  1. Determine the video ID from the URL (the 11-character ID, e.g. twzLDx9iers from https://youtu.be/​twzLDx9iers)
  2. Read output/<video_id>/​metadata.json to get the list of generated slides
  3. Present a summary to the user:
    • Video title and channel
    • Style used
    • Number of slides generated
    • List each slide with its title and file path
  4. Show the user how to open the slides:
    open output/<video_id>/
    

Error Handling

If the pipeline fails, check output for common errors and consult references/​TROUBLESHOOTING.md:

  • 429 Rate Limit — Gemini rate limit hit. The tool has built-in retry logic. If it still fails, suggest waiting 60 seconds and retrying.
  • No transcript available — The video may not have captions. Inform the user.
  • Invalid URL — Ask the user for a valid YouTube URL.
  • API key errors — Guide user to set up their .env file with valid keys.

Variable Reference

  • $SKILL_DIR — Absolute path to this skill's directory (skills/​youtube-to-slides/)
  • $ARGUMENTS — Raw argument string passed by the user

More skills from NeverSight

devops-deployer logo
NeverSight/skills_feed

devops-deployer

Comprehensive DevOps and deployment workflow that orchestrates infrastructure automation, CI/CD pipelines, container orchestration, and cloud deployment. Handles everything from infrastructure as code and pipeline setup to monitoring, scaling, and disaster recovery.

215 1
View
avnu logo
NeverSight/skills_feed

avnu

Integrate avnu SDK for Starknet DeFi: token swaps with best-price routing, DCA recurring buys, native staking, gasless transactions via paymaster, and market data. Use when building Starknet trading, DEX aggregation, or DeFi automation features.

215 0
View
post-to-x logo
NeverSight/skills_feed

post-to-x

发布内容和文章到 X (Twitter)。支持带图片的普通推文和 X Articles(长文)。使用真实的 Chrome 和 CDP 来绕过自动化检测。

215 0
View
ralph-prompt-builder logo
NeverSight/skills_feed

ralph-prompt-builder

Master orchestrator for generating Ralph Wiggum-compatible prompts. Analyzes task requirements and routes to appropriate generator (single-task, multi-task, project, or research). Use when you need to create any Ralph loop prompt and want automatic selection of the right generator.

215 0
View
branch-comparison logo
NeverSight/skills_feed

branch-comparison

Use when the user asks to compare branches, analyze git diffs, review changes between branches, update specifications based on code changes, or analyze what changed. Triggers on keywords like "compare branches", "git diff", "what changed", "branch comparison", "code changes", "spec update".

215 0
View
fastapi-development logo
NeverSight/skills_feed

fastapi-development

Build high-performance FastAPI applications with async routes, validation, dependency injection, security, and automatic API documentation. Use when developing modern Python APIs with async support, automatic OpenAPI documentation, and high performance requirements.

215 0
View
zendesk-chat logo
NeverSight/skills_feed

zendesk-chat

Enables Claude to manage Zendesk Chat conversations, support tickets, and customer service operations

215 0
View
forge logo
NeverSight/skills_feed

forge

Mine transcripts for knowledge - decisions, learnings, failures, patterns. Triggers: "forge insights", "mine transcripts", "extract knowledge".

215 0
View
mixpanel logo
NeverSight/skills_feed

mixpanel

Track product analytics and user behavior with Mixpanel's event-based platform.

215 0
View
ocpp logo
NeverSight/skills_feed

ocpp

OCPP protocol reference for EV charging infrastructure development. Covers OCPP 2.0.1 and OCPP 1.6J. Use when working with OCPP messages, charging station code, CSMS/Central System backends, smart charging, transaction handling, or EV charging protocols. Activates on keywords: OCPP, charging stat...

215 0
View
bee-collect logo
NeverSight/skills_feed

bee-collect

Gather scattered ideas into organized GitHub issues. The bee collects pollen from every flower, checks if the hive already has it, and carefully deposits new work in the comb for later. Never edits code—only organizes the work ahead. Use when creating issues from TODOs or planning work.

215 0
View
vercel-react-native-skills logo
NeverSight/skills_feed

vercel-react-native-skills

Comprehensive best practices for React Native and Expo applications. Contains rules across multiple categories covering performance, animations, UI patterns, and platform-specific optimizations.

215 0
View

Popular AI tools

Kaiber logo
Video

Kaiber

Generate, edit, and beat-sync AI video with leading models in one workspace.

Paid
View
Vimcal logo
Productivity

Vimcal

The world's fastest calendar for remote work

Free
View

Transform Your Design with AI Designer by ImgCreator.ai

Freemium
View
Akool AI logo
Content & writing

Akool AI

Revolutionizing Video Production with AI-Powered Creativity

Paid
View

Extend an image past the frame and let AI fill the new aspect ratio.

Freemium
View
StarByFace logo
Security

StarByFace

Discover your celebrity doppelgänger with StarByFace!

Free
View
C

ChainClarity explains 700+ crypto whitepapers in plain English, with layered summaries, comparisons, research tools, alerts, and a $4.99 Pro plan.

Freemium
View
Opus Clip logo
Coding & apps

Opus Clip

Opus.ai: Revolutionize Your Web Experience

Free
View