youtube-transcript
Transform YouTube videos or transcripts into structured Obsidian notes with timestamps, metadata, callouts, and detailed section breakdowns. Use when the user provides a YouTube URL or asks to summarize, analyze, or convert a YouTube video into notes.
What this skill does
# YouTube Transcript to Obsidian Note
Use this skill when the user asks to "analyze YouTube video", "transform YouTube transcript", "create Obsidian note from YouTube", "summarize YouTube video", or provides a YouTube URL for detailed note-taking.
## Workflow
1. **Get YouTube URL**: If not provided, ask the user for the YouTube URL
2. **Extract transcript**: Use the Bash tool to run `yt-dlp --write-subs --write-auto-subs --skip-download <youtube_url>` to download subtitle files
3. **Read transcript**: Use the Read tool to read the downloaded subtitle file (.vtt or .srt format)
4. **Transform content**: Apply the content analysis and formatting rules below
5. **Ask for save location**: Ask the user where to save the note (suggest `~/Documents/` or their Obsidian vault path)
6. **Write note**: Use the Write tool to save the formatted Markdown file with a descriptive filename based on the video title
---
## Content Analysis Rules
* **Depth & Precision:** Never over-condense. Walk through the video step-by-step in simple language.
* **Frameworks:** If a method, process, or framework appears, rewrite it as clear, well-structured steps or paragraphs.
* **Ambiguity:** Do not add new facts. If the source is ambiguous, preserve the original meaning and explicitly note the uncertainty.
* **Timestamps:** Extract and include timestamps for every important section.
## Obsidian Formatting Rules
You must apply the following specific formatting syntax to the content:
* **Callouts:** Use Obsidian callouts for specific content types:
* `> [!quote]` for noteworthy lines or quotes worth pondering.
* `> [!tip]` for actionable advice, methods, or best practices.
* `> [!warning]` for common pitfalls or things to avoid.
* `> [!note]` for important clarifications, uncertainties, or caveats.
* **Styling:**
* Use **bold** for key concepts (first mention only).
* Use *italic* for subtle emphasis.
* Use `inline code` for technical terms, specific commands, or tools.
* **Structure:** Use `##` for main sections and `###` for subsections.
## Output Structure
Your **ENTIRE** response should be written to a single Markdown file using the Write tool.
### A. YAML Frontmatter
Add this at the very top (no code fences, just raw YAML):
---
title: (Create a descriptive title based on the content)
date: (Today's date YYYY-MM-DD)
tags: [youtube, video-notes, tag1, tag2]
source: (Video URL)
author: (Video Creator Name)
---
### B. Metadata Section
* **Channel/Author:** [Name]
* **Source URL:** [Link]
* **Duration:** [If available from video metadata]
### C. Overview
* A single, high-level paragraph stating the video's core argument and conclusion.
### D. Section Breakdown
* For each major topic/segment:
* **Heading:** (Topic Name)
* **Timestamp:** (e.g., 04:20)
* **Content:** The detailed explanation, steps, or analysis using the formatting rules defined above.
* If any claim is uncertain, mark it [uncertain] with a brief note.
* If there are good lines/quotes worth readers pondering, keep the quote (use quote callout).
### E. Key Takeaways (Optional)
* Bullet points of main insights or action items
---
## File Naming Convention
Use this format: `YYYY-MM-DD - [Video Title].md`
Example: `2026-01-29 - How to Build Better AI Agents.md`
## Error Handling
* If `yt-dlp` is not installed, inform the user and ask them to install it: `pip install yt-dlp`
* If no subtitles are available, inform the user that automatic transcription might not be available
* If the user prefers to provide the transcript manually, accept it and proceed with the transformation
Related in Image & Video
watch
IncludedWatch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or Whisper API fallback), and hands the result to Claude so it can answer questions about what's in the video.
physical-ai-defect-image-generation
IncludedUse when the user wants to orchestrate defect image generation, run associated setup, or handle outputs on OSMO. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint.
accelint-react-best-practices
IncludedReact performance optimization and best practices. ALWAYS use this skill when working with any React code - writing components, hooks, JSX; refactoring; optimizing re-renders, memoization, state management; reviewing for performance; fixing hydration mismatches; debugging infinite re-renders, stale closures, input focus loss, animations restarting; preventing remounting; implementing transitions, lazy initialization, effect dependencies. Even simple React tasks benefit from these patterns. Covers React 19+ (useEffectEvent, Activity, ref props). Triggers - useEffect, useState, useMemo, useCallback, memo, inline components, nested components, components inside components, re-render, performance, hydration, SSR, Next.js, useDeferredValue, combined hooks.
elevenlabs-agents
IncludedBuild conversational AI voice agents with ElevenLabs Platform using React, JavaScript, React Native, or Swift SDKs. Configure agents, tools (client/server/MCP), RAG knowledge bases, multi-voice, and Scribe real-time STT. Use when: building voice chat interfaces, implementing AI phone agents with Twilio, configuring agent workflows or tools, adding RAG knowledge bases, testing with CLI "agents as code", or troubleshooting deprecated @11labs packages, Android audio cutoff, CSP violations, dynamic variables, or WebRTC config. Keywords: ElevenLabs Agents, ElevenLabs voice agents, AI voice agents, conversational AI, @elevenlabs/react, @elevenlabs/client, @elevenlabs/react-native, @elevenlabs/elevenlabs-js, @elevenlabs/agents-cli, elevenlabs SDK, voice AI, TTS, text-to-speech, ASR, speech recognition, turn-taking model, WebRTC voice, WebSocket voice, ElevenLabs conversation, agent system prompt, agent tools, agent knowledge base, RAG voice agents, multi-voice agents, pronunciation dictionary, voice speed control, elevenlabs scribe, @11labs deprecated, Android audio cutoff, CSP violation elevenlabs, dynamic variables elevenlabs, case-sensitive tool names, webhook authentication
humanizer
IncludedHumanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 28 pattern detectors, 560+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
generating-mermaid-diagrams
IncludedSalesforce architecture diagrams using Mermaid with ASCII fallback. Use this skill when generating text-based diagrams for Salesforce architecture, OAuth flows, ERDs, integration sequences, or Agentforce structure. TRIGGER when: user says "diagram", "visualize", "ERD", or asks for sequence diagrams, flowcharts, class diagrams, or architecture visualizations in Mermaid. DO NOT TRIGGER when: user wants PNG/SVG image output (use generating-visual-diagrams), or asks about non-Salesforce systems.