ericgandrade/claude-superskills/youtube-summarizer
Claude Code and agent skill by ericgandrade/claude-superskills
- community
Checking that the SKILL.md file is still in the repository.
This skill should be used when the user needs to extract transcripts from YouTube videos and generate comprehensive, detailed summaries using intelligent analysis frameworks.
Install
npx vskill@latest install ericgandrade/claude-superskills/youtube-summarizerSKILL.md
youtube-summarizer
Purpose
This skill extracts transcripts from YouTube videos and generates comprehensive, verbose summaries using the STAR + R-I-S-E framework. It validates video availability, extracts transcripts using the youtube-transcript-api Python library, and produces detailed documentation capturing all insights, arguments, and key points.
The skill is designed for users who need thorough content analysis and reference documentation from educational videos, lectures, tutorials, or informational content.
When to Use This Skill
This skill should be used when:
- User provides a YouTube video URL and wants a detailed summary
- User needs to document video content for reference without rewatching
- User wants to extract insights, key points, and arguments from educational content
- User needs transcripts from YouTube videos for analysis
- User asks to "summarize", "resume", or "extract content" from YouTube videos
- User wants comprehensive documentation prioritizing completeness over brevity
Step 0: Environment Detection & Setup
Before processing, detect the execution environment to choose the correct transcript extraction strategy.
Environment Detection
Three modes are supported, tried in order:
| Mode | Condition | Strategy | |
|---|---|---|---|
| A — Python/CLI | Python 3 available + library installed | youtube-transcript-api (full featured) | |
| B — WebFetch | No Python OR sandboxed environment | Fetch YouTube page → extract transcript from embedded JSON | |
| C — Manual | YouTube blocked at network level | Ask user to paste transcript text directly |
Mode A Setup (Python available, library missing)
If Python is available but youtube-transcript-api is not installed, offer to install:
Mode B Setup (Sandboxed / Claude Cowork / no Python)
Use WebFetch to extract the transcript embedded in the YouTube page HTML. YouTube embeds full caption track URLs in ytInitialPlayerResponse JSON inside the page source.
Steps:
- WebFetch
https://www.youtube.com/watch?v=VIDEO_ID - Extract
ytInitialPlayerResponseJSON block from the HTML using regex - Parse
captions.playerCaptionsTracklistRenderer.captionTracks[0].baseUrl - WebFetch that URL to retrieve the transcript XML
- Parse XML
<text>elements into plain text
If the YouTube page itself is blocked (proxy/sandbox restriction), fall through to Mode C.
Mode C Setup (Network blocked)
Inform the user clearly:
Main Workflow
Progress Tracking Guidelines
Throughout the workflow, display a visual progress gauge before each step to keep the user informed. The gauge format is:
Format specifications:
- 20 characters wide (use █ for filled, ░ for empty)
- Percentage increments: Step 1=20%, Step 2=40%, Step 3=60%, Step 4=80%, Step 5=100%
- Step counter showing current/total (e.g., "Step 3/5")
- Brief description of current phase
Display the initial status box before Step 1:
Step 1: Validate YouTube URL
Objective: Extract video ID and validate URL format.
Supported URL Formats:
https://www.youtube.com/watch?v=VIDEO_IDhttps://youtube.com/watch?v=VIDEO_IDhttps://youtu.be/VIDEO_IDhttps://m.youtube.com/watch?v=VIDEO_ID
Actions:
If URL is invalid:
Step 2: Check Video & Transcript Availability
Progress:
Objective: Verify video exists and transcript is accessible using the detected mode.
Mode A (Python):
Mode B (WebFetch):
Use WebFetch to load https://www.youtube.com/watch?v=VIDEO_ID. Search the HTML for the string "captionTracks" to confirm captions are available. If the page is inaccessible or no captionTracks key is found, fall through to Mode C.
Error Handling:
| Error | Message | Action | |
|---|---|---|---|
| Video not found | "❌ Video does not exist or is private" | Ask user to verify URL | |
| Transcripts disabled | "❌ Transcripts are disabled for this video" | Cannot proceed | |
| No transcript available | "❌ No transcript found" | Cannot proceed | |
| YouTube blocked (sandbox) | "⚠️ YouTube is not accessible in this environment" | Switch to Mode C |
Step 3: Extract Transcript
Progress:
Objective: Retrieve transcript text using the active mode.
Mode A (Python):
Mode B (WebFetch):
- WebFetch the YouTube video page:
https://www.youtube.com/watch?v=VIDEO_ID - Locate the
ytInitialPlayerResponseJSON block in the HTML - Extract
captions.playerCaptionsTracklistRenderer.captionTracks[0].baseUrl - WebFetch that caption URL (returns XML with
<text>elements) - Strip XML tags and join
<text>segments into plain text
If the page load fails or no caption track URL is found, switch to Mode C.
Mode C (Manual):
Ask the user to provide the transcript:
Accept any plain text the user pastes and proceed directly to Step 4.
Transcript Processing (all modes):
- Combine all segments into coherent text
- Preserve punctuation and formatting where available
- Remove
[Music],[Applause]and other auto-generated noise markers
Step 4: Generate Comprehensive Summary
Progress:
Objective: Apply enhanced STAR + R-I-S-E prompt to create detailed summary.
Prompt Applied:
Use the enhanced prompt from Phase 2 (STAR + R-I-S-E framework) with the extracted transcript as input.
Actions:
- Load the full transcript text
- Apply the comprehensive summarization prompt
- Use AI model (Claude/GPT) to generate structured summary
- Ensure output follows the defined structure:
- Header with video metadata
- Executive synthesis
- Detailed section-by-section breakdown
- Key insights and conclusions
- Concepts and terminology
- Resources and references
Implementation:
Then apply the full summarization prompt (from enhanced version in Phase 2).
Step 5: Format and Present Output
Progress:
Objective: Deliver the summary in clean, well-structured Markdown.
Output Structure:
Save Options:
This is the start of the file. Read the full SKILL.md on GitHub.
Security
- Security scanPassed, 94 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/youtube-summarizer/SKILL.md
Popularity
- Repository stars
- 40
- Repository forks
- 6
- 7-day trend score
- 19
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 18 Mar 2026, 7 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/ericgandrade/claude-superskills/youtube-summarizer)