Skip to main content
skill CX Codex

youtube-transcript · intellectronica — Claude Code skill: what it does, how to install

Extracts transcripts and subtitles from YouTube videos. Useful when you need video text with or without timestamps inside your agent.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add intellectronica/agent-skills --skill youtube-transcript -a claude-code
Open on GitHub

What youtube-transcript does

The skill executes scripts/get_transcript.py using uv and pulls captions via youtube-transcript-api. It accepts standard links like https://www.youtube.com/watch?v=VIDEO_ID, short URLs such as https://youtu.be/VIDEO_ID, embed links, or raw 11-character video IDs.

By default, output arrives as plain text split by speech segments. Supplying --timestamps prepends [MM:SS] or [HH:MM:SS] to each segment. Results write to a specified path or fall back to {video_id}-transcript.txt. The script fails if the video has captions disabled, though it safely falls back to auto-generated subtitles when manual captions are missing.

What it helps with

  • pull captions from a YouTube video into a local text file
  • generate timestamped transcripts for video outlines
  • read auto-generated subtitles without manual copy-pasting

Example prompts for the agent

  • Get transcript from https://www.youtube.com/watch?v=VIDEO_ID
  • Download subtitles with timestamps from https://youtu.be/VIDEO_ID into summary.txt
  • Extract clean text from YouTube video VIDEO_ID

How to install youtube-transcript

1Skills CLI (Vercel)

npx skills add intellectronica/agent-skills --skill youtube-transcript -a claude-code

2Manually: put the files in place

~/.claude/skills/youtube-transcript/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/youtube-transcript/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about youtube-transcript

How to install youtube-transcript in Claude Code?

Run npx skills add intellectronica/agent-skills --skill youtube-transcript -a claude-code. The skill file is placed in ~/.claude/skills/youtube-transcript/SKILL.md.

What does youtube-transcript do?

It runs a Python script via uv to extract video captions. The result can include timestamp markers or plain paragraph text.

What are the requirements for extracting captions?

You need uv installed, and the video must have captions enabled. It retrieves manual captions first and falls back to auto-generated ones.

Source text

SKILL.md · CC0-1.0
---
name: youtube-transcript
description: Extract transcripts from YouTube videos. Use when the user asks for a transcript, subtitles, or captions of a YouTube video and provides a YouTube URL (youtube.com/watch?v=, youtu.be/, or similar). Supports output with or without timestamps.
---

# YouTube Transcript

Extract transcripts from YouTube videos using the youtube-transcript-api.

## Usage

Run the script with a YouTube URL or video ID:

```bash
uv run scripts/get_transcript.py "VIDEO_URL_OR_ID"
```

With timestamps:

```bash
uv run scripts/get_transcript.py "VIDEO_URL_OR_ID" --timestamps
```

## Defaults

- **Without timestamps** (default): Plain text, one line per caption segment
- **With timestamps**: `[MM:SS] text` format (or `[HH:MM:SS]` for longer videos)

## Supported URL Formats

- `https://www.youtube.com/watch?v=VIDEO_ID`
- `https://youtu.be/VIDEO_ID`
- `https://youtube.com/embed/VIDEO_ID`
- Raw video ID (11 characters)

## Output

- CRITICAL: YOU MUST NEVER MODIFY THE RETURNED TRANSCRIPT
- If the transcript is without timestamps, you SHOULD clean it up so that it is arranged by complete paragraphs and the lines don't cut in the middle of sentences.
- If you were asked to save the transcript to a specific file, save it to the requested file.
- If no output file was specified, use the YouTube video ID with a `-transcript.txt` suffix.

## Notes

- Fetches auto-generated or manually added captions (whichever is available)
- Requires the video to have captions enabled
- Falls back to auto-generated captions if manual ones aren't available

© intellectronica · CC0-1.0 · intellectronica/agent-skills

Similar skills

All skills for Agent setup: memory, context, orchestration →

youtube-transcript by other authors comes first.

youtube-transcript badlogic Fetches timestamped transcripts from YouTube videos for summarization and quick analysis. Useful when extracting key insights directly in your coding assistant. CX Codex +1 714installs youtube-transcript michalparkola Downloads YouTube captions and transcripts from a video URL. Use it when you need a video’s text for reading or analysis. CX Codex +1 861installs setup-matt-pocock-skills Matt Pocock This skill configures a repository for Matt Pocock's engineering skills by setting its issue tracker, triage labels, and domain docs layout. Run it before using the other skills. 1,052,851installs ask-matt Matt Pocock Routes you to the right Matt Pocock skill or flow for the task at hand. Use it when you need a starting point for a feature, prototype, incoming issue, or hard bug. 766,587installs to-tickets Matt Pocock Turns a plan, spec, or conversation into small end-to-end tickets with explicit blockers. Use it to agree on the work breakdown before tickets go to a tracker. 711,230installs writing-plans Jesse Vincent This skill turns requirements for a multi-step task into an implementation plan before code changes begin. It helps when another engineer needs exact files, interfaces, and checks. CX Codex 282,859installs caveman-review JuliusBrussee Turns code review comments into one line per finding: location, problem, fix. Useful when a diff or PR needs a fast pass without the filler. CX Codex +1 411,800installs caveman-compress JuliusBrussee Compresses CLAUDE.md, todo lists, and other prose files into a shorter format while retaining a readable backup. CX Codex +1 411,500installs

From the same set20

notion-api A skill for interacting with the Notion API through REST requests. Gives agents full access to pages, databases, blocks, and comments — read, create, update, and delete content. CX Codex +1 94,900installs context7 Fetches up-to-date documentation and code examples for libraries via the Context7 API. Useful when model training data is outdated or API methods changed. CX Codex +1 11,200installs nano-banana-pro Generates and modifies images using Google's Gemini 3 Pro Image API. Handy when you need quick illustrations or visual edits directly from your coding session. CX Codex +1 3,200installs ultrathink The skill displays colorful ANSI art of the word "ultrathink" in the terminal. It triggers on the word itself or via /ultrathink. CX Codex +1 1,900installs beautiful-mermaid Renders Mermaid diagrams into SVG and PNG formats using the Beautiful Mermaid library. Useful when the agent needs visual architecture diagrams, workflows, or data models. CX Codex +1 1,800installs todoist-api This skill tells the agent how to drive Todoist through the td CLI: tasks, projects, sections, labels and comments. Handy when you want your lists sorted without leaving the chat. CX Codex +1 1,700installs markdown-converter Converts documents, spreadsheets, and media files to Markdown via markitdown. Prepares data for LLM processing while preserving headings and tables. CX Codex +1 1,700installs anki-connect Connects AI agents to the Anki desktop app via the local AnkiConnect API. It helps inspect decks, search cards, and manage notes. CX Codex +1 891installs

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor