$npx skillfedfor your agent

baoyu-youtube-transcript

Fetch transcripts and captions from YouTube videos in markdown or SRT format, with optional timestamps, chapter segmentation, and speaker metadata. The skill caches raw data for fast re-formatting and automatically falls back to yt-dlp when direct API access is blocked.

baoyu-youtube-transcript downloads YouTube video transcripts with timestamps, supporting multiple languages and output formats.

AI-generated summary based on this skill's SKILL.md

24,241 2,697 MITupdated by JimLiu

Decision gist · record as of 2026-07-04

baoyu-youtube-transcript downloads YouTube video transcripts with timestamps, supporting multiple languages and output formats. Fetch transcripts and captions from YouTube videos in markdown or SRT format, with optional timestamps, chapter segmentation, and speaker metadata. The skill caches raw data for fast re-formatting and automatically falls back to yt-dlp when direct API access is blocked.

manual: git clone https://github.com/JimLiu/baoyu-skills → cp -r baoyu-skills/skills/baoyu-youtube-transcript ~/.claude/skills/baoyu-youtube-transcript
skills/baoyu-youtube-transcript/SKILL.md · version ef54b852

Use it when

  • baoyu-youtube-transcript converts YouTube captions to SRT, markdown, and text formats.
  • Yes, baoyu-youtube-transcript supports extracting captions from YouTube with timestamps included.

Verify before relying

Read SKILL.md below before installing (9 files). Open directory: indexed for reading, not audited.

Same gist for agents: .md · .json

Install

JimLiu/baoyu-skills/baoyu-youtube-transcript · repository language: TypeScript

Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.

Frequently asked questions

AI-generated answers based on this skill's SKILL.md and metadata

How do I download a YouTube transcript?

baoyu-youtube-transcript lets you download YouTube transcripts directly by providing a video URL. The skill extracts the full transcript with optional timestamps and can output it in multiple formats including markdown, SRT, and plain text. It automatically handles cases where direct API access is blocked by falling back to yt-dlp.

What formats can baoyu-youtube-transcript convert captions to?

baoyu-youtube-transcript converts YouTube captions to SRT, markdown, and text formats. You can choose your preferred output format when downloading, making it easy to use transcripts in video editors, documentation, or other applications that support these standard formats.

Can I extract YouTube subtitles with timestamps?

Yes, baoyu-youtube-transcript supports extracting captions from YouTube with timestamps included. The skill preserves timing information from the original captions, allowing you to maintain synchronization between text and video content in your downloaded transcript files.

Does baoyu-youtube-transcript support multiple languages?

baoyu-youtube-transcript retrieves transcripts in multiple languages with translation support. If a video has captions available in different languages, you can fetch transcripts in your preferred language, and the skill can help translate content across language pairs.

Can I get YouTube video cover images and metadata?

baoyu-youtube-transcript retrieves YouTube video cover images (thumbnails) and metadata alongside transcripts. This includes video information that helps you organize and document your downloaded content alongside the transcript data.

Does baoyu-youtube-transcript identify speakers and chapters?

baoyu-youtube-transcript can identify speakers and segment transcripts by chapters when that information is available in the video. This helps you organize longer videos by topic and understand who is speaking at each point in the transcript.

SKILL.md

Rendered from the published skill. Quoted content, verbatim.

YouTube Transcript

Downloads transcripts (subtitles/captions) from YouTube videos. Works with both manually created and auto-generated transcripts. No API key or browser required — uses YouTube's InnerTube API directly and automatically falls back to yt-dlp when YouTube blocks the direct API path.

Fetches video metadata and cover image on first run, caches raw data for fast re-formatting.

Script Directory

Scripts in scripts/ subdirectory. {baseDir} = this SKILL.md's directory path. Resolve ${BUN_X}

(truncated - see the full file via the links below)

File tree — 9 files
skills/baoyu-youtube-transcript/SKILL.md
skills/baoyu-youtube-transcript/prompts/speaker-transcript.md
skills/baoyu-youtube-transcript/scripts/main.test.ts
skills/baoyu-youtube-transcript/scripts/main.ts
skills/baoyu-youtube-transcript/scripts/shared.ts
skills/baoyu-youtube-transcript/scripts/storage.ts
skills/baoyu-youtube-transcript/scripts/transcript.ts
skills/baoyu-youtube-transcript/scripts/types.ts
skills/baoyu-youtube-transcript/scripts/youtube.ts

Let your AI agent find skills like this

Example. Real query, live index.

You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.

wish › “Download and extract YouTube video transcripts with timestamps”

Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →

Related skills

Youtube Transcript
by glebis · glebis/claude-skills

Pull transcripts directly from YouTube videos along with metadata like title, channel, and upload date, then save everything as a formatted Markdown file to your Obsidian vault. The skill organizes transcript segments by video chapters and timestamps, making it easy to reference specific moments. Requires subtitles to be available on the video.

no license declared → metadata onlyupdated Jul 2026
★ 334repo stars
Youtube Transcript
by intellectronica · intellectronica/agent-skills

Retrieve full text transcripts from YouTube videos by providing a URL or video ID. The skill fetches available captions—whether manually added or auto-generated—and outputs them as plain text, optionally formatted with timestamps for easy reference.

CC0-1.0updated Apr 2026
★ 279repo stars
baoyu-url-to-markdown
by JimLiu · JimLiu/baoyu-skills

baoyu-url-to-markdown fetches URLs using Chrome DevTools Protocol and transforms them into clean markdown. It includes specialized adapters for X/Twitter, YouTube transcripts, and Hacker News, plus a generic fallback for any page. The skill supports interaction wait modes for login and CAPTCHA handling, optional media download, and customizable output directories through preference files.

MITupdated Jul 2026
★ 24,241repo stars
baoyu-translate
by JimLiu · JimLiu/baoyu-skills

baoyu-translate offers three translation modes—quick for speed, normal for balanced analysis-informed work, and refined for polished publication-quality results. Configure target language, audience, style, and custom glossaries via preferences, with built-in support for chunking longer texts and upgrading between modes mid-workflow.

MITupdated Jul 2026
★ 24,241repo stars
youtube-watcher
by gooseworks-ai · gooseworks-ai/goose-skills

YouTube Watcher pulls transcripts from YouTube videos, letting you summarize content, answer questions about what's said, and extract specific information. It works with videos that have captions or auto-generated subtitles, requiring yt-dlp to be installed.

MITupdated Jul 2026
★ 1,062repo stars
faster-whisper
by ThePlasmak · ThePlasmak/faster-whisper

Faster-whisper delivers rapid, offline speech-to-text transcription using CTranslate2, achieving 4-6x speed over OpenAI Whisper while maintaining identical accuracy. Generate subtitles in multiple formats (SRT, VTT, TTML, CSV), identify speakers, process batches with ETA, search transcripts, and detect chapters—all without API dependencies.

MITupdated Feb 2026
★ 9repo stars

More skills Youtube Content (Apache-2.0) · youtube-content (MIT) · youtube-content (MIT) · Transcription Automation (MIT) · youtube-transcript (MIT) · Youtube Transcript Cn (unlicensed)

Tags
video-metadata-extractionsubtitle-format-conversionmultilingual-transcriptioncaption-caching-systemspeaker-diarizationchapter-segmentationtimestamp-alignmentfallback-retry-logic