Skill not invoked — Claude summarizes without fetching

Say 'fetch the transcript using youtube-fetcher-to-markdown' explicitly.

SKILL.md frontmatter wrong

Re-clone; description drives activation.

freemcplab / Directory / Playground / youtube-fetcher-to-markdown

← All servers ↗ GitHub

● Community JimmySadek ⚡ Instant

youtube-fetcher-to-markdown

Name: youtube-fetcher-to-markdown (Claude Skill)
Author: JimmySadek

by JimmySadek · JimmySadek/youtube-fetcher-to-markdown

Turn any YouTube URL into a queryable Markdown note — YAML frontmatter, chapters, full transcript, Obsidian-ready.

JimmySadek/youtube-fetcher-to-markdown converts YouTube videos into structured Markdown in ~/yt_transcripts/. Accepts URLs in any format. Options: --timestamps (temporal markers), --lang (caption language), --format (json / srt), --source (project tag). Output includes YAML frontmatter (title, channel, id, date, duration, language), full description with links, chapter timestamps, and transcript. Frontmatter lets Obsidian Dataview query your entire transcript library.

▶ Watch demo 📦 Install 💡 Use Cases

Why use it

Key features

Any YouTube URL format accepted (short, embed, playlist, watch)
YAML frontmatter for Obsidian Dataview querying across transcripts
Optional timestamps, language choice, JSON/SRT output
Chapter-aware markdown when the video has chapters
File naming with date + slug + video ID for stable sorting

Live Demo

What it looks like in practice

youtube-fetcher-to-markdown-skill.replay ▶ ready

0/0

Install

Author repository · Claude Skills documentation

Use Cases

Real-world ways to use youtube-fetcher-to-markdown

Archive a YouTube lecture series as a searchable Obsidian vault

👤 Self-learners and researchers ⏱ ~20 min beginner

When to use: You're studying from YouTube and want to search across 20+ videos later.

Flow

Fetch a playlist's transcripts

youtube-fetcher-to-markdown — fetch every video in playlist <URL>, include timestamps, source=cs-course.✓ Copied

→ ~/yt_transcripts/ fills with per-video markdown files, all tagged source: cs-course
Query via Dataview

In Obsidian, write a Dataview query listing all cs-course videos sorted by upload date.✓ Copied

→ Dataview returns the set because the frontmatter is consistent

Outcome: A queryable knowledge base you can grep, tag, and cross-link.

Pitfalls

Some videos have no captions and the transcript is empty — Check the skill's log; fall back to Whisper locally for those

Combine with: filesystem

Turn a YouTube talk into a blog post draft

👤 Creators repurposing content ⏱ ~25 min beginner

When to use: Your talk went up; you want a written version for SEO.

Flow

Fetch the transcript

youtube-fetcher-to-markdown <URL> with chapters and timestamps.✓ Copied

→ Markdown with chapter-delimited sections
Rewrite as blog

Now draft a blog post from this transcript.✓ Copied

→ Structured post using the chapters as section anchors

Outcome: Draft-quality blog post based on your own talk.

Combine with: seo-blog-writer-claude-skill

Combinations

Pair with other MCPs for X10 leverage

youtube-fetcher-to-markdown-skill + filesystem

Route transcripts into a specific Obsidian vault folder with custom naming

Save fetched transcripts to ~/obsidian/sources/youtube/.✓ Copied

youtube-fetcher-to-markdown-skill + seo-blog-writer-claude-skill

Fetch transcript → generate blog post in one chain

Fetch the transcript for <URL>, then seo-blog-writer target keyword 'X'.✓ Copied

youtube-fetcher-to-markdown-skill + claude-content-writer-skill

Turn transcripts into newsletters in your brand voice

Fetch transcript, then claude-content-writer newsletter version in my voice profile.✓ Copied

Tools

What this MCP exposes

Tool	Inputs	When to call
fetch_single	URL + options (timestamps, lang, format, source)	One video at a time
fetch_playlist	playlist URL + options	Bulk archiving
export_json	URL	You want the data in a non-markdown pipeline

Cost & Limits

What this costs to run

API quota: YouTube has no explicit scrape quota for captions but be reasonable
Tokens per call: Proportional to video length
Monetary: Free — skills are local files
Tip: For very long videos, use JSON export + snippet extraction instead of loading full transcripts into context.

Security

Permissions, secrets, blast radius

Credential storage: No credentials — pure prompts

Data egress: Fetches from YouTube. No data leaves your machine afterward.

Respect YouTube's ToS and creators' rights when redistributing transcripts.
Don't rely on auto-captions as ground truth for quotes — they have errors.

Troubleshooting

Common errors and fixes

Wrong trigger keywords — transcript has no timestamps

Pass --timestamps explicitly in the prompt.

Alternatives