RonanCodes/ingest-youtube
.claude/skills/ingest-youtube/SKILL.md
Extract transcript from YouTube videos for wiki ingestion. Lazy-installs yt-dlp on first use.
$ install --global
skillsauthnpx skillsauth add RonanCodes/llm-wiki ingest-youtubeInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 24, 2026, 9:03 PM1.8s1 file scanned
SKILL.md
- name:
- ingest-youtube
- description:
- Extract transcript from YouTube videos for wiki ingestion. Lazy-installs yt-dlp on first use.
- user-invocable:
- false
- allowed-tools:
- Bash(which *) Bash(brew *) Bash(yt-dlp *) Bash(sed *) Bash(awk *) Read
Ingest YouTube Video
Extract auto-generated or manual subtitles from a YouTube video.
Dependency Check
which yt-dlp >/dev/null 2>&1 || {
echo "Installing yt-dlp for YouTube transcript support..."
brew install yt-dlp
}
Extraction Method
- Extract video metadata:
yt-dlp --dump-json --skip-download "<url>" 2>/dev/null | python3 -c "
import json, sys
data = json.load(sys.stdin)
print(f'Title: {data.get(\"title\", \"Unknown\")}')
print(f'Channel: {data.get(\"channel\", \"Unknown\")}')
print(f'Upload Date: {data.get(\"upload_date\", \"Unknown\")}')
print(f'Duration: {data.get(\"duration_string\", \"Unknown\")}')
print(f'Description: {data.get(\"description\", \"\")[:500]}')
"
- Download subtitles:
VIDEO_ID="<extracted-id>"
yt-dlp --write-auto-sub --sub-lang en --skip-download --sub-format srt \
-o "/tmp/yt-ingest-${VIDEO_ID}" "<url>"
- Clean SRT to readable text:
sed '/^[0-9]*$/d; /^$/d; /-->/d' "/tmp/yt-ingest-${VIDEO_ID}.en.srt" \
| awk '!seen[$0]++' \
> "/tmp/yt-ingest-${VIDEO_ID}.txt"
- Read the cleaned transcript and pass to ingest router.
Post-Extraction
- Save transcript to vault's
raw/<video-slug>-transcript.mdwith YAML header:
---
source-url: <youtube-url>
title: <video-title>
author: <channel-name>
date-fetched: <today>
source-type: video
---
- Set
source-type: videoin the source-note frontmatter - Note in source-note that this is from auto-generated subtitles (may have transcription errors)
Fallback
If no English subtitles available, try: --sub-lang en,en-US,en-GB
If still none, list available: yt-dlp --list-subs --skip-download "<url>"
Related Skills
RonanCodes/yt-transcript
data-ai
VerifiedTrustedCommunity
Extract transcript from a YouTube video as clean readable text. Use when user shares a youtube.com or youtu.be link and wants the transcript, content summary, or to read what was said.
1SKILL.mdUpdated Apr 17, 2026
RonanCodes/wiki-templates
development
VerifiedTrustedCommunity
Page type templates and frontmatter conventions for LLM Wiki pages. Reference skill loaded by ingest, query, and lint skills to ensure consistent wiki structure.
1SKILL.mdUpdated Apr 17, 2026
RonanCodes/vault-status
testing
VerifiedTrustedCommunity
Show status of all LLM Wiki vaults — page counts, source counts, last activity, and git status. Use when user wants to see vault status, list vaults, or check wiki health.
1SKILL.mdUpdated Apr 17, 2026
RonanCodes/vault-import
documentation
VerifiedTrustedCommunity
Import an existing Obsidian vault, markdown folder, or git repo as an llm-wiki vault. Moves content into vaults/, adds missing structure (index, log, CLAUDE.md, frontmatter). Use when user wants to import, adopt, migrate, or bring in an existing knowledge base.
1SKILL.mdUpdated Apr 17, 2026