{"id":"jimmysadek-youtube-fetcher-to-markdown","name":"youtube-fetcher-to-markdown","af_score":65.0,"security_score":41.2,"reliability_score":33.8,"what_it_does":"Provides a Claude Code “skill” (and a standalone Python script) that takes a YouTube URL, fetches captions/transcript and video metadata (optionally chapters/description/duration via yt-dlp), and outputs an Obsidian-ready Markdown file with YAML frontmatter (plus optional JSON/SRT exports).","best_when":"You want local, repeatable generation of structured transcript notes for personal knowledge management, with optional enrichment when yt-dlp is installed.","avoid_when":"You need strict privacy controls, enterprise governance, or a documented, stable network/API interface rather than a local script/skill.","last_evaluated":"2026-03-30T15:38:16.220821+00:00","has_mcp":false,"has_api":false,"auth_methods":["No authentication for local skill usage (public web access to YouTube/oEmbed and caption endpoints)"],"has_free_tier":false,"known_gotchas":["Captions must exist and be accessible; some videos may disable captions or be age-restricted/private.","Optional metadata enrichment depends on yt-dlp; without it, description/chapters/duration may be missing even if transcript still works.","Duplicate detection may skip work unless --force is used.","External network availability and YouTube endpoint behavior can cause transient failures."],"error_quality":0.0}