{“content”:”---\nname: youtube-content\ndescription: >\n Fetch YouTube video transcripts and transform them into structured content\n (chapters, summaries, threads, blog posts). Use when the user shares a YouTube\n URL or video link, asks to summarize a video, requests a transcript, or wants\n to extract and reformat content from any YouTube video.\n---\n\n# YouTube Content Tool\n\nExtract transcripts from YouTube videos and convert them into useful formats.\n\n## Setup\n\nbash\npip install youtube-transcript-api\n\n\n## Helper Script\n\nSKILL_DIR is the directory containing this SKILL.md file. The script accepts any standard YouTube URL format, short links (youtu.be), shorts, embeds, live links, or a raw 11-character video ID.\n\nbash\n# JSON output with metadata\npython3 SKILL_DIR/scripts/fetch_transcript.py \"https://youtube.com/watch?v=VIDEO_ID\"\n\n# Plain text (good for piping into further processing)\npython3 SKILL_DIR/scripts/fetch_transcript.py \"URL\" --text-only\n\n# With timestamps\npython3 SKILL_DIR/scripts/fetch_transcript.py \"URL\" --timestamps\n\n# Specific language with fallback chain\npython3 SKILL_DIR/scripts/fetch_transcript.py \"URL\" --language tr,en\n\n\n## Output Formats\n\nAfter fetching the transcript, format it based on what the user asks for:\n\n- Chapters: Group by topic shifts, output timestamped chapter list\n- Summary: Concise 5-10 sentence overview of the entire video\n- Chapter summaries: Chapters with a short paragraph summary for each\n- Thread: Twitter/X thread format — numbered posts, each under 280 chars\n- Blog post: Full article with title, sections, and key takeaways\n- Quotes: Notable quotes with timestamps\n\n### Example — Chapters Output\n\n\n00:00 Introduction — host opens with the problem statement\n03:45 Background — prior work and why existing solutions fall short\n12:20 Core method — walkthrough of the proposed approach\n24:10 Results — benchmark comparisons and key takeaways\n31:55 Q&A — audience questions on scalability and next steps\n\n\n## Workflow\n\n1. Fetch the transcript using the helper script with --text-only --timestamps.\n2. Validate: confirm the output is non-empty and in the expected language. If empty, retry without --language to get any available transcript. If still empty, tell the user the video likely has transcripts disabled.\n3. Chunk if needed: if the transcript exceeds ~50K characters, split into overlapping chunks (~40K with 2K overlap) and summarize each chunk before merging.\n4. Transform into the requested output format. If the user did not specify a format, default to a summary.\n5. Verify: re-read the transformed output to check for coherence, correct timestamps, and completeness before presenting.\n\n## Error Handling\n\n- Transcript disabled: tell the user; suggest they check if subtitles are available on the video page.\n- Private/unavailable video: relay the error and ask the user to verify the URL.\n- No matching language: retry without --language to fetch any available transcript, then note the actual language to the user.\n- Dependency missing: run pip install youtube-transcript-api and retry.\n”}