// Extract the transcript from a YouTube video by URL or video ID. Use when the user shares a YouTube link and wants the transcript, captions, or text content of the video. Falls back automatically if the requested language isn't available.
| name | get-youtube-transcript |
| description | Extract the transcript from a YouTube video by URL or video ID. Use when the user shares a YouTube link and wants the transcript, captions, or text content of the video. Falls back automatically if the requested language isn't available. |
| allowed-tools | ["Bash"] |
| user-invocable | true |
| argument-hint | <youtube-url-or-video-id> |
Extract a full transcript from any YouTube video using the local youtube-transcript-api (no rate limits, no API key required).
| Source | Location | Read | Write |
|---|---|---|---|
| Script | scripts/utilities/yt-transcript.sh | ✓ | - |
| Venv | scripts/utilities/yt_transcript_venv/ | ✓ | - |
| YouTube | External (via youtube-transcript-api) | ✓ | - |
Run the wrapper script with the URL or video ID the user provided:
scripts/utilities/yt-transcript.sh "<url-or-id>"
Options:
-l <lang> — language code (default: en). If user specifies a language, pass it.-f text — plain text output (default, best for reading)-f json — structured output with timestamps (use when user needs timestamps)If the script fails:
-l flag (auto-selects any available language)Return the full transcript text to the user. If it's long (>500 lines), summarize what the video covers first, then provide the full text.
User: "get me the transcript of https://youtu.be/abc123"
scripts/utilities/yt-transcript.sh "https://youtu.be/abc123"
youtube-transcript-api Python package — works locally with no quotaRun a full coherence sweep across the Brain Dependency Graph - computes staleness, lifecycle transitions, structural health, and generates a report
Compute lifecycle scores for all insight and framework notes - detect which notes are crystallizing or becoming generative
Autonomous research pipeline - discover, extract, and integrate cutting-edge insights into knowledge base
Detect productive contradictions between notes - high semantic similarity with opposing conclusions that represent synthesis opportunities
Autonomous perception layer - scans KB for new notes matching domain watch configs, checks gap resonance with the Thinking Registry, probes external signals via web search, and auto-activates HIGH/MEDIUM signals into the Thinking Registry for the incubation loop.
Extract insights from external documents (research papers, books, articles). Spawns document-insight-extractor subagent. Requires session name.