lecture

<Use_When>

• User provides a local video file and wants lecture notes
• User says "take notes from this lecture/video"
• User uses /lecture with a file path
• User has an MP4/MOV/MKV file to process </Use_When>

<Do_Not_Use_When>

• User has a YouTube URL (use /youtube instead)
• User wants to process an existing vault note (use /process)
• User wants audio-only transcription without note synthesis </Do_Not_Use_When>

<Execution_Policy>

• Extract first, synthesize second, integrate third
• Always check vault for existing notes on the same topic before creating
• Create note as type: lecture with processing_status: inbox
• The note is a starting point — user can /process it later for deeper engagement
• Transcription can take several minutes for long videos — inform the user </Execution_Policy>

Stage 1: EXTRACT

Parse the video file path from $ARGUMENTS. If no path provided, ask the user. Verify the file exists and is a video format (mp4, mov, mkv, avi, webm).

Run the extraction script:

SKILL_DIR="${CLAUDE_SKILL_DIR}"
LECTURE_OUTPUT="temp/lecture-extract-output.json"
uv run "$SKILL_DIR/scripts/extract_lecture.py" "VIDEO_PATH" > "$LECTURE_OUTPUT" 2>&1 &

IMPORTANT: This script takes time (several minutes for a 30-60 min video). Inform the user: "Extracting audio and transcribing — this will take a few minutes for a [duration] video."

Run it and wait for completion. Then read the output JSON.

The JSON contains:

• filename, duration, duration_seconds, width, height
• transcript.full_text, transcript.segments (with start/end times), transcript.language
• transcript.error (null if success)
• frames[] — array of {path, timestamp_seconds, timestamp} for each extracted slide
• output_dir — temp directory with extracted frames

If transcript.error is not null: inform the user and stop. Check if mlx-whisper is installed.

If transcript is very long (>80,000 chars): warn the user. Send first 60,000 chars to the agent with a note about total length.