List every course you're enrolled in on learn.deeplearning.ai.

Specializations are flattened into their constituent courses. Each item has slug, name, type ("course"|"short_course"), progress_percent, and (for courses inside a specialization) the parent specialization info.

Use the returned slug when calling list_lessons or get_lesson_transcript.

List lessons for one course, grouped by module in playback order.

Args: course_slug: from list_enrolled_courses, e.g. "agentic-ai".

Returns a dict with course_name, total_duration_seconds, and modules — each module has a name and a lessons array of {slug, index, name, type, video_id, duration_seconds}. Pass the lesson slug (not the numeric video_id) to get_lesson_transcript.

Fetch the full transcript for one video lesson.

Args: course_slug: from list_enrolled_courses. lesson_slug: from list_lessons (the short lesson id like "pu5xbv"). format: "plain" gives one flowing text block; "timestamped" gives lines prefixed with [M:SS] markers.

Returns {course_name, lesson_name, duration_seconds, transcript}. Only video lessons have transcripts; other lesson types raise an error.

Screenshot a single video frame from a lesson at the given timestamp.

Args: course_slug: from list_enrolled_courses. lesson_slug: from list_lessons (the short id like "pu5xbv"). timestamp_seconds: where in the video to grab the frame. quality: "low" 640x360 (default, fast); "high" full HD (slower). save_path: if set, write the JPEG to this path ( and $VARS expanded; parent dirs auto-created) so downstream tools can reference it. The absolute path is included in the response. include_image: default True. Set False to skip the inline image (useful with save_path when the caller only needs the file).

Returns a JSON summary text block, plus a caption + inline image (unless include_image=False). Requires ffmpeg on PATH.

Auto-detect slide changes in a lesson video and return one frame per slide.

Args: course_slug: from list_enrolled_courses. lesson_slug: from list_lessons. threshold: 0..1 scene-change sensitivity. 0.3 catches slide changes; raise to 0.5+ to only cut on very distinct visuals. max_frames: cap total frames returned. Prevents very long lectures from swamping the response. min_gap_seconds: skip candidates that fall within this many seconds of the previously kept frame — suppresses near-duplicates from small on-camera movements while the slide hasn't changed. 0 disables the dedup. save_dir: if set, write each JPEG to this directory (created if missing). Filenames are "{course_slug}--{lesson_slug}--{index:03d}-{seconds}s.jpg". Absolute saved paths are included in the JSON summary so downstream tools can reference them. include_images: default True. Set False to get only timestamps + saved paths (structured data), skipping inline image content — useful for building a chapter index without image tokens.

Returns a JSON summary block first (course/lesson/frame list with timestamps and saved paths), then per-frame caption + inline image unless include_images=False. Requires ffmpeg.

Health check.