Long videos hold useful insight buried under filler. This agent takes any YouTube URL, transcribes it when needed, and reads the whole thing so you don't have to sit through it.
sonnet3 daysYouTube Data APIWhisperClaudeNotion
Claude
74ROI
88Scale
$1.5k92Saved
ROI for
README.md
Why this subagent
Long videos hold useful insight buried under filler. This agent takes any YouTube URL, transcribes it when needed, and reads the whole thing so you don't have to sit through it.
It returns a single page: a few-bullet takeaway up top, timestamped sections so you can jump to the part that matters, and one quotable line. Each summary files itself in Notion under the channel, turning an hour of video into a scannable one-pager.
How it runs
Used at step 01 to kick off the pipeline.
Write
Used at step 01 to kick off the pipeline.
WebFetch
Used at step 01 to kick off the pipeline.
WebSearch
Used at step 01 to kick off the pipeline.
Read the full transcript and extract the main argument, key points, and any concrete examples or numbers.
pending
Write a one-page summary with a short takeaway block, timestamped sections, and a quotable line.
pending
Save the one-pager to Notion under the channel name with the source link attached.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
From a video transcript, produce a one-page summary with a 3-bullet takeaway, timestamped sections, and one pull quote; output as structured markdown.
Unlock the rest
The full agent definition, install snippet, and starter task are gated for community members.
Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.