Debrief an 84-minute YouTube panel with Claude Code
- Posted
- by Vu Ha (@vha14)
- Last checked
- Method:
- How we verify
Evidence: Described by posterThe person describes what happened in words, without screenshots or video.
Outcome
Claude Code installed yt-dlp, pulled and cleaned the captions of an 84-minute Gurley/Gerstner/Nadella talk, wrote focused debriefs, then packaged it as a reusable skill.
Agent
Prompt Recreated prompt
The source didn't share its exact prompt, so we wrote this from what it describes.
Here's a task I'd like your help with. Read it all the way through before you start. Goal: Get the transcript of a long YouTube video and give me short debriefs of the parts I care about. Check with me first: Which sections or topics do I want covered? What I'll give you: - The YouTube link - The topics I care about Rules: - Get the video's captions and clean them into readable text. - If a tool you need isn't installed, tell me and walk me through installing it. - Write a short, structured debrief for each topic I picked. - If something is missing or unclear, ask me instead of guessing. - Stick to what's said in the video. Output: A clean transcript and a concise debrief for each topic. You'll know it worked when: I understand the key points without watching the whole video. Later I may also ask you to: turn this into a reusable skill so next time I just paste a YouTube link.
Try this in:
Sends the Recreated prompt shown above. ChatGPT and Grok open with it filled in, and ChatGPT may send it straight away. Gemini opens empty, so we copy the prompt for you to paste. Every button also copies it.
The source used Claude Code, which can take actions on your computer or in a browser. These are general chat tools, so results may differ, and a normal chat may only give you a plan.
Opens in a new tab. We don't see what you send.
These links are only a shortcut. We're not affiliated with OpenAI, Google or xAI, and your results may not match the source.
Optional stronger version
Our rewrite with extra checks. The poster didn't test it.
Here's a task I'd like your help with. Read it all the way through before you start. Goal: Get the transcript of a long YouTube video and write short debriefs of the parts I care about. Quick check first: tell me if anything below is missing or unclear. Inputs (fill in or confirm): - YouTube link - Topics to cover - Debrief length - Speakers' names, if known Rules: - Use captions; clean them into readable paragraphs. - Find sections for each topic with timestamps. - Summarize each in 3–5 bullets with quotes. - Note speakers where clear. - Mark any part where captions are unclear rather than guessing words. - Give each debrief a one-line 'why it matters' summary. - Link each debrief to its timestamp. - Mark which speaker said what. - Say if the transcript has gaps. - Keep each debrief under the length I set. If you get stuck: If captions are missing, say so and suggest a transcription tool. If a login, CAPTCHA or two-step code appears, stop and ask me to handle it; never guess or store passwords. Verify before you finish: Spot-check timestamps. Output: Markdown debriefs with timestamp links. Done when: I can read the parts I care about in minutes.
Source
https://x.com/vha14/status/2014848771503620499
Related cases
- Turn one video script into a newsletter, titles, thread and description with Claude Code subagentsRecreated promptEvidence: Screenshots or logs
From one long-form video script, an orchestrator in Claude Code calls subagents that write a newsletter, generate titles, create thumbnails, write a thread and draft the YouTube description.
Claude Code · Content · Source date:
- Find repurposable clips in years of YouTube videos with Claude CoworkImproved promptEvidence: Screenshots or logsPartial
Given brand context, timestamped transcripts, example clips and performance data, Claude Cowork analyzed the content well and surfaced topics and hooks, saving hours of watching; but the clips it cut started mid-thought or lacked context or conclusions, even after several re-prompts.
Claude Cowork · Content · Source date:
- Make years of calls, podcasts and posts searchable with Claude CodeRecreated promptEvidence: Described by poster
Claude Code organized years of calls, podcasts, tweets and presentations into a searchable database connected to AI, with a daily job that adds new content; asked for a masterclass outline, it drew on 224 chunks from 78 sources.
Claude Code · Content · Source date: