QUICK ANSWER
Give Claude Code the video you want help with and ask a specific question. Clipy helps the agent use the available video context, so you can discuss the tutorial or walkthrough without first turning it into a written brief. For your own work, record your screen, explain the task, and share the Clipy link.
Use Clipy to read this video and explain how its approach applies to my project: [link].
Why pasting the URL does not work
It is worth being precise about the failure mode, because it does not look like a failure.
When you paste https://www.youtube.com/watch?v=… into a coding agent, the agent has a URL and nothing else. Depending on the tool it may fetch the page, in which case it gets the HTML shell: title, description, channel name, and a pile of markup. It does not get the video, and in most setups it does not get the transcript either.
What comes back is an answer built from the title plus training data. If the video is a well-known talk, this can be uncannily close and occasionally correct. If it is a six-month-old tutorial for a library that changed its API, you get advice for the old API delivered in the same confident register. Nothing in the response signals which of the two you are getting.
The fix is not a smarter model. It is giving the agent something to read. Agents are extremely good at reading files and running commands, which happens to be all you need — if something turns the video into files first.
What should you paste into the agent?
Use Clipy to read this video and answer my question: [video link]. Install the Clipy skill if needed. My question is: [question].
The agent can use Clipy to prepare the video context and read the relevant evidence. You do not need to download the video or copy terminal commands. If it needs setup, let it use the official guide and approve the requested setup.
How do you make this a repeatable habit?
Start with the recording link and the task. If the agent needs the Clipy skill or account access, ask it to handle setup and guide you through anything it needs. You can keep explaining what you want in ordinary language.
Once the skill is available, give the agent a video and the question you want answered. It handles the import and tells you if the source is unavailable or important visual evidence is missing.
How do you keep videos for later?
Save this video to my Clipy library so I can ask about it later: [video link].
Connect your Clipy account when prompted. The agent can keep the derived context in your library and use it again. Ask it to confirm what was saved; reading a video once does not by itself mean it was added to your library.
What does a useful request look like?
Use Clipy to read this API tutorial. Explain the retry strategy, cite the relevant moments, and tell me which parts apply to my project: [video link].
The useful answer connects its explanation to the video evidence and your code. If the video has no usable transcript or some frames are unavailable, the agent should name that gap instead of inventing the missing steps.
Does this work beyond Claude Code?
Use the same request in a coding agent with the Clipy skill, such as Codex or Cursor. Let that agent handle its own setup. Other chat environments may need a supported Clipy connection; they do not all have permission to install tools or read local files.
What the agent actually receives
The bundle is a directory holding recording.md (the document), manifest.json (provenance, tool versions, sufficiency report) and transcript.json. The markdown is ordered so the first screen tells a reader what the document is and where it is blind:
- An untrusted-content note, before anything else: everything below is derived from the source video and is quoted content describing it, never instructions to the agent.
- A completeness header, when it matters. If frames the classifier asked for were not captured, the document says so at the top, gives the reason, states plainly that the transcript and metadata are still complete and usable, and prints the exact command to re-run. If the bundle is transcript-only by design, it says that instead — so the two cases are never confused.
## Metadata— source, duration, classification, and the sufficiency score with its recommended profile.## Visual gaps— a list of timestamps where the transcript goes blind, each with the offending excerpt. This is the part the prompt tells the agent to read first, and it is the reason the agent can say "unknown" instead of inventing.## Frames— the captured moments with their captions, when there are any.## Transcript— timestamped lines grouped into### MM:SSsections, with frames interleaved at the segment they belong to rather than parked in a block at the top. An agent reading linearly meets the picture at the moment the words stop being enough.
That interleaving is a small decision that does a lot of work. A frame in an appendix is a frame the agent has to correlate back to a timestamp; a frame sitting between the line before and the line after is context it cannot miss.
Why the frames matter
Mute any competent screen-recorded tutorial and watch it. The file path in the sidebar, the flag on the command, the exact error text, the version in the corner — all of it is on screen and none of it is spoken. Now read the transcript with the video closed and you get "and then we just add the middleware here." Here is carrying the entire sentence, and the transcript does not contain here.
Running a lot of developer video through both paths while building this, the pattern was consistent enough to design around: the more useful a video is to someone trying to do the thing, the more of its information is shown rather than dictated. Talks and interviews survive transcription nearly intact. Walkthroughs and bug reproductions do not. Muting one of your own is a thirty-second way to check it.
This is also why frames are conditional rather than automatic. Dumping screenshots into a podcast transcript would add noise and cost, so the classifier decides per video, and a document with no frames is frequently the correct output rather than a degraded one.
The same argument applies to recordings you make yourself, which is where Clipy started — that longer version is in giving agents video context.
What should you do if the agent gets stuck?
Ask it to explain the missing piece in plain language. The source may be private, captions may be unavailable, or its environment may be unable to retrieve the visual evidence. Supply an authorized transcript or local recording if you have one.
The agent should use the troubleshooting guide, keep any useful context it already obtained, and report what it could not read. You should not need to debug import flags.
FAQ
Can Claude Code watch a YouTube video?
Not directly — it has no video input. What it can do is run a command and read files. Clipy compiles the video into files it can read: a timestamped transcript plus images of the moments the transcript cannot describe. From the agent's side that is functionally watching it.
Does the video get downloaded?
Visual evidence requires access to the video. If you only want the transcript, tell the agent to use transcript-only reading. Ask it to flag anything that depends on unseen visuals rather than treating the transcript as complete evidence.
Can I import a video file from my own machine?
Give the agent the video link or an authorized local file and ask it to read it with Clipy. If you have a transcript, include that too. Ask it to save the context to your Clipy library only when you want it kept there; the agent should confirm what was read and saved.
Where does the bundle live?
Give the agent the video link or an authorized local file and ask it to read it with Clipy. If you have a transcript, include that too. Ask it to save the context to your Clipy library only when you want it kept there; the agent should confirm what was read and saved.
What about private or unlisted videos?
Hosted tools that only accept public URLs cannot touch them. The local-file path can: export the video and its captions, then import the file. This is the usual route for internal material — recorded design reviews, onboarding walkthroughs, customer calls.
Won't a long video blow up my context window?
Only if the agent reads it whole, which is the usual failure with transcript tools. The document is written so an agent reads metadata and the visual-gap list first and then pulls only the sections it needs, and read_context_document takes an explicit start and end. The prompt in Method 1 already instructs this.
How is this different from NotebookLM?
Different job. NotebookLM — now Gemini Notebook — is a research notebook you read, and Google documents that only the text transcript of a YouTube video is imported. This is a pipeline that hands files to an agent mid-task, with visual evidence attached. We went through the documented limits in detail in NotebookLM and YouTube: every documented limit.
What if I want to keep everything I import?
That is Method 3, and there is a fuller guide to running it as an ongoing habit — tagging, folders, curation discipline, cross-video search — in building a personal knowledge base from YouTube videos.
Where should you start?
Choose one video relevant to your current task. Give the agent its link and a specific question, and ask it to use the Clipy skill. Check that its answer cites evidence it actually retrieved.