QUICK ANSWER

Record your screen while explaining what you want changed, then give the Clipy link to Cascade. Point to the button, show the bug, or walk through the flow as you would with a teammate. Ask Cascade to use that recording to make the change, then show you the result.

Use this Clipy recording to make the changes I described: [link].

How do you give Cascade a recording?

Paste the normal Clipy recording link into Cascade and say what you want help with. You do not need to edit the URL or configure a server to try a public recording.

Read this Clipy recording and help me with the change I described: [paste the recording link]. Tell me what you understood before editing.

What if Clipy is not connected yet?

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.

How do you ask about your own recording library?

Ask the agent to connect your Clipy library when you want to search private recordings. Follow the sign-in prompt if needed. A public recording link can be read without library access; private material still requires the right account.

Connect my Clipy library, then find the recording where we discussed the webhook retry logic.

The connection reference is available for the agent to use when needed.

What should you ask the agent to do?

Read this Clipy recording. List the changes I asked for, then implement the agreed changes. Verify them in the app and attach Clipy proof to the GitHub PR.

Name anything that must stay unchanged. That keeps a focused request from turning into a redesign. The Clipy skill supplies the recording workflow; your prompt supplies the goal.

Can the team reuse the same request?

Yes. Make “attach Clipy proof to the PR” part of your normal review habit. Ask the agent to save that convention in your project instructions if you want it reused. You do not need to learn a separate configuration format for each editor.

When showing beats typing

Not everything deserves a recording. A stack trace is already text and pasting it is faster.

Recording wins when the bug has a when or a which:

  • Timing. A spinner that never resolves, a toast that vanishes too fast, a race that only shows up if you click twice quickly. Prose destroys timing.
  • Deixis. Any bug you would explain by pointing. "This one, not that one" is unactionable as text and trivial as a frame plus a coordinate.
  • Visual judgement. Spacing, contrast, alignment. You cannot describe a four pixel misalignment faster than you can show it.
  • Long flows. Six steps with state built up along the way. Writing them out is where reproduction steps quietly go wrong.

How do you get proof back in the PR?

Verify this change in the running app. Record the verification with Clipy and attach the Clipy proof link to this GitHub PR: [PR link]. Show the problem before the fix and the result after it.

The agent handles recording and sharing. Open the proof link in the PR to see what it actually checked. Ask it to include the important screens and a reload when the change should persist.

A recording shows the run that was captured, not every possible case. If the agent cannot record in its current environment or cannot update the PR, it should say so. A walkthrough assembled from screenshots should be labeled as such, not presented as continuous screen capture.

What if the agent gets stuck?

Ask it what it could read or record and what is missing. It may need the Clipy skill, permission to open the link, a sign-in, or access to the app being tested. Let it use the troubleshooting guide instead of asking you to debug commands.

If the recording is still processing, let the agent wait for the available context. If a private link is inaccessible, connect the right account. Do not make private work public just to bypass an access problem.