Who it is forA founder or speaker preparing for a demo day, investor meeting or conference talk who wants evidence about how they delivered the material.
The problemPractising in front of a mirror gives no measurable feedback on pacing, filler words or where the talk drifts.
The outcomeA report based on the transcript and audio that points to the sections where you rambled and the words you overused.
What you need first
- An Apple Silicon Mac running macOS 26 or newer
- Claude Code, Codex or another AI agent harness
- Permission to record the screen, microphone and optional camera when the app asks
- Accessibility permission only if you want ⌥⇧V to paste the prompt for you
Steps
- Press ⌥⇧S to record the practice pitch, with the camera enabled in the menu bar recording options.
- Press ⌥⇧S again to finish the recording.
- Wait for the automatic transcription to complete.
- Ask your agent how your pacing was and where you rambled, and which filler words came up most.
- Keep your best take if you want, and ask the agent to keep only that take.
Prompt for your agent
Using the Yap CLI and skill, read the transcript and audio of the practice recording <recording ID>. Report the pacing, the filler words with their timestamps and any sections where the pitch drifted. Verify each timestamp by checking the transcript word timings.
Caveat. The feedback comes from the transcript and audio measurements, so it describes what was said and how it sounded rather than how it looked on camera.
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page