Who it is forA developer who has an agent reviewing a capture and needs it to inspect a specific second without scrubbing through the whole video.
The problemA contact sheet shows only keyframes, so the detail of a short interaction can be missed.
The outcomeThe agent pulls a dense set of frames around the moment it cares about and reports what changed.
What you need first
- An Apple silicon Mac running macOS 26 or later (or Windows 10 2004 or later, x64, preview build)
- Screen & System Audio Recording, Microphone, and Accessibility permissions granted during onboarding
- Claude Code, Codex, or another agent that can read the pasted contact sheet and summary.md
- For the source-build steps: a Rust toolchain with cargo
Steps
- Install the agent skill with
bunx skills add kitlangton/scrawl. - Run
scrawl inspect --marksto list the numbered marks in a capture. (inferred, check the README) - Run
scrawl zoom --at 0:12for a timestamp, orscrawl zoom --at "a phrase you said"for a spoken phrase. (inferred, check the README) - Run
scrawl frameson a time range to extract the frames for a closer look. (inferred, check the README)
Prompt for your agent
Use the scrawl command on the capture at <bundle-path>. Run `scrawl inspect --marks`, then `scrawl zoom --at <timestamp>` for the first mark, and report what happens in those frames. Verify that the reported timestamp matches the summary.md timeline.
Caveat. The zoom and frames commands work on bundles that Scrawl has already made, so you must record at least one capture first.
Get 5 new use cases every morning. Free, one short email, 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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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