Babysit PR skill
Workflow
Write a 'babysit' skill, a short saved instruction file, that tells the agent to watch its pull request. It fixes failing checks, updates the change onto the latest code, handles review-bot comments, and keeps going until everything is green.
Theo's current stance
Theo uses it so that when he returns to a thread, the change is ready to merge. It's not foolproof: in one test Astra stopped monitoring too early and missed comments.
Try it
- Ask your agent to write a skill that monitors a PR's comments and checks, fixes CI failures, rebases on conflicts and fixes real findings.
- Include rules: verify each bot finding against the code, don't add new features, don't post filler comments.
- End prompts with 'babysit it until everything is green'.
- Spot-check afterward whether new comments slipped through.
First seen
37:40
…skill that I wrote that explicitly explains to the model what I want it to do. I want it to keep an eye on the PR, usually through polling or through some monitoring tech.
Every mention
14:39
This is a skill that gets invoked when I tell the model to watch or babysit a pull request. The point of this skill is to keep the model checking for updates, for new comments, and make sure by the time I go check the thread, it's good to go.
30:17
I want you to keep an eye on it. Take a look every time automated review comments come in and decide if they're worth addressing.
37:40
…skill that I wrote that explicitly explains to the model what I want it to do. I want it to keep an eye on the PR, usually through polling or through some monitoring tech.
37:52
And most importantly, I want it to address comments as they come in, in particular, from those review bots. And it should not stop monitoring until everything is a check mark in green.
Theo Daily is unofficial and not affiliated with Theo or t3.gg. Written by Claude Opus 5.5 from each video's transcript.