Full Send skill
Workflow
A skill telling the agent nobody is watching. It must finish the change, prove it works, open the pull request, handle reviews and failing checks, and merge on its own. It only interrupts you if it gets stuck.
Theo's current stance
Once he and the model agree on a plan, Theo doesn't want to be pulled back just to click merge. He found OpenAI models hesitate to merge unless the skill says he explicitly allowed it.
Try it
- State in the skill that the user explicitly allows merging.
- Define proof: reproduce the bug, fix it, see the same test pass; for screen changes, run the app and look.
- List merge conditions: checks pass, review bot comments handled, no human still asking for changes.
First seen
15:48
you stop. You own the work from its current state to a merged PR. If the user did not explicitly request this in some clear way, do not assume full autonomy. If they did, everything else
Every mention
15:48
you stop. You own the work from its current state to a merged PR. If the user did not explicitly request this in some clear way, do not assume full autonomy. If they did, everything else
17:17
proof section. Proof is evidence that you observed yourself in the session. Command outputs, reproduction, screenshots. Use the most direct proof that the change allows. Reproduce the original failure, apply the fix, then watch the same reproduction pass. Run
Theo Daily is unofficial and not affiliated with Theo or t3.gg. Written by Claude Opus 5.5 from each video's transcript.