github:jasonsilberman/agent-browser-loop · first seen 2026-10-31 · source · badge
Use when an agent must drive a live browser session in a back-and-forth loop (state -> explicit actions -> state) for UI validation, reproducible QA, or debugging UI behavior. Prefer this over one-shot CLI usage when an agent needs inspectable, stepwise control.
Listed, not yet scored. This skill has no public model test yet. It is in the scoring queue; submitted skills go first, then the most-installed.