ByteBrief
We're a portrait publication through and through. Turn your phone back and your briefing picks up right where you left it.
(We tried widescreen once. It wasn't us.)
A test using 1,872 runs shows a session-start hook raised the pooled rate for Claude Code skills from 15% to 62%. The study compared Haiku, Sonnet, and Opus models against 26 public skills. Pushy descriptions alone increased the rate by 5.2 percentage points. No near-miss request fired its target in any of the three setups.
Tap to vote and see what everyone thinks.
Summary by ByteBrief