Agent Skills

All skills

caveman-review (JuliusBrussee/caveman) vs internal-comms (Anthropic)

caveman-review (JuliusBrussee/caveman)

25.1 / 30

SituationalSafe

caveman-review: shifts code reviews toward short per-finding lines (control 3.3, skill 4.2, one-liner 4.8) at the same tokens, but the skill's own L<line> line format was followed in only some runs; a one-sentence prompt of the format scores higher

  • SOTAPass

internal-comms (Anthropic)

26.0 / 30

SituationalSafe

internal-comms: the skill writes updates in its own compact 3P format, but all three groups pass our rules at 5.0

  • SOTAPass