Agent Skills

All skills

improve-codebase-architecture (mattpocock/skills) vs diagnosing-bugs (Matt Pocock)

improve-codebase-architecture (mattpocock/skills)

23.0 / 30

SituationalSafe

improve-codebase-architecture: 4.1/5 against 3.2 plain, but a one-sentence prompt reaches 3.9 for 58% of the skill's tokens

  • SOTAPass

diagnosing-bugs (Matt Pocock)

22.9 / 30

SituationalSafe

mattpocock diagnosing-bugs: a one-sentence version of its 'build the feedback loop first' rule did as well as the full skill, at 0.95x the cost of the skill

  • SOTAPass