Agent Skills

All skills

receiving-code-review (obra/superpowers) vs verification-before-completion (obra/superpowers)

receiving-code-review (obra/superpowers)

23.9 / 30

SituationalSafe

receiving-code-review: stops the agent from blindly applying wrong review comments (control 3.4, skill 3.7, one-liner 4.2) but in the pricing task it stopped to ask before implementing the correct items, at about the same tokens

  • SOTAPass

verification-before-completion (obra/superpowers)

25.0 / 30

SituationalSafe

verification-before-completion: all 18 runs verify before claiming done, with or without the skill (5.0 / 5.0 / 5.0); the skill adds ~20% tokens

  • SOTAPass