codebase-design (mattpocock/skills) vs pdf (Anthropic)
codebase-design (mattpocock/skills)
23.6 / 30
SituationalSafe
codebase-design: gives architecture reviews the depth vocabulary and clearer structure (control 3.2, skill 3.9, one-liner 4.5) for 1.1x the tokens, but it did not find more of the planted problems than the one-liner prompt
- SOTAPass
pdf (Anthropic)
20.6 / 30
SituationalSafe
pdf skill review: no lift on our tasks, twice the cost
- SOTAPass