List your company

Software Engineering Skill Evaluation on SWE-Skills-Bench bash-defensive-patterns

50Pass RateVanilla LLM
29.234.64045.4Jun 15, 2026

Evaluation results

MethodLinks
Vanilla LLMSetting=Vanilla baseline2026.0650——
S2LSetting=Our method2026.0640-26.6-0.38
Full Skill TextSetting=Full Skill Text prompting2026.063012.95-1.54