Software Engineering Skill Evaluation on SWE-Skills-Bench bazel-build-optimization
10Pass RateVanilla LLM
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Vanilla LLMSetting=Vanilla baseline2026.06 | 10 | — | — | |
| Full Skill TextSetting=Full Skill Text prompting2026.06 | 0 | -0.0391 | -2.56 | |
| S2LSetting=Our method2026.06 | 0 | -0.2476 | -0.4 |