Megadose AI progress, ranked and analyzed.

SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries

· HF Daily Papers ·
The paper claims agents can shrink large skill libraries without breaking the executable contracts those skills rely on.

SkillZip compresses skills as section-level execution graphs, replacing repeated valid patterns with reversible macros. The method is designed to preserve boundary signatures, dependencies, verifier paths, and the ability to expand back to source-level routines. At inference time, it loads a compact dependency-closed context and expands macros only when needed. The authors report up to a 12.2-point gain over the strongest baseline, with 3.46x compression and high dependency and verifier preservation. HF Daily Papers' note

score 4

Categories: Research