Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward

ArXi:2602.12430v4 Announce Type: replace-cross The transition from monolithic language models to modular, skill-equipped agents marks a defining shift in how large language models (LLMs) are deployed in practice. Rather than encoding all procedural knowledge within model weights, agent skills -- composable packages of instructions, code, and resources that agents load on demand -- enable dynamic capability extension without re