Agent Skills

Across 60 research projects, ASI-Bench found full procedures averaged 50.91, versus 29.10 for prompts naming only a method. Other evaluations similarly measure whether procedural skills improve execution rather than merely adding more instructions.

A study of 557 coding-agent sessions finds instruction files and working notes account for most of what agents read. Related work puts installed skills' standing prompt cost at 50–280 tokens, while Backpass turns past sessions into reviewable AGENTS.M files.

A study summary reports 307 confirmed failures caused by agent skills, including 125 functional failures. Practitioners favor user-invoked skills to avoid ambiguous automatic triggers and token use before a skill is needed.

Google DeepMind introduced SkillSmith, a method that treats prefix weights or KV-cache states as an input modality so a frozen Gemma 3 4B model can synthesize new skill prefixes at inference time. Reported Composite-SNI Elo improved when cache composition was combined with text descriptions, making it a research artifact rather than a deployable runtime.

New guides, plugins, and reusable libraries show the Agent Skills format moving beyond Claude Code into multiple coding-agent clients and runtimes. That matters because workflows are becoming portable artifacts instead of one-off prompts tied to a single harness.