Workflow-to-Skill: Skill Creation via Routing-Workflow-Semantics-Attachments Decomposition
For developers of LLM agents, this work addresses the costly manual creation of high-quality skills by automating construction from traces, though the improvement is incremental over existing methods.
The paper tackles automatic skill construction from heterogeneous interaction traces for LLM agents, introducing RWSA (a workflow-oriented intermediate representation) and W2S (a framework that segments traces, induces drafts, aligns structures, and compresses redundancy). Experiments on 70 skills show W2S improves behavioral replay consistency by 10.5% over baselines.
Large language model agents increasingly rely on Skills to encode procedural knowledge, yet high-quality Skills remain costly to hand-write. This paper studies automatic Skill construction from heterogeneous interaction evidence, including demonstrations, agent trajectories, tool traces, and execution logs. We argue that trace-to-skill construction is not simple summarization tasks, because traces are fragmented, redundant, and may miss rare but safety-critical behaviors. To address this, we introduce RWSA, a workflow-oriented intermediate representation that decomposes Skills into Workflow structure, execution Semantics, and runtime Attachments, capturing task decomposition, control flow, verification, safety, rollback, and state management. Building on RWSA, we propose W2S, a framework that segments traces, induces local Skill drafts, aligns shared structures, reconciles branches, and compresses redundancy while preserving evidence and confidence annotations. Experiments on 70 Skills show that W2S improves behavioral replay consistency by 10.5% over summarization- and prompting-based baselines, highlighting the need to treat traces as executable runtime specifications rather than compressible text.