From Skill Text to Skill Structure
Free while signed in. Answers cite the passages they came from.
SKILL.md files entangle invocation interface, execution flow, and tool side effects in a single blob of natural language. That makes downstream discovery and risk review brittle as skill registries scale. This paper proposes SSL, a three-layer typed JSON representation drawn from Schank and Abelson's classical work on scripts, MOPs, and conceptual dependency. An LLM-based normalizer converts existing SKILL.md files into the structure, so adoption does not require rewriting registries by hand.
Three layers, cleanly separated: A Scheduling layer captures invocation signals and trigger conditions, a Structural layer encodes execution scenes and ordering, and a Logical layer specifies atomic actions plus resource and side-effect annotations. The separation lets discovery, risk, and execution each reason about the layer they care about.
Skill Discovery MRR jumps 0.573 to 0.707: Treating skills as typed structure rather than prose makes retrieval significantly more accurate, even before any model fine-tuning. The gain comes from the structure exposing what skills actually do, not just how they describe themselves.
Risk Assessment macro F1 of 0.787: The Logical layer's resource annotations enable a 0.744 to 0.787 jump in risk classification. Auditors can now reason about side effects directly instead of inferring them from free-form prose.
A 6,184-skill corpus released: The authors ship a normalized corpus of 6,184 skills, 403 task queries, and 500 risk-labeled skills. As skill registries cross a million entries, structured representations are the only path that keeps discovery and review tractable.
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack