// From Skill Text to Skill Structure // One of the more practical skill papers I've seen this month. SKILL.md files entangle invocation int…

// From Skill Text to Skill Structure // One of the more practical skill papers I've seen this month. SKILL.md files entangle invocation interface, execution flow, and tool/resource side effects in one blob of natural language. This makes downstream discovery and risk review brittle. New research proposes SSL, a three-layer typed JSON representation: a Scheduling layer for invocation signals, a Structural layer for execution scenes, and a Logical layer for atomic actions and resource use. It's drawn from Schank and Abelson's classical work on scripts, MOPs, and conceptual dependency. An LLM-based normalizer converts existing SKILL.md files into this structure. The numbers: Skill Discovery MRR jumps from 0.573 to 0.707, and Risk Assessment macro F1 from 0.744 to 0.787. They release a 6,184-skill corpus, 403 task queries, and 500 risk-labeled skills. As skill registries scale, you can't keep treating capability packages as unstructured prose. Paper: https://arxiv.org/abs/2604.24026 Learn to build effective AI agents in our academy: https://academy.dair.ai/

Related

• Coding agents learn from experience, but that knowledge stays locked in silos. Solve a thousand SWE tasks, and none of that wisdom helps wit…
• A few notes on how to get started with building LLM Knowledge Bases. @karpathy popularized it but most people don't know where to start. Eve…
• LLM agents loop, drift, and get stuck on hard reasoning tasks up to 30% of the time. Current fixes are either too blunt (hard step limits) o…
• Working with Codex
• A Practical Guide to LLM Fine Tuning

Source: DAIR.AI (X) | 2026-04-28