Search papers, labs, and topics across Lattice.
This paper introduces SkCC, a compilation framework for LLM agent skills that uses a strongly-typed intermediate representation (SkIR) to decouple skill semantics from platform-specific formatting. SkCC also includes a compile-time analyzer to enforce security constraints and prevent anti-skill injection. Experiments on SkillsBench demonstrate that SkCC improves skill performance across platforms, achieving higher pass rates and token savings, while also providing proactive security.
LLM agent skills are needlessly brittle and insecure: SkCC compiles them into a portable, hardened format that boosts performance by 50% and proactively blocks attacks.
LLM-Agents have evolved into autonomous systems for complex task execution, with the SKILL.md specification emerging as a de facto standard for encapsulating agent capabilities. However, a critical bottleneck remains: different agent frameworks exhibit starkly different sensitivities to prompt formatting, causing up to 40% performance variation, yet nearly all skills exist as a single, format-agnostic Markdown version. Manual per-platform rewriting creates an unsustainable maintenance burden, while prior audits have found that over one third of community skills contain security vulnerabilities. To address this, we present SkCC, a compilation framework that introduces classical compiler design into agent skill development. At its core, SkIR - a strongly-typed intermediate representation - decouples skill semantics from platform-specific formatting, enabling portable deployment across heterogeneous agent frameworks. Around this IR, a compile-time Analyzer enforces security constraints via Anti-Skill Injection before deployment. Through a four-phase pipeline, SkCC reduces adaptation complexity from $O(m \times n)$ to $O(m + n)$. Experiments on SkillsBench demonstrate that compiled skills consistently outperform their original counterparts, improving pass rates from 21.1% to 33.3% on Claude Code and from 35.1% to 48.7% on Kimi CLI, while achieving sub-10ms compilation latency, a 94.8% proactive security trigger rate, and 10-46% runtime token savings across platforms.
