SkCC: Portable and Secure Skill Compilation for Cross-Framework LLM Agents

TL;DR

SkCC introduces a portable, secure skill compiler for LLM agents that decouples skill semantics from framework-specific formatting, improving security, efficiency, and cross-framework deployment.

Contribution

The paper presents SkCC, a novel compiler with a strongly-typed IR and static optimizer that enhances skill portability and security for LLM agents.

Findings

SkCC increases skill pass rates significantly on benchmark tasks.

It reduces adaptation complexity from O(m×n) to O(m+n).

Achieves sub-10ms compilation latency and high security trigger rate.

Abstract

LLM agents increasingly rely on reusable skills (e.g., `SKILL.md`) to execute complex tasks, yet these artifacts lack portability: agent frameworks are highly sensitive to prompt formatting, leading to a large performance variation for the same skill. Nevertheless, most skills are authored once as format-agnostic Markdown, necessitating costly per-framework rewrites and also leaving security largely unaddressed, with widespread vulnerabilities in practice. To address this, we present SkCC, a compiler for LLM agents that introduces classical compilation design into agent skill development. SkCC centers on SkIR, a strongly-typed intermediate representation that decouples skill semantics from framework-specific formatting, thus enabling portable deployment across agent frameworks. Atop of this IR, a static Optimizer enforces security constraints, blocking vulnerabilities before deployment. Implemented as a four-phase pipeline, SkCC effectively reduces adaptation complexity from $O(m \times n)$ to $O(m + n)$ across $m$ skills and $n$ frameworks. Experiments on SkillsBench demonstrate that SkCC delivers consistent and substantial gains over original counterparts, with pass rate increases from 21.1% to 33.3% on Claude Code and from 35.1% to 48.7% on Kimi CLI. Further, the design achieves sub-10ms compilation latency, 94.8% proactive security trigger rate, and 10-46% runtime token savings across frameworks.