Skilldex: A Package Manager and Registry for Agent Skill Packages with Hierarchical Scope-Based Distribution
For developers of LLM agents, Skilldex offers tooling to improve skill package quality and coherence, but the contributions are incremental, building on existing community registries and package managers.
Skilldex introduces a package manager and registry for LLM agent skill packages, addressing the lack of format conformance scoring against Anthropic's specification and the absence of mechanisms for bundling related skills with shared context. The system provides compiler-style diagnostics and a skillset abstraction to ensure cross-skill coherence.
Large Language Model (LLM) agents are increasingly extended at runtime via skill packages, structured natural-language instruction bundles loaded from a well-known directory. Community install tooling and registries exist, but two gaps persist: no public tool scores skill packages against Anthropic's published format specification, and no mechanism bundles related skills with the shared context they need to remain mutually coherent. We present Skilldex, a package manager and registry for agent skill packages addressing both gaps. The two novel contributions are: (1) compiler-style format conformance scoring against Anthropic's skill specification, producing line-level diagnostics on description specificity, frontmatter validity, and structural adherence; and (2) the skillset abstraction, a bundled collection of related skills with shared assets (vocabulary files, templates, reference documents) that enforce cross-skill behavioral coherence. Skilldex also provides supporting infrastructure: a three-tier hierarchical scope system, a human-in-the-loop agent suggestion loop, a metadata-only community registry, and a Model Context Protocol (MCP) server. The system is implemented as a TypeScript CLI (skillpm / spm) with a Hono/Supabase registry backend, and is open-source.