Skilldex: A Package Manager and Registry for Agent Skill Packages with Hierarchical Scope-Based Distribution
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913042460049408 |
|---|---|
| author | Saha, Sampriti Hemanth, Pranav |
| author_facet | Saha, Sampriti Hemanth, Pranav |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_16911 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Skilldex: A Package Manager and Registry for Agent Skill Packages with Hierarchical Scope-Based Distribution Saha, Sampriti Hemanth, Pranav Artificial Intelligence D.2.7; K.6.3 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. |
| title | Skilldex: A Package Manager and Registry for Agent Skill Packages with Hierarchical Scope-Based Distribution |
| topic | Artificial Intelligence D.2.7; K.6.3 |
| url | https://arxiv.org/abs/2604.16911 |