Open Source Summit Korea 2026

AI agents like Claude Code, Cursor, and Codex learn libraries via SKILL.md files, but these skills are currently unversioned, ungoverned, and unshared. We solved code dependency management with pip and npm — now it's time to solve it for AI knowledge.
This talk presents an open-source, package-manager-style system for agent skills. Skills are linked to their packages, versioned with semver, declared in skills.toml, and locked via skills-lock.toml — just like regular dependencies.
The CLI (skills add, install, lock, publish) feels native to any developer using pip or uv.
We'll cover:

The SKILL.md open standard (YAML frontmatter + Markdown) — model-agnostic and runtime-agnostic
Manifest format supporting version constraints, inheritance, and monorepo scoping
Resolver that enforces constraint narrowing across org hierarchies
Registry with publishing, discovery, approval workflows, and security scanning
Real cases where this prevented production incidents by keeping agents on correct, up-to-date patterns

Live demo: Add a skill, resolve dependencies, publish it, and watch a new engineer's agent instantly get the right knowledge - no onboarding docs required.