Agent Skill Harbor – a GitHub-native skill platform for teams

Name: Agent Skill Harbor – a GitHub-native skill platform for teams
Availability: InStock
Author: hatappo

by hatappo·Mar 26, 2026·10 points·8 comments

Visit Project View on HN

AI Analysis

●●SolidBig BrainShip It

Git as the database for skills is clever, but MCP registries already exist.

Strengths

•DB-less design stores collected data as YAML/JSON committed back to Git repository
•Built-in audit-skill-scanner analyzes safety before skills reach production systems
•Static prerendered catalog hosted on Pages eliminates server maintenance entirely

Weaknesses

•AI skill management is emerging but already has MCP Registry and similar tools
•GitHub Actions as the update mechanism adds latency vs real-time skill discovery

Post Description

There are already many services for discovering public skills, and many ways to manage your own personal skills.

What still feels missing is the middle layer: how teams and organizations share AI agent skills, track provenance, and keep them safe to use.

Agent Skill Harbor is an OSS skill management platform for that layer. It is GitHub-native, DB-less, and serverless by design, because skills are mostly text artifacts that already fit naturally in Git.

It collects skills from GitHub repos, tracks provenance, supports governance and safety checks, and publishes a static catalog site with GitHub Actions and GitHub Pages.

Repo: https://github.com/skill-mill/agent-skill-harbor Demo: https://skill-mill.github.io/agent-skill-harbor-demo/