Google adds automated quality gates and an AI reviewer to Agent Skills
Google says its Agent Skills repository has grown to more than 21,000 GitHub stars and over 170 skills from teams across the company, distributed across multiple AI platforms. It has added semantic-versioning checks, evaluation gates, deterministic linters, and an AI review agent to its CI/CD workflow, while requiring human approval before publication. Google says developers can reuse the same gates and review rules in their own skill repositories.
The changes provide a concrete governance pattern for maintaining AI agent skills at scale, including automated validation, evaluation evidence, and human oversight, though their effectiveness has not been independently verified.
In my previous post, I took you behind the scenes of Google Agent Skills, covering how the project started, how we maintain quality at scale, and how we handle governance. In this post, I'll share what we've built since then: the automated quality gates every change must pass, the AI review agent that inspects skill quality, and the lessons we learned along the way. You can adopt the same gates and review rules in your own skill repository.
Since my last post, the Google Agent Skills repository has passed 21,000 GitHub stars, up from 15,000. It now hosts over 170 skills from teams across Google, and we distribute them across multiple AI platforms.
Building agent skills for a single developer or a small project is straightforward. You write a SKILL.md file, define a few instructions, test it manually, and it works. At our scale, manual workflows stop being effective. Unvetted edits can introduce subtle bugs, and it becomes difficult to catch issues before they reach users.
The core philosophy: Ship skills like products
One key lesson from my previous post: a skill is a living product, not a one-off document. In practice, that means we ship every skill update like a product release.