谷歌为 Agent Skills 增加自动质检与 AI 审查
谷歌表示,其 Agent Skills 仓库的 GitHub 星标已超过 21,000,并收录了谷歌内部团队贡献的 170 多项技能,分发至多个 AI 平台。其 CI/CD 流程新增语义版本检查、评估门禁、确定性检查工具和 AI 审查智能体,发布前仍需人工批准。谷歌称开发者可在自己的技能仓库中采用相同的门禁和审查规则。
这些机制提供了规模化维护 AI 智能体技能的具体治理方案,涵盖自动验证、评估证据与人工审核,但实际效果尚未得到独立验证。
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.