Genkit Go 引入 Agent Skills，按需加载技能防止上下文膨胀
Enable on-demand expertise with Agent Skills in Genkit Go
Genkit Go 推出基于渐进式披露架构的 Agent Skills，将专用指令、脚本和参考资料打包为模块化 SKILL.md 包，初始仅向系统提示暴露 frontmatter 元数据。当任务匹配技能描述时，Genkit 中间件动态加载完整指令和关联资源，确保模型在需要时访问精确工作流，以减少 token 消耗并防止上下文窗口膨胀。
To prevent context window bloat and reduce token consumption, Genkit Go introduces Agent Skills based on a progressive disclosure architecture. Developers can package specialized instructions, scripts, and references into modular SKILL.md bundles where only the frontmatter metadata is initially exposed to the agent's system prompt. When a task matches the skill's description, Genkit's middleware dynamically loads the full instruction body and associated assets, ensuring the model accesses precise workflows exactly when needed.
来源：Google Developers Blog · developers.googleblog.com