--- format: "aidr-story-markdown/v1" id: "1aae3752f0ae75b2145234607d18040653040d151037e1b2f0f0d9496bd4753c" canonical_url: "https://aidr.today/1aae3752?lang=en" title: "Enable on-demand expertise with Agent Skills in Genkit Go" lang: "en" requested_lang: "en" available_langs: ["en","vi"] translation_fallback: null fallback_fields: [] published_at: "2026-09-15T19:46:17.000Z" category: "Agents" topics: [] source_urls: ["https://developers.googleblog.com/enable-on-demand-expertise-with-agent-skills-in-genkit-go/"] summary: "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." --- # Enable on\-demand expertise with Agent Skills in Genkit Go > [Open the canonical story]() **Published:** 2026-09-15T19:46:17.000Z **Category:** Agents ## Summary 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\. ## Sources - [Story source]()