Tool Tutorial · Xiaohu's Take

Google wires Agent Skills into its Genkit framework for on-demand skill packs

Anthropic's open skills standard is now wired into all four of Google's language versions. Two runnable Go examples walk you through it, and hooking it in takes one line of code.
One-Minute Read
  • AI agent manuals keep piling up, and cramming them all into context burns tokens and distracts the model. Google wired Agent Skills into its own framework, Genkit: the manuals stay on disk, and the right one loads only when needed.
  • The skills standard started with Anthropic, and Google hooked it into all four language versions. Enabling it takes one line of code.
  • Google's official test image is the original painting of "Monkey Jesus" (disfigured in 2012). The model correctly identifies it as an oil painting and summons the matching restoration skill.
⚑ Source material comes from a Google Developers Blog tutorial on their own framework, Genkit. The example outputs shown are as displayed in the original article; this site has not independently re-run them.
The Problem

Stuffing the manual into the AI's head is a losing game

The Google Developers Blog just published a refreshingly practical tutorial: Genkit, their open-source AI application framework, now officially supports Agent Skills — the "AI skill pack" format started by Anthropic and now open as an industry standard. The short version: you used to have to shove every operating manual into the prompt, but now the manuals stay on disk and only the one you need gets loaded. The tutorial includes two directly runnable Go examples: a recipe bot, and an AI art restorer that picks its own restoration approach.

4 Languages
TypeScript / Go / Dart / Python all supported
3 Stages
Progressive disclosure: Discover → Activate → Execute
1-Line Hookup
ai.WithUse(...) is all it takes

Every agent builder knows this problem: the more tasks your agent takes on, the more manuals you have to hand it—operating procedures, reference guides, assorted docs. Keep all of it resident in the context window and three problems hit at once: tokens burn fast (every request re-reads the whole pile), attention dilutes (the few lines that matter get buried in hundreds of pages), and the odds of a wrong answer actually climb. It's like making an employee memorize the entire corporate rulebook every morning when they'll only need one page all day.

Before: crammed into context Operating rules Reference guide Brand book Review checklist Data dictionary More docs... (still coming) Every request carries the whole pile After: on-demand loading Skill card Room for the actual task Disk Skill bodies live here Summoned in
The same stack of manuals, two placements: always in context vs. card resident, body on disk (this site's diagram)

Agent Skills is the answer: package expertise into individual skills that sit in the background until the moment they're needed. If you've used Skills in Claude Code, this will feel familiar—same format, and Anthropic has opened it up as a standard (agentskills.io). Genkit now plugs into that same spec. We've previously broken down Anthropic's official take on using Skills to build a validation loop:

Related on this site
Anthropic shows you how to turn manual code review into a skill that reviews and fixes itself
That piece gives you the full breakdown of how Skills work in practice inside Claude Code. Today's piece is about the same format running inside Google's framework.
The Format

A skill is just a folder

So what does an "on-demand" skill actually look like? Surprisingly simple: a skill is a folder containing exactly one required file, SKILL.md. That file has two parts. At the top is the frontmatter — a small block of metadata wrapped in --- that says what the skill is called and when to reach for it. Below that is the body: the actual operating instructions. The folder can also hold three types of optional resources: scripts/ (executable code), references/ (documentation), and assets/ (templates or other resources).