Big picture for Day 3

Day 2 connected agents outward (tools, APIs, MCP). Day 3 looks inward: what the agent keeps in mind while working.

If you stuff every instruction into one giant prompt, the agent gets confused — wrong tools, forgotten rules, made-up details. Today you learn a cleaner pattern: skills (playbooks) and workflows (step-by-step flows).

Concepts you need today

Context

Everything the model can “see” when it answers: system instructions, chat history, file snippets, tool results, and loaded guides. Context has a size limit (token budget).

Context rot

When too much context makes performance worse — the model ignores rules, picks wrong tools, or hallucinates. More text is not always better.

Like cramming an entire textbook into your head right before one exam question — you miss the important line.

Agent skill (playbook)

A small folder (often with a SKILL.md file) that teaches the agent how to do one job step by step — e.g. format commits, validate a database schema, run a security checklist.

Skills = recipe cards. Tools/MCP = oven and ingredients.

Progressive disclosure

Show only a short summary of each skill at first; load the full instructions only when that skill is needed. Saves memory and reduces rot.

Procedural memory

Remembering how to do something (steps), not just what happened (events) or facts (knowledge). Skills are a form of procedural memory for agents.

Agent framework

Code libraries that structure agents: nodes, tools, state, and flows. This course uses ADK 2.0 with graph-style workflows.

Workflow / graph

A flowchart of steps: “first classify the question → then route to FAQ or decline.” Some steps use the LLM; some use plain code for speed and reliability.

Agents CLI (lifecycle tool)

A command-line toolkit to scaffold, lint, run, test, and later deploy agent projects — not the same as Antigravity CLI (agy), which is for general coding chat. Think: “project manager for ADK agents.”

Skills vs tools — don’t mix them up

Skill (playbook) Tool / MCP (capability)
Provides Know-how: steps, rules, examples Action: API call, DB query, file read
Simple test If you remove the skill, the model might still do the task clumsily If you remove the tool, the action becomes impossible
Examples “How we write commit messages at our company” “Fetch row from database”

Tool categories (not just Google)

Category What it does In this course Same idea elsewhere
Portable skill / rule packs Reusable instruction folders the agent loads on demand. Agent Skills (SKILL.md) Cursor rules, Claude PROJECT.md / skills, Copilot instructions, custom GPT knowledge
Agent dev CLI Scaffold projects, run playground, lint, eval, deploy. Agents CLI (google-agents-cli) LangGraph CLI patterns, framework-specific CLIs, Makefile/scripts around your agent
Agent framework Code structure for multi-step agents. ADK 2.0 (Workflow, LlmAgent, nodes) LangGraph, CrewAI, AutoGen, OpenAI Agents SDK
Local test UI Chat with your agent while developing. agents-cli playground LangSmith playground, custom Streamlit/Gradio UIs, ADK web UI

Podcast

Whitepaper Companion Podcast: Agent Skills youtube.com/watch?v=uYURYHhpmKc

What you will get from it: Why skills spread quickly, how they fight context rot, and why one flexible agent can play many “roles” without building ten separate bots.

Whitepaper

Agent Skills kaggle.com/whitepaper-agent-skills

Main ideas: Skill folder format, progressive disclosure, builder vs developer concerns, evaluating whether skills trigger correctly, and security when importing skills from the internet.

Codelabs

Codelab 1: Explore how Skills work in Antigravity codelabs.developers.google.com/getting-started-with-antigravity-skills

Concept practiced: Authoring skills from simple formatters up to procedural validators; installing skill packs.

Transferable skill: Same pattern as “rules files” or “custom instructions” in any agent IDE — one markdown spec + optional scripts.

Codelab 2: Build agents with Agents CLI and ADK 2.0 codelabs.developers.google.com/agents-cli-adk-lifecycle

Concept practiced: Full local dev loop — scaffold a workflow agent (classify → route → answer), lint, playground test with hot reload, CLI single-shot test.

Transferable skill: Every framework needs: project template → run locally → inspect steps → fix graph logic.

Livestream

Day 3 Livestream (~58 min) youtube.com/watch?v=1T2mxYZkqL0

Deep dive on skills security (trust tiers, scanning shared skills), when to promote a skill to an MCP tool, and meta-skills (agents improving their own playbooks).

Check yourself