Skip to content
Learn Kiro.

Practice · Chapter 8 of 17

The Workspace Game

An interactive game that drills Kiro's core concepts: 18 setup decisions drawn from a 31-question pool, a repair round for misses, and a per-concept mastery map.

All levels last reviewed 2026-06-13

◎ Learning objective

Pick the right Kiro tool, location, sequence, and judgment call for realistic project situations, quickly and from memory, without the docs open.

Reading about steering files is one thing. Recognizing “oh, this is a steering problem” in the middle of a messy Tuesday is the actual skill. This game drills that recognition. You join a fictional project with an empty .kiro/ folder and make eighteen setup decisions — which tool, which path, which order, which judgment call — while the workspace panel fills with every artifact you earn.

Three things make it a teacher rather than a quiz. Pick a wrong answer and it explains why that option fails, not just which one was right. Misses come back in a repair round, so every mistake gets corrected by you, not just shown to you. And a mastery map tracks each concept across runs, so after a few plays it knows your weak spots better than you do.

~6 minutes · 3 rounds + repair · 18 decisions

New project. Empty .kiro/ folder.

The team just adopted Kiro, and setting it up is your job. Every question is one setup decision: which tool, which path, which order, which judgment call. Answer it and the piece is added to your workspace. Each run draws its 18 questions from a pool of 31, so replays stay honest.

  • One attempt per question. A miss shows you why your pick fails, not just the right answer.
  • +100 per correct answer, +50 extra on streaks of 3 or longer.
  • Missed chips come back in a repair round: fix one for +50.
  • Your per-concept mastery is tracked across runs on this device.

☰ Chapter summary

  • Round 1 drills tool choice across all eleven core concepts: steering, hooks, MCP, specs, custom agents, skills, powers, checkpoints, context providers, and the three surfaces.
  • Round 2 drills anatomy: .kiro/steering/, .kiro/settings/mcp.json, .kiro/agents/, SKILL.md structure, front-matter placement, spotting secrets and autoApprove risks in real configs.
  • Round 3 drills fluency: EARS lines, inclusion modes, spec and skill workflows in sequence, headless kiro-cli, and judgment calls like reviewing cloud-agent pull requests.
  • Every wrong answer explains why that exact option fails, misses return in a repair round, and a per-concept mastery map accumulates across runs to tell you what to reread.

All chapter summaries are collected on the revision page.