메뉴
Test at extremes (1000x bigger/smaller, instant/year-long) to expose fundamental truths hidden at normal scales
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Use when initializing or maintaining agent-friendly repo context, setting up AGENTS.md or CLAUDE.md, adding local rules, defining verification commands, or checking whether context files are stale.
Use when the user asks to run workflow:ship, ship a branch, publish a feature branch, open and merge a PR, or push/PR/merge/cleanup completed work.
Use when the user asks to run workflow:commit, create a commit, make a git commit, stage changes, write a commit message, or prepare local changes for shipping.
Turn any rough prompt, half-formed idea, or task description into a finished, ready-to-send prompt optimized for Opus 4.7 (with adaptive thinking) inside the chat app — claude.ai, the Mac app, the iOS app — NOT the API. Use this skill whenever the user wants to write, rewrite, optimize, improve, sharpen, or polish a prompt for the chat app. Trigger phrases include "rewrite this prompt", "make this a better prompt", "optimize this prompt", "turn this into a prompt", "help me prompt this", "draft a prompt that...", "I want to ask...", or whenever the user pastes a draft prompt and asks for improvements. Also trigger when the user describes a task they plan to send into the chat app and clearly wants a reusable, well-structured prompt rather than a direct answer. The output is always a single, copy-pasteable prompt in a code block that the user sends as-is — never a template with placeholders. Always ends with the exact line "Think before answering (maximum reasoning)".
Entry point for new work. Determines the best action path or work decomposition (update existing spec, create new spec, mixed decomposition, or no spec needed) and refines ideas through structured dialogue.
Pre-discovery intent exploration for genuinely vague ideas. Use when the user pitches an idea where the real user-need, problem framing, or core assumptions are unclear — before /kiro-discovery. Delegates to the intent-explorer skill, which produces .kiro/specs/<slug>/intent-spec.md. The output is auto-detected by /kiro-discovery and downstream spec skills, so the user does not need to pass intent context as an argument. Skip this skill entirely when the user already has a clear problem statement.
| name | scale-game |
| description | Test at extremes (1000x bigger/smaller, instant/year-long) to expose fundamental truths hidden at normal scales |
| when_to_use | when uncertain about scalability, edge cases unclear, or validating architecture for production volumes |
| version | 1.1.0 |
Test your approach at extreme scales to find what breaks and what surprisingly survives.
Core principle: Extremes expose fundamental truths hidden at normal scales.
| Scale Dimension | Test At Extremes | What It Reveals |
|---|---|---|
| Volume | 1 item vs 1B items | Algorithmic complexity limits |
| Speed | Instant vs 1 year | Async requirements, caching needs |
| Users | 1 user vs 1B users | Concurrency issues, resource limits |
| Duration | Milliseconds vs years | Memory leaks, state growth |
| Failure rate | Never fails vs always fails | Error handling adequacy |
Normal scale: "Handle errors when they occur" works fine At 1B scale: Error volume overwhelms logging, crashes system Reveals: Need to make errors impossible (type systems) or expect them (chaos engineering)
Normal scale: Direct function calls work At global scale: Network latency makes synchronous calls unusable Reveals: Async/messaging becomes survival requirement, not optimization
Normal duration: Works for hours/days At years: Memory grows unbounded, eventual crash Reveals: Need persistence or periodic cleanup, can't rely on memory
