菜单
Adversarial critic workflow for the limited-stock booking system. Use when the user asks AI to attack a design or implementation for Redis outage, oversell, undersell, duplicate booking/payment, retry storm, fallback collapse, correctness gaps, or operational blind spots.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Generate an Architecture Decision Record for a technical decision
Skeptical first-principles design review skill. Use when the user asks whether a design, architecture, product plan, API, data model, workflow, or system design truly satisfies the real requirements. Reviews from fundamentals: decompose claims into requirements, assumptions, constraints, evidence, invariants, trade-offs, failure modes, and simpler alternatives. Inspired by first-principles reasoning and Cartesian doubt, but does not impersonate any real person.
Validate current project phase deliverables against PRD checklist
Resilience4j circuit breaker, retry, rate limiter, and bulkhead patterns with testing strategies. Use when implementing fault tolerance between services.
Design partner mode for system design practice. Activated when the user wants to design a new system (chat, notification, news feed, URL shortener, etc.). Sets up topic directory, uses the project mock-interview document, loads the matching problem from sysdesign-question-bank, marks the topic as active in .omx/state/, and conducts a back-and-forth Clarifying → High Level → Drill Down conversation, updating <topic>/System-Design-Document/mock-interview.md immediately as each decision lands. Uses Alex Xu Vol.1's canned numbers as the starting point (book-first), user adjusts. NOT an interview — the user drives, this skill is a design collaborator with a calculator (back-of- envelope, latency estimation via auto-injected sysdesign-frameworks) and a reference book (sysdesign-question-bank).
Promote a filled mock-interview.md into a formal Software Design Document (sdd.md) following the IEEE 1016 / Atlassian / Google design-doc style. Activated when the user says they are ready to write the SDD. Reads the topic's mock-interview.md AND the topic's conversation log files (which capture the back-and-forth detail not preserved in the structured mock-interview), then asks the user the SDD-specific questions that mock-interview doesn't cover (Constraints, ADRs, Risk Register, Rollout, Testing strategy). Writes sdd.md incrementally as decisions land.
| name | adversarial-review |
| description | Adversarial critic workflow for the limited-stock booking system. Use when the user asks AI to attack a design or implementation for Redis outage, oversell, undersell, duplicate booking/payment, retry storm, fallback collapse, correctness gaps, or operational blind spots. |
| triggers | ["adversarial review","critic mode","공격적으로 리뷰","비판적으로 공격","Redis 장애 공격","oversell 공격","undersell 공격","retry storm 공격","설계 공격"] |
| allowed-tools | Read, Write, Edit, Glob, Grep, Bash |
Use this skill to attack the design before production assumptions harden.
Always check:
docs/requirements.md.docs/decisions/DECISIONS.md.docs/reviews/adversarial-review.md.docs/reviews/adversarial-review.md with new findings or status changes.## Verdict
{Pass / Pass with reservations / Needs changes / Unsafe}
## Findings
| ID | Severity | Attack | Finding | Required Response |
|---|---|---|---|---|
| ... | Critical/High/Medium/Low | ... | ... | ... |
## Attack Walkthrough
1. {How the failure happens}
2. {What invariant breaks}
3. {How to prove or prevent it}
## Required Next Action
{single highest-leverage next action}
docs/requirements.md.