菜单
Adversarial design review of a System Design Doc. Interrogates the staff questions, finds the cost-explosion and failure risks, returns a verdict. Sensors and evals gate.
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
Visual + UX design defaults for new UIs. Material Design 3, dark/light theme, modern type, Behance-grade polish, i18n (en, pt-BR, es), context-aware favicon. No emojis and no em-dashes; use MD3/modern icons instead. Apply when building something new. Project conventions in .claude/conventions/web.md override these defaults.
Re-install / upgrade harness-kit in the current project to the version bundled in the installed plugin. Run after /plugin update harness-kit fetches a newer plugin version.
Generate a Product Requirements Prompt for engineering handoff. Needs an approved PRD. Sensors, link validation, and eval gates.
Install the harness-kit pipeline into the current project. Copies agents, slash commands, skills, hooks, and the status bar into the project's .claude/, plus AGENTS.md and CLAUDE.md at the repo root. Run after adding the harness-kit plugin from the marketplace.
Design any system from scratch into a rigorous System Design Doc. Generic fallback when no topic-specific playbook fits. Sensors and evals gate.
Design a distributed rate limiter at scale, policy model, enforcement layers (edge/gateway/service), algorithms (token bucket, sliding window), hot keys, fail-open vs fail-closed, multi-region, shadow mode. Topic playbook from the System Design series EP (Rate Limit
| name | review |
| description | Adversarial design review of a System Design Doc. Interrogates the staff questions, finds the cost-explosion and failure risks, returns a verdict. Sensors and evals gate. |
| user_invocable | true |
Review a System Design Doc the way a staff engineer runs a design review. Follow guides/pipeline.md.
Ask once if missing: path to the design doc (default latest under
.claude/runtime/outputs/architect/design/). Reviews own or external designs.
Read:
Interrogate, do not summarize. For each of the 10 staff questions, give the design's answer and the gap. Order findings by severity (blocker / high / medium / low). Name trade-offs the design left implicit. Be specific: cite the section, name the failure, propose the fix. Default to skeptical.
Verdict: ship | revise | block.
Save to .claude/runtime/outputs/architect/review/{feature_id}.md (reuse the design's feature_id).
Sensors: sensors/design-structure.md (review variant: all 10 questions answered, verdict present). Evals: evals/design-review-depth.md.
After save reply: Review saved at {path}. Verdict: {ship|revise|block}. Score: {N}/10.
