design-review-gate

SkillSecurity

design-review-gate adds a review step your AI can run on a design proposal. The proposal is examined in parallel by six simulated specialists — a PM, an Architect, a Designer, a Security Design reviewer, a UX reviewer, and a CTO — and it only passes if all six approve. That way a design has to satisfy every perspective before it moves ahead.

Available today. Use it from your connected AI after setup.

Add the skill, then give your AI a design proposal and ask it to run the review. The proposal moves forward only if all six reviewers approve.

Then ask your AI: use the design-review-gate skill

What your AI can do with it

  • Review a design proposal from six viewpoints: PM, Architect, Designer, Security Design, UX, and CTO
  • Run all six reviews in parallel
  • Require unanimous approval from every reviewer before a design passes
  • Hold a design back when any one of the six reviewers does not approve

What this skill tells your AI

The instructions your AI receives, as published by a5c-ai/babysitter in library/methodologies/metaswarm/skills/design-review-gate/SKILL.md and read by ahel’s review.

  • When validating a new feature design
  • When introducing new architectural patterns

Process

  1. Run 6 reviews in parallel: PM, Architect, Designer, Security Design, UX, CTO
  2. All 6 must approve (unanimous)
  3. If any reject, consolidate findings and iterate
  4. Max 3 iterations before escalating to human

Reviewers

AgentFocus
Product ManagerUse cases, user benefits, scope alignment
ArchitectArchitectural fit, patterns, technical debt
DesignerUX/API design, developer experience
Security DesignThreat modeling, OWASP Top 10
UX ReviewerUsability, accessibility, user flows
CTOTDD readiness, codebase alignment, risk

Tool Use

Invoke via babysitter process: methodologies/metaswarm/metaswarm-design-review

Signals

GitHub stars
2k
Forks
106
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
design-review-gate
Source
github.com/a5c-ai/babysitter