design-review-gate

Parallel design review by 6 specialist agents (PM, Architect, Designer, Security Design, UX, CTO) with mandatory unanimous approval.

509 stars

Best use case

design-review-gate is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Parallel design review by 6 specialist agents (PM, Architect, Designer, Security Design, UX, CTO) with mandatory unanimous approval.

Teams using design-review-gate should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/design-review-gate/SKILL.md --create-dirs "https://raw.githubusercontent.com/a5c-ai/babysitter/main/library/methodologies/metaswarm/skills/design-review-gate/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/design-review-gate/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How design-review-gate Compares

Feature / Agentdesign-review-gateStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Parallel design review by 6 specialist agents (PM, Architect, Designer, Security Design, UX, CTO) with mandatory unanimous approval.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Design Review Gate

## Overview

Run 6 specialist design reviews in parallel. ALL SIX must approve before implementation begins. Maximum 3 iterations before human escalation.

## When to Use

- After brainstorming and planning, before implementation
- 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

| Agent | Focus |
|-------|-------|
| Product Manager | Use cases, user benefits, scope alignment |
| Architect | Architectural fit, patterns, technical debt |
| Designer | UX/API design, developer experience |
| Security Design | Threat modeling, OWASP Top 10 |
| UX Reviewer | Usability, accessibility, user flows |
| CTO | TDD readiness, codebase alignment, risk |

## Tool Use

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