OpenSkillIndex← back to search
claude-codedevelopment

Babysitter design-review-gate

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

install
source · Clone the upstream repo
git clone https://github.com/a5c-ai/babysitter
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/a5c-ai/babysitter "$T" && mkdir -p ~/.claude/skills && cp -r "$T/library/methodologies/metaswarm/skills/design-review-gate" ~/.claude/skills/a5c-ai-babysitter-design-review-gate && rm -rf "$T"
manifest: library/methodologies/metaswarm/skills/design-review-gate/SKILL.md
tags
#design-review#parallel-approval#architectural-validation#security-assessment#ux-validation#cto-approval
source content

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

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