design-review-gate
npx machina-cli add skill a5c-ai/babysitter/design-review-gate --openclawFiles (1)
SKILL.md
1.3 KB
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
- Run 6 reviews in parallel: PM, Architect, Designer, Security Design, UX, CTO
- All 6 must approve (unanimous)
- If any reject, consolidate findings and iterate
- 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
Source
git clone https://github.com/a5c-ai/babysitter/blob/main/plugins/babysitter/skills/babysit/process/methodologies/metaswarm/skills/design-review-gate/SKILL.mdView on GitHub Overview
Design Review Gate runs six specialist reviews in parallel and requires unanimous approval before implementation. If any reviewer rejects, findings are consolidated and the design is iterated up to three times before escalation.
How This Skill Works
Six reviewers (PM, Architect, Designer, Security Design, UX, CTO) assess the design in parallel. All must approve; any rejection triggers consolidation of findings and an iteration cycle, capped at three iterations before escalation.
When to Use It
- After brainstorming and planning, before implementation
- When validating a new feature design
- When introducing new architectural patterns
- For critical features requiring cross-disciplinary clearance
- During design refreshes to enforce security, UX, and architectural alignment
Quick Start
- Step 1: Initiate six parallel reviews (PM, Architect, Designer, Security Design, UX, CTO) using the metaswarm gate
- Step 2: Gather unanimous approvals; if any reviewer rejects, log findings and prepare an iteration plan
- Step 3: Repeat up to three iterations; escalate to a human if still unresolved
Best Practices
- Define unanimous approval criteria up front and align reviewers' focus
- Run all six reviews in parallel to save time
- Document each review's findings and rationale
- Limit iterations to a maximum of three before escalation
- Consolidate feedback before iteration steps to avoid redundancy
Example Use Cases
- Rolling out a new payment feature with UX, security, and API implications
- Adopting a new microservice pattern across the stack
- Overhauling the user onboarding flow with usability and accessibility checks
- Rearchitecting data access for performance while maintaining security
- Assessing a critical risk feature requiring unanimous sign-off before launch
Frequently Asked Questions
Add this skill to your agents