multi-agent-brainstorming
CommunityStructured design review by specialized agents.
Software Engineering#system design#validation#design review#risk assessment#agent collaboration#peer review
Authormrsono0
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill transforms a single-agent design into a robust, review-validated design by simulating a formal peer-review process using multiple constrained agents, preventing hidden assumptions and failure modes.
Core Features & Use Cases
- Simulated Peer Review: Employs distinct agent roles (Designer, Skeptic, Guardian, Advocate, Integrator) for comprehensive design validation.
- Structured Feedback Loop: Enforces sequential, role-specific critique to identify weaknesses and ensure adherence to constraints.
- Decision Logging: Mandates a detailed Decision Log to track all design choices, objections, and resolutions.
- Use Case: Before launching a new software feature, use this Skill to have specialized AI agents rigorously challenge the initial design, identify potential security flaws, ensure user experience is optimal, and confirm all technical constraints are met.
Quick Start
Use the multi-agent-brainstorming skill to review the initial design document for the new user authentication system.
Dependency Matrix
Required Modules
None requiredComponents
references
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: multi-agent-brainstorming Download link: https://github.com/mrsono0/lecture_factory/archive/main.zip#multi-agent-brainstorming Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.