perspective-swarm

Orchestrate five archetype-driven agents to generate viewpoints on a user prompt.

6|Updated Feb 3, 2026
One-click install
npx skills add https://github.com/dangeles/claude --skill perspective-swarm
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: perspective-swarm
Source: https://github.com/dangeles/claude/tree/main/claude-config/skills/perspective-swarm
Command: npx skills add https://github.com/dangeles/claude --skill perspective-swarm

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

perspective-swarm enables rapid multi-perspective brainstorming by running five archetype-driven agents in parallel to surface a balanced synthesis of insights.

Core Features & Use Cases

  • Multi-archetype analysis: Optimist, Critic, Analyst, Innovator, and Pragmatist perspectives
  • Confidence-weighted synthesis: identify convergent and divergent insights with transparent attribution
  • Handoff readiness: structured outputs that can be handed to lit-pm or pov-expansion for deeper analysis

Quick Start

To deploy perspective-swarm, provide a clear prompt and trigger Stage 1 framing; the system will generate five agent perspectives, converge results, and present synthesis with optional handoffs.

Frequently Asked Questions about perspective-swarm

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run multi-agent brainstorming for strategic decisions?

Multi-agent brainstorming for strategic decisions is orchestrated by deploying five archetype-driven agents in parallel to analyze a clear prompt. This process generates independent viewpoints, applies neutral framing, and presents a confidence-weighted synthesis of convergent and divergent insights.

What is confidence-weighted synthesis in multi-perspective analysis?

Confidence-weighted synthesis in multi-perspective analysis aggregates independent viewpoints from multiple agents to identify convergent and divergent insights. It provides transparent attribution and neutral presentation of results to support complex problem-solving and strategic decision workflows.

Can I use archetype-driven perspectives for product roadmap planning?

Archetype-driven perspectives can be used for product roadmap planning by running five specific agents: Optimist, Critic, Analyst, Innovator, and Pragmatist. This approach surfaces a balanced synthesis of diverse insights within a 15 to 30 minute processing window.

How do I mitigate bias when evaluating complex problems with multiple agents?

Bias mitigation when evaluating complex problems with multiple agents is achieved by enforcing neutral framing across five independent archetype perspectives. The system applies confidence-weighted synthesis to transparently attribute and present convergent and divergent insights.

What's the best way to structure multi-agent outputs for deeper analysis?

The best way to structure multi-agent outputs for deeper analysis is through handoff-ready formatting that identifies convergent and divergent insights. Perspective-swarm generates structured synthesis outputs that can be directly handed to related workflows for expanded analysis.

When should I not use parallel archetype agents for decision support?

Parallel archetype agents for decision support should not be used for rapid tasks requiring immediate results outside the 15 to 30 minute processing window. This approach is designed for complex problems where diverse perspectives and confidence-weighted synthesis are explicitly valuable.