Menu
Perform multi-perspective analysis and deep-research of a problem to arrive at a well-considered proposed solution (alias for /socratize)
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | brainstorm |
| description | Perform multi-perspective analysis and deep-research of a problem to arrive at a well-considered proposed solution (alias for /socratize) |
⚠️ CRITICAL INSTRUCTION: This is an alias for /socratize. You MUST IMMEDIATELY invoke the /socratize slash command. DO NOT attempt to do any work yourself. Your ONLY job is to invoke /socratize right away.
Use the Skill tool to invoke /socratize:
Skill(
skill: "socratize"
)
The /socratize command will orchestrate the Socratic dialogue process for multi-agent consensus building.
The /brainstorm command is an alias for /socratize, which orchestrates a Socratic dialogue process with multiple analyst and architect agents, each with unique personalities and perspectives, to thoroughly analyze complex software problems and build consensus on solutions.
For complete documentation, see the socratize skill.
User: "We need to add rate limiting to the API endpoints"
/brainstorm
→ This will invoke /socratize, which will:
1. Deploy technical-analyst to clarify problem/context/outcome
2. Determine scope and agent counts
3. Deploy analysts and architects with diverse personalities
4. Manage Socratic dialogue until consensus
Use /brainstorm (same as /socratize) when you need:
Hybrid multi-perspective analysis combining Socratic personality-driven deliberation with LLM Council multi-model factual grounding. Uses Team Mode to coordinate 3 topic-appropriate personality-diverse agents while injecting multi-model council queries for evidence-backed resolution. Use when the user needs deep research with structured debate on complex technical decisions, architecture choices, or technology evaluations.
LLM Council - 3-stage multi-model research pipeline (collect, peer review, synthesize). Queries OpenAI, Perplexity, Claude, and Gemini in parallel, has them anonymously critique each other, then synthesizes a final answer. Keywords: research, code review, architecture, multi-model consensus, LLM council, peer review, technology comparison.
Perform multi-perspective analysis and deep-research of a problem to arrive at a well-considered proposed solution