Skip to content
Back to skills

Society Of Mind

ASecurity

Strategy: Multi-agent collaborative debate based on Du et al. Society of Mind. Agents share perspectives iteratively until convergence or divergence is detected.

  • 417 stars
  • 0 votes
  • 0 copies
  • 3 views
  • Added May 27, 2026
research

Security analysis

A100/100

Scanned May 27, 2026

npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill society-of-mind --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Society Of Mind?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Society Of Mind
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/yogsoth-ai-society-of-mind/badge)](https://www.skillsdirectory.com/skills/yogsoth-ai-society-of-mind)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: society-of-mind
description: "Strategy: Multi-agent collaborative debate based on Du et al. Society of Mind. Agents share perspectives iteratively until convergence or divergence is detected."
type: strategy
used-by: [multiagent-debate]
tactics: [perspective-rotation]
---

# Society of Mind Strategy

Multiple agents evaluate independently, then share and revise through iterative rounds.

## Method

1. **debate-architect** assigns N distinct perspectives to agents
2. Each **perspective-critic** evaluates artifact from assigned viewpoint
3. All perspectives shared — agents revise positions given others' arguments
4. **divergence-detection** identifies agreement clusters and persistent disagreements
5. Repeat sharing rounds until convergence or saturation

## Budget Table

| Parameter | S | M | L |
|---|---|---|---|
| Debate rounds | 4 | 8 | 12 |
| Participating agents | 3 | 5 | 8 |
| Coverage dimensions | 3 | 5 | 7 |
| External evidence searches | 2 | 5 | 10 |

## Orchestration

```
debate-architect → [assign perspectives]
→ [parallel]: perspective-critic × N
→ [for each sharing round]:
    share all outputs → perspective-critic revises
    → divergence-detection → (converge or continue)
→ debate-transcript-analysis → verdict-synthesis
```

## Subagents

- debate-architect (perspective assignment)
- perspective-critic × N (perspective evaluation)
- divergence-detection (convergence tracking)
- confidence-calibration (termination decision)

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.