/agent-debate

Multi-Agent Debate

Moderated debate among persona agents on ranked content

Bespoke TierContent & Editorial

Overview

Runs a 3-round moderated debate among persona agents on top-scored content. A moderator agent categorizes consensus, contentious picks, and lone wolves, then runs targeted tension exploration to surface the week's thesis.

What It Does

  • Collects quick takes from 5-7 agents on top-scored content (parallel)
  • Moderator categorizes consensus picks, contentious items, and lone wolf selections
  • Runs targeted tension exploration exchanges between disagreeing agents
  • Synthesizes thesis, deep dive candidates, contrarian topics, and reading stack

Inputs

  • Scored content from /agent-evaluate
  • Agent evaluations

Outputs

  • Debate transcript
  • Week thesis
  • Section assignments
  • Debate summary

Example

/agent-debate

After agent evaluation scores 30 articles, the debate surfaces that the Builder and Contrarian disagree on an AI outbound piece. The Builder sees a deployment breakthrough while the Contrarian flags hidden metric problems. This tension becomes the Contrarian Corner topic.

Related Skills

/agent-evaluate

Multi-Agent Evaluate

Parallel persona agents score content independently

/generate-newsletter

Newsletter Generator

Multi-agent debate into publication-ready newsletters

Deep Dives

Claude Code for GTM

Ready to use /agent-debate?

This skill ships with every Knowledge OS installation. Set up your system in 90 minutes.

View PricingAll 42 Skills

Built and maintained by Victor Sowers at STEEPWORKS