debate

Original：🇨🇳 Chinese

Translated

Multi-AI Agent P2P Debate. Suitable for technical solution stress testing, multi-perspective collision, and design decision convergence. Use it when you want a solution to be challenged or to understand the pros and cons of different technical routes. Triggered when mentioning "debate", "agent discussion", "multi-angle analysis", or "start a team".

2installs

Source9ashwin/aswin-skills

Added on2026-06-02

NPX Install

npx skill4agent add 9ashwin/aswin-skills debate

SKILL.md Content (Chinese)

View Translation Comparison →

Debate — Multi-AI Agent P2P Debate

Deploy 3 AI Agents (Architect, Skeptic, Practical Engineer) to conduct P2P mutual debate around a topic, and automatically archive all messages to a document.

Pre-checks

Before starting, confirm that the

env

in

~/.claude/settings.json

includes:

json

"CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1"

If missing, ask the user to add it and restart Claude Code first.

Process

1. Clarify the Topic

Confirm the debate topic with the user. Ask one question at a time, don't bombard. Understand the following dimensions:

What is the specific debate topic?
Are there any particular controversial points to focus on?
Desired debate mode (see below)?

2. Select Mode

Provide three modes for the user to choose from:

Mode	Roles	Applicable Scenarios
Tri-perspective (Default)	Architect + Skeptic + Practical Engineer	Technical solution exploration, architecture design discussion
Adversarial Debate	Proponent + Opponent + Referee	When there is a clear binary choice (choose A or B)
Devil's Advocate	Proposer + Skeptic	When an existing solution needs stress testing

3. Create Team & Agents

TeamCreate → Agent × N（run_in_background: true）

The prompt for each agent must include:

Role definition and discussion topic
List of teammate names
Clear instruction: After completing the analysis, use SendMessage to send to both teammates and team-lead (CC to record the full text)
Response instruction: After receiving a message from a teammate, reply directly to them and CC the team-lead
Must not wait for team-lead instructions, take the initiative to send messages

4. Monitoring & Recording

All messages CC'd to the team-lead are appended in real-time to
```
debate-<topic>.md
```
in the project root directory
Only summaries of P2P messages without CC can be seen, full text cannot be recorded — remind agents to CC
If an agent remains idle 3 times without producing content, actively send a SendMessage to urge them

5. Advance the Debate

First round: Each agent independently presents initial views
Subsequent rounds: Agents spontaneously comment and debate. If you find a thread is broken, manually send a SendMessage to re-trigger
When the debate reaches diminishing returns (repeated arguments, no new points), prompt the user to conclude

6. Conclude & Archive

Ask each agent to provide a final conclusion
Organize the consensus framework and unresolved issues
Shut down agents (shutdown_request → TeamDelete)
Finalize the document

Document Format

The debate document should include:

Pre-configuration instructions
Agent speeches for each round (marked with Sender → Receiver)
Debate connection graph
Final consensus framework
Key conclusion table (Controversial Point / Convergence Direction / Status)
Debate statistics

Known Issues

Experimental feature, agent responses are occasionally unstable
Agents may not respond to shutdown, will be automatically recycled when the session ends
Full text of P2P messages without CC cannot be obtained
Agents will not actively initiate multi-round conversations, clear instructions in the prompt are required