DE
debate
| Role | Responsibility | |------|----------------| | **Architect A** | Propose practical, proven solution | | **Architect B** | Propose alternative approach | | **Critic C** | Identify weaknesses and gaps | | **Devil's Advocate D** | Challenge assumptions | | **Lead** | Moderate
Install
mkdir -p .claude/skills/debate && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/14207" && unzip -o skill.zip -d .claude/skills/debate && rm skill.zipInstalls to .claude/skills/debate
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
| Role | Responsibility | |------|----------------| | **Architect A** | Propose practical, proven solution | | **Architect B** | Propose alternative approach | | **Critic C** | Identify weaknesses and gaps | | **Devil's Advocate D** | Challenge assumptions | | **Lead** | Moderate280 chars · catalog descriptionno explicit “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
About this skill
Debate Skill
Overview
Council-style debate skill for decision making with multiple perspectives.
Modes
IDE Mode (Single Model)
One model plays multiple roles sequentially.
Runner Mode (Multi-Model)
Multiple models participate as different council members.
Council Roles
| Role | Responsibility |
|---|---|
| Architect A | Propose practical, proven solution |
| Architect B | Propose alternative approach |
| Critic C | Identify weaknesses and gaps |
| Devil's Advocate D | Challenge assumptions |
| Lead | Moderate discussion and make final decision |
Scoring Rubric
| Criterion | Weight | Description |
|---|---|---|
| constraint_compliance | 0.30 | Fits within project constraints |
| practicality | 0.25 | Can be implemented effectively |
| risk_awareness | 0.25 | Risks identified and mitigated |
| clarity | 0.20 | Clear and understandable |
Usage
# Run debate in IDE mode (single model)
node .agent/skills/debate/scripts/debate.js --mode ide --input research.shortlist.json
# Run debate with config file
node .agent/skills/debate/scripts/debate.js --config debate-config.json
Inputs
20_research/research.shortlist.json20_research/research.reuse_assessment.json20_research/research.patterns.md
Outputs
30_debate/debate.inputs_for_spec.json30_debate/debate.decision.md
Output Schema
See schemas/debate.inputs_for_spec.schema.json
Decision Lock
- Once decision is locked, changes require re-running Debate
- Prevents silent scope changes during implementation