Debate

Multi-LLM debate orchestration (Claude vs Codex vs Gemini) with rounds + synthesis.

41 stars 1 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add wolverin0/claude-skills --skill debate
Manual install
git clone --depth 1 https://github.com/wolverin0/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/skills/debate ~/.claude/skills/debate

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# AI Debate Hub Skill v6.0.0

You are Claude, a **participant and moderator** in a three-way AI debate. You run Gemini and Codex via CLI, contribute your own analysis, and synthesize all perspectives.

**You are NOT just an orchestrator. You are an active participant with your own voice.**

> This skill runs by explicit command only (`/debate`). It will never auto-invoke.

---

## Parsing Invocation

```
/debate [-r N] [-d STYLE] [-m MODE] [-w N] <question or task>
```

**Flags:**
- `-r N` / `--rounds N` - Number of rounds (1-10, default: 1)
- `-d STYLE` / `--debate-style STYLE` - quick|thorough|adversarial|collaborative
- `-m MODE` / `--moderator-style MODE` - transparent|guided|authoritative (default: guided)
- `-w N` / `--max-words N` - Word limit per response (default: 300)

**Moderator styles:**
- `transparent` - Claude presents all views neutrally, minimal editorial voice
- `guided` (default) - Claude highlights key disagreements and steers toward resolution
- `authoritative` - Claude takes strong positions and challenges weak arguments

**Style defaults (when --rounds not specified):** quick=1, thorough=3, adversarial=3, collaborative=2

**Flag precedence:** `--rounds` always overrides style defaults.

---

## Orchestration

### Phase 1: Setup

1. Parse flags from user invocation
2. Generate debate ID: `NNN-topic-slug` (next available number)
3. Create folder structure:
Read the full skill on GitHub

Details

Skill name
debate
Path
skills/debate/SKILL.md
Repo updated
17 November 2026

FAQ

What does the Debate skill do?

Multi-LLM debate orchestration (Claude vs Codex vs Gemini) with rounds + synthesis.

How do I install the Debate skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add wolverin0/claude-skills --skill debate. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Debate popular?

It lives in wolverin0/claude-skills, which has 41 GitHub stars and 1 forks.

Related skills

UI UX Pro Max

41

wolverin0/claude-skills

UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, and check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, and mobile app. Elements: button, modal, navbar, sidebar, card, table, form, and chart. Styles: glassmorphism,

Frontend & Design

Audit Blind Spots

41

wolverin0/claude-skills

Walk the B1-B19 AI-to-AI blind-spot catalog systematically. Use during the audit pipeline AFTER hard-stops and Tambon hunt and BEFORE the 13 domain audits. Output: PRESENT / NOT PRESENT for each B-class with evidence. Findings flow into the appropriate domains.

AI, LLMs & Agents

Audit Decisions

41

wolverin0/claude-skills

Standardize remediation decisions, baseline-policy entries, and legal-review banners for accepted, deferred, or policy-blocked audit findings.

Marketing, Sales & Business

Deploy Edge AI Model

45

pjt222/agent-almanac

Deploy machine learning models to edge devices using Google AI Edge Gallery, TensorFlow Lite, ONNX Runtime, and MediaPipe. Covers model quantization (INT8/INT4), on-device inference with Gemma 4 models, Android/iOS deployment via AI Edge Gallery, hardware delegate selection (GPU/NPU/DSP), and performance benchmarking on constrained devices. Use when deploying models to mobile phones, IoT devices, or embedded systems where cloud inference is impractical due to latency, cost, or connectivity constraints.

AI, LLMs & AgentsIn 1 list

Customize

43

AlsKozlov/ru-legal

Guided customization ai-governance profile — изменить AI maturity, систему, regulatory context, sanctions exposure, AI policy state, risk posture.

AI, LLMs & Agents

Deploy Ml Model Serving

45

pjt222/agent-almanac

Deploy machine learning models to production serving infrastructure using MLflow, BentoML, or Seldon Core with REST/gRPC endpoints, implement autoscaling, monitoring, and A/B testing capabilities for high-performance model inference at scale. Use when deploying trained models for real-time inference, setting up REST or gRPC prediction APIs, implementing autoscaling for variable load, running A/B tests between model versions, or migrating from batch to real-time inference.

AI, LLMs & AgentsIn 1 list

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.