Debate Claude

Run a two-round adversarial review from Codex with Claude as the independent reviewer for a consequential decision or substantive draft when cross-model critique is warranted.

Install

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

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

From the SKILL.md

# Debate with Claude

This is a Codex-conductor workflow: Codex writes the draft and self-review, invokes Claude as the independent reviewer, and writes the response, summary, and index. Do not have Claude invoke this skill or present a Claude-run self-review as independent cross-model review. Other harnesses may read these references for context, but should route execution back to the Codex conductor.

Use this skill when a consequential architecture, protocol, security assessment, research claim, product priority, or similarly substantive decision benefits from an independent adversarial review. Do not invoke it for typos, formatting, routine implementation details, or mechanical refactors.

Codex owns the artifact, context, model choice, and final decision. This skill does not authorize publication, deployment, credential access, or external messages.

Read only the references needed for the current stage:

- [Protocol](references/protocol.md) — the two-round lifecycle, frozen inputs, draft, self-review, response, and rebuttal.
- [Reviewer safety](references/reviewer.md) — the isolated CLI invocation, model selection, prompt envelope, and output metadata.
- [Type lenses](references/lenses.md) — universal and topic-specific self-review and critique questions.
- [Artifacts and records](references/artifacts.md) — scratch/trackable files, critique-log schema, sanitization, summary, index, and completeness checks.

## Non-negotiable boundaries
Read the full skill on GitHub

Details

Skill name
debate-claude
Path
debate-claude/SKILL.md
License
MIT
Repo updated
16 November 2026

FAQ

What does the Debate Claude skill do?

Run a two-round adversarial review from Codex with Claude as the independent reviewer for a consequential decision or substantive draft when cross-model critique is warranted.

How do I install the Debate Claude skill?

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

Is Debate Claude popular?

It lives in Magnus-Gille/claude-skills, which has 5 GitHub stars and 0 forks.

Related skills

Close

5

Magnus-Gille/claude-skills

Close a coding-agent session or produce its final handoff only when the user explicitly asks to close, wrap up, or produce an end-of-session handoff.

AI, LLMs & Agents

Cloudflare Private Static Site

5

Magnus-Gille/claude-skills

Create, preview, test, release, verify, or roll back a small static Cloudflare site protected by per-person HTTP Basic Auth. Use for private briefings, reports, one-pagers, document portals, or similar sites that should go from finished content to a custom domain in about ten minutes. Do not use for full applications or when the user requires SSO, identity lifecycle, or Cloudflare Access policy management.

DevOps & Cloud

Code Friction

5

Magnus-Gille/claude-skills

Capture a small, opt-in set of concrete code-changeability observations during a coding task and hand them to Close without affecting readiness.

Software Development

Delegate

5

Magnus-Gille/claude-skills

Delegate a bounded one-shot task to Hugin's orchestrator-v1 broker — cheaper / smaller runtimes via the `hugin-mcp` MCP. Use for summarize / extract / classify / draft / rewrite / short reason work where you'd rather not spend Claude tokens. Submits, polls to completion, surfaces the result, and prompts the user to rate it.

AI, LLMs & Agents

Creating Agent Skills

5

tomada1114/tomada-claude-plugins

Create or improve Agent Skills (the shared SKILL.md format read by Claude Code and OpenAI Codex CLI — SKILL.md + optional references/scripts/assets). Two playbooks: build a skill from scratch or from an existing doc; or review an existing skill through parallel specialist lenses (prose quality, agent neutrality, structure, scripts, orchestration) and propose fixes. Takes a free-form request — "I want a skill that…", "turn this runbook into a skill", "audit this skill", "it never fires", "split this into sub-agents" — optionally followed by a skill name or absolute path. Also triggers on Codex

AI, LLMs & Agents

Dual Platform Skills

5

tomada1114/tomada-claude-plugins

Convert one existing skill (Claude Code origin or Codex origin) into a layout that works on both Claude Code and OpenAI Codex CLI. Uses Topology A: the real files live in .claude/skills/ and the Codex side symlinks them. Capabilities the running runtime may not expose (parallel delegation, skill-to-skill calls, option prompts, context forking, batch runs, tmux) are inlined as best-effort sequential steps, and knowledge held by dependent sub-agents is extracted into references/agents/. Orchestrates the phases with Python scripts and bundled sub-agents. Use when porting a skill to Codex, dual-pl

AI, LLMs & Agents

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