Conclave

Runs Claude, Gemini and GPT in parallel and synthesizes a debated consensus answer.

Works with setup

Test report

Verdict
Works with setup
Score
7.6/10
Tested
Jul 16, 2026
Environment
Claude Code 2.x (agent harness)
Upstream re-checked
Aug 10, 2026 · 5531af8

Ran it live with no provider keys configured: `doctor` and a real `--depth quick` call both degraded exactly as documented (Gemini/GPT report clean auth errors, Claude's local slot stays fillable) — the JSON contract in SKILL.md matches the actual script output field-for-field.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

  • Installs cleanly 5/5
  • Triggers reliably 5/5
  • Output vs. baseline 5/10
  • Docs & honesty 4/5

What Conclave does

Conclave orchestrates multiple LLMs (Claude, Gemini, GPT, Grok, Llama via OpenRouter) through independent-draft, anonymized cross-critique, and synthesis phases via a bundled Python CLI. Triggers on '/conclave', 'ask the conclave', 'get council opinion', or multi-model debate/architecture/security-review requests; each remote provider needs its own paid API key in a local .env.

How to install Conclave

git clone https://github.com/tommasinigiovanni/conclave.git
mkdir -p ~/.claude/skills
cp -r conclave/. ~/.claude/skills/conclave

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Conclave

  • /conclave Runs Claude, Gemini and GPT in parallel and synthesizes a debated consensus answer.

It also activates on plain-language prompts like these:

  • Ask the AI council to debate whether we should split this into microservices
  • Get GPT, Gemini, and Claude to cross-review my authentication design
  • Run a multi-model debate on the best caching strategy for our API

Frequently asked questions

Is the Conclave skill free?
Yes. The skill itself is free from tommasinigiovanni/conclave. SkillProof publishes the install command and an independent test verdict at no cost.
Does Conclave work with Claude Code?
We tested it with Claude Code 2.x (agent harness) on Jul 16, 2026. Verdict: Works with setup. Ran it live with no provider keys configured: `doctor` and a real `--depth quick` call both degraded exactly as documented (Gemini/GPT report clean auth errors, Claude's local slot stays fillable) — the JSON contract in SKILL.md matches the actual script output field-for-field.
What is the Conclave SkillProof Score?
7.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 4/5.
How do I install Conclave?
Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Conclave with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.