# LLM Council

> Use this tool when you need to leverage the collective intelligence of multiple AI models to generate well-informed and robust responses. The LLM Council solves complex problems by combining the outputs of frontier models through structured deliberation protocols, addressing challenges such as inconsistent or biased responses. It accepts natural language queries as input and produces a synthesized response as output, ideal for use cases requiring high-stakes decision-making or critical thinking.

Canonical page: https://skillsregistry.net/skills/rachittshah-llm-council  
JSON: https://api.skillsregistry.net/v1/skills/rachittshah-llm-council

## Description

Queries frontier models (GPT-5, Gemini 2.5, Claude) in parallel and combines responses through structured deliberation protocols. Supports voting with anonymous peer review, multi-round debate with adaptive KS-statistic stopping, chairman synthesis, peer critique, adversarial red teaming, and model-as-verifier cross-checking. Includes cost estimation and configurable council composition.

## Trust

- **Trust score (0–1):** 0.90
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/rachittshah-llm-council)
- **Repository:** <https://github.com/rachittshah/llmcouncil>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "rachittshah-llm-council"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/rachittshah-llm-council` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/rachittshah-llm-council/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt