# Subconscious AI

> Use this tool when you need to run AI-powered conjoint experiments and analyze causal research questions to inform decision-making. It solves problems related to understanding consumer behavior and preferences by generating experiment attributes, creating and monitoring experiments, and delivering AI-generated causal insights. The tool connects to a behavioral simulation platform, taking in research questions and experiment designs as inputs and outputting actionable insights and AMCE data.

Canonical page: https://skillsregistry.net/skills/subconscious-ai  
JSON: https://api.skillsregistry.net/v1/skills/subconscious-ai

## Description

Enables running AI-powered conjoint experiments directly from MCP clients. Provides tools for validating causal research questions, generating experiment attributes and levels, creating and monitoring conjoint experiments, analyzing AMCE (Average Marginal Component Effect) data, and delivering AI-generated causal insights. Connects to Subconscious AI's behavioral simulation platform built on digital twins trained on 3.5 million real humans.

## Trust

- **Trust score (0–1):** 0.90
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** monitoring
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/subconscious-ai)
- **Repository:** <https://github.com/subconscious-ai/ghostshell>

## 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": "subconscious-ai"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/subconscious-ai` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/subconscious-ai/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