# VectorDecisions

> Use this tool when you need to ensure AI model compliance and governance, as it solves problems related to non-compliant agent actions and regulatory auditing by evaluating model behaviors and detecting policy violations through the GATRI trust scoring framework. It takes in AI model behaviors and policy rules as inputs and outputs trust scores and compliance audits, with a kill-switch mechanism for halting non-compliant actions. Use VectorDecisions in contexts where EU AI Act compliance is required, such as auditing and risk management.

Canonical page: https://skillsregistry.net/skills/nikitadatar-vectordecisions  
JSON: https://api.skillsregistry.net/v1/skills/nikitadatar-vectordecisions

## Description

VectorDecisions provides AI governance infrastructure implementing the GATRI trust scoring framework to evaluate model behaviors and detect policy violations. It includes a kill-switch mechanism for halting non-compliant agent actions and tooling for EU AI Act compliance auditing integrated with Claude.

## Trust

- **Trust score (0–1):** 1.00
- **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/nikitadatar-vectordecisions)
- **Repository:** <https://github.com/nikitadatar/vectordecisions-mcp-server>

## 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": "nikitadatar-vectordecisions"
    }
  }
}
```

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