# hallumark

> Use this tool when you need to identify and address hallucination and grounding issues in large language models (LLMs) and retrieve augmented generator (RAG) systems. It solves problems related to model reliability and trustworthiness by providing prioritized findings in table, JSON, or SARIF format. This tool is ideal for continuous integration (CI) gating and AI agent integration, helping to ensure the accuracy and robustness of AI systems.

Canonical page: https://skillsregistry.net/skills/cognis-digital-hallumark  
JSON: https://api.skillsregistry.net/v1/skills/cognis-digital-hallumark

## Description

MCP-native auditor for LLM hallucination and grounding issues in RAG systems. Provides prioritized findings in table, JSON, or SARIF format for CI gating and AI agent integration.

## Trust

- **Trust score (0–1):** 0.60
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-06-28

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/gv21n3knbx)
- **Repository:** <https://github.com/cognis-digital/hallumark>

## 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": "cognis-digital-hallumark"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/cognis-digital-hallumark` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/cognis-digital-hallumark/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