# Omni NLI by CogitatorTech

> Use this tool when you need to analyze relationships between text pairs and determine if a hypothesis is supported or contradicted by a premise. It solves problems in text understanding, sentiment analysis, and information retrieval by classifying entailment, contradiction, or neutrality between text pairs. It takes in premise-hypothesis text pairs as input and outputs a classification of their relationship, making it useful for applications in question answering, text summarization, and dialogue systems.

Canonical page: https://skillsregistry.net/skills/gh-cogitatortech-omni-nli  
JSON: https://api.skillsregistry.net/v1/skills/gh-cogitatortech-omni-nli

## Description

Provides natural language inference capabilities for determining relationships between text pairs. Classifies whether a hypothesis is entailed by, contradicts, or is neutral with respect to a given premise using machine learning models.

## Trust

- **Trust score (0–1):** 0.64
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-02

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/gh-cogitatortech-omni-nli)
- **Repository:** <https://github.com/cogitatortech/omni-nli>

## 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": "gh-cogitatortech-omni-nli"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/gh-cogitatortech-omni-nli` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/gh-cogitatortech-omni-nli/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