# modelwatch

> modelwatch — bch1212-modelwatch. Use this tool when you need to monitor and detect continuous behavioral drift in Large Language Model (LLM) applications, solving problems related to model performance degradation and data drift. It provides real-time insights into model behavior, accepting LLM application data as input and outputting alerts and notifications when drift is detected. Ideal for use in production environments where LLM models are deployed, to ensure reliability and accuracy over time.

Canonical page: https://skillsregistry.net/skills/bch1212-modelwatch  
JSON: https://api.skillsregistry.net/v1/skills/bch1212-modelwatch

## Description

Continuous behavioral drift monitoring for LLM applications.

## Trust

- **Trust score (0–1):** 0.67
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** ai-ml
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/bch1212/modelwatch)

## 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": "bch1212-modelwatch"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/bch1212-modelwatch` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/bch1212-modelwatch/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