# safety-checks

> safety-checks — leegitw-safety-checks. Use this tool when you need to verify the trustworthiness of models and ensure runtime safety. It provides core functionality for model pinning, fallbacks, and runtime safety validation, solving problems related to model reliability and security. By taking in models as input and outputting validation results, it helps prevent potential risks and errors in various applications, particularly in critical or high-stakes contexts.

Canonical page: https://skillsregistry.net/skills/leegitw-safety-checks  
JSON: https://api.skillsregistry.net/v1/skills/leegitw-safety-checks

## Description

Verify before you trust — model pinning, fallbacks, and runtime safety validation.

## Trust

- **Trust score (0–1):** 0.30
- **Verification tier:** unverified
- **Last scanned:** 2026-08-23

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** instructions
- **Runtime environment:** llm
- **Category:** other
- **Updated:** 2026-09-27

## Source

- **Source listing:** [ClawHub](https://clawskills.sh/skills/leegitw-safety-checks)

## 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": "leegitw-safety-checks"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/leegitw-safety-checks` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/leegitw-safety-checks/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