# semantic-dog

> Use this tool when you need to automatically detect corruption in media files beyond simple checksum verification. The semantic-dog tool parses various file types, including images, videos, and documents, to identify real corruption, providing a robust solution for maintaining data integrity. It offers a command-line interface, FastAPI integration, customizable alerts, and compatibility with AI agents like Claude for seamless integration into existing workflows.

Canonical page: https://skillsregistry.net/skills/kytmanov-semantic-dog  
JSON: https://api.skillsregistry.net/v1/skills/kytmanov-semantic-dog

## Description

Your NAS media library’s smart watchdog. Parses images, RAW, videos, PDFs & docs to catch real corruption — not just checksums. CLI + FastAPI + alerts + Claude-ready MCP for AI agents.

## Trust

- **Trust score (0–1):** 0.00
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/kytmanov/semantic-dog)

## 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": "kytmanov-semantic-dog"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/kytmanov-semantic-dog` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/kytmanov-semantic-dog/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