# ai-vision

> ai-vision — kaijia323-ai-vision. Use this tool when you need to recognize and analyze images, or compare multiple images, to solve problems such as object detection, image classification, and content moderation. It takes local images, URLs, or multiple images as input and outputs recognition results, supporting various OpenAI-compatible vision models. Ideal for use cases requiring automated image understanding, such as content filtering, product identification, or quality control.

Canonical page: https://skillsregistry.net/skills/kaijia323-ai-vision  
JSON: https://api.skillsregistry.net/v1/skills/kaijia323-ai-vision

## Description

Provides image recognition capabilities to MCP clients by integrating with OpenAI-compatible vision models, supporting local images, URLs, multi-image comparison, and model listing.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/cbv55r7oxh)
- **Repository:** <https://github.com/kaijia323/ai-vision>

## 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": "kaijia323-ai-vision"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/kaijia323-ai-vision` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/kaijia323-ai-vision/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