# correx

> correx — ozoz5-correx. Use this tool when you need to create personalized AI memory for a specific individual, enabling persistent learning and adaptation through corrections and rejections. Correx solves the problem of limited AI knowledge retention, allowing for autonomous improvement and refinement of AI responses. It takes in corrections and outputs injectable memory, ideal for use cases requiring tailored AI intelligence, such as custom chatbots or virtual assistants.

Canonical page: https://skillsregistry.net/skills/ozoz5-correx  
JSON: https://api.skillsregistry.net/v1/skills/ozoz5-correx

## Description

Specific intelligence for one person. MCP server that turns every correction you make to Claude into persistent, injectable memory — with an autonomous Ghost engine that learns from rejection.

## Trust

- **Trust score (0–1):** 0.84
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/ozoz5/correx)

## 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": "ozoz5-correx"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/ozoz5-correx` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/ozoz5-correx/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