# correction-memory

> correction-memory — donovanpankratz-del-correction-memory. Use this tool when you need to retain and reuse corrections made to an agent's responses, enabling persistent learning and improvement. It solves the problem of transient corrections by storing them for future reference, reducing the need for repeated corrections. This tool accepts agent responses and corrections as inputs and outputs revised, corrected responses for consistent and accurate output.

Canonical page: https://skillsregistry.net/skills/donovanpankratz-del-correction-memory  
JSON: https://api.skillsregistry.net/v1/skills/donovanpankratz-del-correction-memory

## Description

Makes agent corrections persistent and reusable.

## 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:** 2026-09-13

## Source

- **Source listing:** [ClawHub](https://clawskills.sh/skills/donovanpankratz-del-correction-memory)

## 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": "donovanpankratz-del-correction-memory"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/donovanpankratz-del-correction-memory` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/donovanpankratz-del-correction-memory/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