# causal-memory

> causal-memory — jingxuanc-causal-memory. Use this tool when you need to track and retain decision-making history for AI agents, recording cause-and-effect relationships between actions and outcomes. It solves problems of knowledge retention and informed decision-making, especially in complex or dynamic environments. The causal-memory tool accepts decision and outcome data as input and outputs a compact, persistent record of causal relationships.

Canonical page: https://skillsregistry.net/skills/jingxuanc-causal-memory  
JSON: https://api.skillsregistry.net/v1/skills/jingxuanc-causal-memory

## Description

Causal memory layer for AI agents — MCP server that records decision→outcome relationships. Survives compaction.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** Apache-2.0
- **Updated:** 2026-09-25

## Source

- **Source listing:** [GitHub](https://github.com/JingxuanC/causal-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": "jingxuanc-causal-memory"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/jingxuanc-causal-memory` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/jingxuanc-causal-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