# ChatCrystal

> ChatCrystal — zengliangyi-chatcrystal. Use this tool when you need to organize and make sense of complex AI conversations, and crystallize knowledge from various sources like Claude Code, Cursor, or Codex CLI. ChatCrystal solves the problem of information overload by summarizing conversations with Large Language Models (LLM) and enabling semantic search. It takes in conversation data as input and outputs summarized, searchable knowledge that can be managed through git integration.

Canonical page: https://skillsregistry.net/skills/zengliangyi-chatcrystal  
JSON: https://api.skillsregistry.net/v1/skills/zengliangyi-chatcrystal

## Description

Local-first AI PKM for coding conversations: import Claude Code/Cursor/Codex, distill notes, semantic search, tag graph, MCP memory.

## Trust

- **Trust score (0–1):** 0.65
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** ai-ml
- **Updated:** 2026-09-22

## Source

- **Source listing:** [GitHub](https://github.com/ZengLiangYi/ChatCrystal)

## 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": "zengliangyi-chatcrystal"
    }
  }
}
```

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