# scriptorium

> Use this tool when you need to collaboratively manage and document large language models (LLMs) within your team, leveraging a self-hosted wiki solution that integrates with Git for version control. It solves problems of knowledge sharing, model documentation, and team collaboration, providing a centralized repository for LLM-related information. With inputs from Git and outputs in a searchable wiki format, it's ideal for teams working on complex LLM projects requiring transparent knowledge management.

Canonical page: https://skillsregistry.net/skills/zyx1121-scriptorium  
JSON: https://api.skillsregistry.net/v1/skills/zyx1121-scriptorium

## Description

Self-hosted LLM wiki for teams — Karpathy's pattern over Postgres + MCP.

## Trust

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

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** database
- **Updated:** 2026-05-07

## Source

- **Source listing:** [GitHub](https://github.com/zyx1121/scriptorium)

## 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": "zyx1121-scriptorium"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/zyx1121-scriptorium` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/zyx1121-scriptorium/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