# geml

> geml — geml-spec-geml. Use this tool when you need to collaborate with both humans and AI agents on a document, requiring a format that is legible for people and addressable, verifiable, and versioned for machines. GEML provides a plain text format with a single typed block for organization and a .gemlhistory sidecar for versioning. It is ideal for use cases where transparency, accountability, and machine readability are crucial, such as in git-based workflows.

Canonical page: https://skillsregistry.net/skills/geml-spec-geml  
JSON: https://api.skillsregistry.net/v1/skills/geml-spec-geml

## Description

One format, two readers. People and AI agents now co-write the same document. Legible for people; addressable, verifiable, and versioned for machines.  GEML is plain text — organized by one typed block for everything, remembered by a .gemlhistory sidecar.

## Trust

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

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/geml-spec/geml)

## 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": "geml-spec-geml"
    }
  }
}
```

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