# klaar

> klaar — nma-vc-klaar. Use this tool when you need to optimize AI coding agents and manage model context protocols locally, solving issues with coding efficiency and data consistency. It takes in coding projects and model configurations as inputs and outputs optimized code and synchronized model contexts. Ideal for use in development environments where git version control and hybrid-search memory are essential.

Canonical page: https://skillsregistry.net/skills/nma-vc-klaar  
JSON: https://api.skillsregistry.net/v1/skills/nma-vc-klaar

## Description

Universal local-first AI coding agent optimizer and Model Context Protocol (MCP) server backed by SurrealDB hybrid-search memory and pre-push checks.

## 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:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/NMA-vc/klaar)

## 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": "nma-vc-klaar"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/nma-vc-klaar` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/nma-vc-klaar/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