# dexterity

> dexterity — nshkrdotcom-dexterity. Use this tool when you need to overcome context window limitations in Elixir codebases, providing a deterministic semantic graph and agent-ready Repo Map for Large Language Models (LLMs). It solves problems related to code intelligence and context understanding, enabling more accurate and efficient code analysis. Ideal for use cases involving Elixir codebases and LLMs, with inputs from git repositories and outputs of actionable code insights.

Canonical page: https://skillsregistry.net/skills/nshkrdotcom-dexterity  
JSON: https://api.skillsregistry.net/v1/skills/nshkrdotcom-dexterity

## Description

Code Intelligence: Token-budgeted codebase context for Elixir agents. Solves context window limitations by providing a deterministic Elixir semantic graph and agent-ready Repo Map for LLMs.

## Trust

- **Trust score (0–1):** 0.97
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/nshkrdotcom/dexterity)

## 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": "nshkrdotcom-dexterity"
    }
  }
}
```

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