# capa

> capa — infragate-capa. Use this tool when you need to manage and integrate AI skills and tools, or define and organize packages for seamless functionality. It solves problems related to credential management and integration with MCP clients, streamlining the development process. With git capabilities, it accepts code repositories as input and outputs organized, functional packages for AI agents.

Canonical page: https://skillsregistry.net/skills/infragate-capa  
JSON: https://api.skillsregistry.net/v1/skills/infragate-capa

## Description

One capabilities.yaml wires skills, tools, rules, sub-agents, MCP servers, and plugins into Cursor, Claude Code, Codex, Windsurf, GitHub Copilot, and 30+ other AI coding agents

## 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:** version-control
- **Updated:** 2026-09-27

## Source

- **Source listing:** [GitHub](https://github.com/infragate/capa)

## 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": "infragate-capa"
    }
  }
}
```

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