# OpenSkill

> Use this tool when you need to execute Anthropic Skills across various coding agents, or require sandboxed skill execution with management capabilities. OpenSkill solves the problem of skill accessibility and security by utilizing Docker containers, providing a unified interface for skill management. It is ideal for use cases where multiple coding agents need to access and execute skills in a controlled environment.

Canonical page: https://skillsregistry.net/skills/agiflow-openskill  
JSON: https://api.skillsregistry.net/v1/skills/agiflow-openskill

## Description

An MCP server that makes Anthropic Skills universally accessible across coding agents, enabling sandboxed execution of skills in Docker containers with skill management and MCP tools.

## Trust

- **Trust score (0–1):** 0.67
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** cloud-infra
- **Updated:** 2026-09-01

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/a0imfzqbw5)
- **Repository:** <https://github.com/AgiFlow/openskill>

## 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": "agiflow-openskill"
    }
  }
}
```

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