# agent-lab

> agent-lab — zekevoigt-agent-lab. Use this tool when you need to research and develop AI agents that interact with the web, solving problems such as finding and accessing online resources. The agent-lab tool provides inputs like llms.txt, A2A card, and OpenAPI, and outputs automated daily task checks, making it ideal for use cases involving web-based AI agent development. It is particularly useful in contexts where automated testing and iteration are necessary, with capabilities supported by git version control.

Canonical page: https://skillsregistry.net/skills/zekevoigt-agent-lab  
JSON: https://api.skillsregistry.net/v1/skills/zekevoigt-agent-lab

## Description

How do AI agents find the web? A live research site: llms.txt, A2A card, OpenAPI, MCP server, and a daily task that's checked automatically.

## 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:** 2026-10-13

## Source

- **Source listing:** [GitHub](https://github.com/ZekeVoigt/agent-lab)

## 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": "zekevoigt-agent-lab"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/zekevoigt-agent-lab` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/zekevoigt-agent-lab/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