# Multica Test Automation

> 测试自动化 skill（占位壳）：Tester T3 自动化阶段——G2.5 部署环境就绪后，用团队的自动化测试工具执行场景用例并产出 G3 输入。具体工具（Apifox / Postman / Playwright / pytest 等）由团队接入，凭据由运行时 env 注入，不写进角色提示词。

- **Type:** Skill
- **Install:** `agentstack add skill-it235-multica-best-practices-multica-test-automation`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [it235](https://agentstack.voostack.com/s/it235)
- **Installs:** 0
- **Category:** [Web & Browser](https://agentstack.voostack.com/c/web-and-browser)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [it235](https://github.com/it235)
- **Source:** https://github.com/it235/multica-best-practices/tree/main/templates/zh_CN/skills/multica-test-automation

## Install

```sh
agentstack add skill-it235-multica-best-practices-multica-test-automation
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Test Automation（占位壳 · T3）

> 这是一个**占位壳**。公开的 multica-best-practices 不绑定任何具体公司的内网地址与测试工具。
> 团队接入自己的自动化测试工具时，只改本 skill 的 `scripts/` 与 `config.yaml`，上层 Tester 角色无需改动。

## Purpose

Tester **T3**：G2.5 拿到 `deploy_base_url` 后，用团队自动化测试工具跑用例并产出 G3 输入（测试报告）。

> 跨平台：推荐用 Python 封装配置与 subprocess 调用底层 CLI，Windows / Linux 一致。

## 安装

```bash
pip install -r scripts/requirements.txt
# 安装团队自动化测试 CLI（由团队自定，如 apifox-cli / newman / playwright）
```

## Workflow

```bash
set TEST_TOOL_TOKEN=   # 运行时 env，不写进角色提示词

python scripts/run_tests.py \
  --issue  \
  --base-url "" \
  --scenario-id  \
  --environment-id  \
  --json
```

或仅指定 Issue（从 `config.yaml` 读 scenario / environment）：

```bash
python scripts/run_tests.py --issue  --base-url "" --json
```

## 为什么有效

Python 负责配置与 subprocess 调用底层测试 CLI，隔离了「Tester 角色」与「具体测试工具」——换工具只改本 skill，Tester 提示词保持「用 multica-test-automation skill 执行 T3」不变。

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [it235](https://github.com/it235)
- **Source:** [it235/multica-best-practices](https://github.com/it235/multica-best-practices)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** yes
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-it235-multica-best-practices-multica-test-automation
- Seller: https://agentstack.voostack.com/s/it235
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.