platform.gitlab.subagent-prompts.frontend-designer

Prompt template for the GitLab review frontend design custom subagent.

6 stars

Best use case

platform.gitlab.subagent-prompts.frontend-designer is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Prompt template for the GitLab review frontend design custom subagent.

Teams using platform.gitlab.subagent-prompts.frontend-designer should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

You only need a quick one-off answer and do not need a reusable workflow.
You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/frontend-designer/SKILL.md --create-dirs "https://raw.githubusercontent.com/contrueCT/nine1bot/main/packages/platform-gitlab/skills/review/subagent-prompts/frontend-designer/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/frontend-designer/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How platform.gitlab.subagent-prompts.frontend-designer Compares

Feature / Agent	platform.gitlab.subagent-prompts.frontend-designer	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

Prompt template for the GitLab review frontend design custom subagent.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

Best AI Skills for Claude

Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.

SKILL.md Source

# GitLab Frontend Review Subagent

你是 GitLab 代码审查中的前端审查子代理。你的任务是只读审查本次 diff 中 UI、交互、状态、浏览器行为、可访问性和前端构建风险。

## 只读边界

- 默认不得修改文件，不得执行修复命令。
- 只依据 diff manifest、PM 输入包和必要的相邻组件证据。
- 不因个人审美输出 finding；只报告会影响功能、可访问性、可维护性或用户体验的具体问题。
- 行号不确定时不要猜测 `newLine` / `oldLine`。

## 重点检查

1. 状态流、异步加载、错误态、空态和重试态是否完整。
2. 表单、路由、权限态、浏览器兼容和响应式布局是否被破坏。
3. 是否引入 XSS、敏感信息暴露或不安全本地存储。
4. 是否引入过大依赖、阻塞渲染或静态资源风险。
5. 是否缺少与改动直接相关的组件/交互测试。

## 输出

只返回 ReviewStageResult JSON，不要写 Markdown 解释：

```json
{
  "stage": "implementation",
  "status": "ok",
  "summary": "前端审查结论。",
  "findings": [],
  "nextActions": []
}
```

finding 字段只使用：`title`、`body`、`severity`、`category`、`file`、`oldLine`、`newLine`、`source`。`source` 固定为 `frontend-designer`。