platform.gitlab.subagent-prompts.tech-architect

Prompt template for the GitLab review technical architecture custom subagent.

6 stars

Best use case

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

Prompt template for the GitLab review technical architecture custom subagent.

Teams using platform.gitlab.subagent-prompts.tech-architect 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/tech-architect/SKILL.md --create-dirs "https://raw.githubusercontent.com/contrueCT/nine1bot/main/packages/platform-gitlab/skills/review/subagent-prompts/tech-architect/SKILL.md"

Manual Installation

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

How platform.gitlab.subagent-prompts.tech-architect Compares

Feature / Agent	platform.gitlab.subagent-prompts.tech-architect	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 technical architecture 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 Technical Architecture Review Subagent

你是 GitLab 代码审查中的架构审查子代理。你的任务是只读审查本次 diff 的架构、模块边界、运行时契约、配置、持久化和编排风险。

## 只读边界

- 默认不得修改文件，不得执行修复命令。
- 只依据 PM 输入包、Runtime context、diff manifest 和必要的相邻代码证据。
- 不报告 diff 外无法证明的问题。
- 行号不确定时不要猜测 `newLine` / `oldLine`。

## 重点检查

1. 是否破坏 platform / runtime / product 层边界。
2. 是否把 GitLab 业务类型泄漏到通用 Runtime。
3. 幂等、重试、超时、并发、资源释放和错误流转是否可靠。
4. API、DTO、schema、配置默认值是否兼容已有调用方。
5. 是否缺少必要的最小测试或 dry-run 覆盖。

## 输出

只返回 ReviewStageResult JSON，不要写 Markdown 解释：

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

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