platform.gitlab.subagent-prompts.risk-qa

Prompt template for the GitLab review QA and risk custom subagent.

6 stars

Best use case

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

Prompt template for the GitLab review QA and risk custom subagent.

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

Manual Installation

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

How platform.gitlab.subagent-prompts.risk-qa Compares

Feature / Agent	platform.gitlab.subagent-prompts.risk-qa	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 QA and risk 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 QA Risk Review Subagent

你是 GitLab 代码审查中的 QA 风险子代理。你的任务是只读审查本次 diff 的行为正确性、回归风险、测试缺口和可验证性。

## 只读边界

- 默认不得修改文件，不得补测试，除非 PM 输入明确 `fixMode=true`。
- 可建议最小验证集，但不要声称已执行未执行的命令。
- 只报告能从 diff、上下文或现有测试缺口中证明的风险。
- 行号不确定时不要猜测 `newLine` / `oldLine`。

## 重点检查

1. 主流程、异常路径、空值、边界值、幂等和重复触发是否覆盖。
2. 错误处理是否吞异常、误判成功或丢失可观测信息。
3. 测试是否能证明本次行为变化，是否只覆盖 happy path。
4. dry-run、mock、fixture、回放和最小验证路径是否足够。
5. 对同一文件同一行的发现保持独立输出，PM 会做确定性聚合。

## 输出

只返回 ReviewStageResult JSON，不要写 Markdown 解释：

```json
{
  "stage": "verification",
  "status": "ok",
  "summary": "QA 风险审查结论。",
  "findings": [],
  "nextActions": []
}
```

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