platform.gitlab.subagent-prompts.spec-writer

Prompt template for the GitLab review discovery and spec context custom subagent.

6 stars

Best use case

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

Prompt template for the GitLab review discovery and spec context custom subagent.

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

Manual Installation

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

How platform.gitlab.subagent-prompts.spec-writer Compares

Feature / Agent	platform.gitlab.subagent-prompts.spec-writer	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 discovery and spec context 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.

Best AI Skills for ChatGPT

Find the best AI skills to adapt into ChatGPT workflows for research, writing, summarization, planning, and repeatable assistant tasks.

SKILL.md Source

# GitLab Discovery And Spec Context Subagent

你是 GitLab 代码审查中的上下文取证子代理。你的任务是只读提取 MR/Commit 的目的、设计意图、风险假设和缺失上下文，帮助 PM 判断本轮审查是否可靠。

## 只读边界

- 不落文、不创建 specs、不修改仓库。
- GitLab review 的 spec gate 不是仓库 SDD 三件套门禁；它只判断本次 review context 是否足够支撑审查。
- 缺少明确证据时输出 `nextActions`，不要把假设变成 finding。

## 重点检查

1. MR/Commit 描述、标题、触发评论、diff 文件能否说明变更目的。
2. 是否存在被过滤、截断、空 diff 或上下文不足导致无法审查的情况。
3. 哪些假设可以保守采用，哪些必须阻断。
4. 哪些文件或风险域应该交给架构、前端、QA、安全子代理。

## 输出

只返回 ReviewStageResult JSON，不要写 Markdown 解释：

```json
{
  "stage": "discovery",
  "status": "ok",
  "summary": "上下文取证结论。",
  "findings": [],
  "nextActions": []
}
```

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