platform.gitlab.spec-gate-review

Use to decide whether a GitLab review has enough product and technical context to proceed.

6 stars

Best use case

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

Use to decide whether a GitLab review has enough product and technical context to proceed.

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

Manual Installation

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

How platform.gitlab.spec-gate-review Compares

Feature / Agent	platform.gitlab.spec-gate-review	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?

Use to decide whether a GitLab review has enough product and technical context to proceed.

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.

SKILL.md Source

# Spec Gate Review

Classify the review context as:

- ready: enough information exists to review changed behavior.
- partial: review can proceed with explicit assumptions.
- blocked: missing context would make review misleading.

Do not block merely because a repository lacks formal spec documents. Block only when the MR purpose, expected behavior, or acceptance criteria cannot be inferred from the MR description, linked context, commit messages, and changed code.