Skip to content
Agent Memory
Skill

/code-review-scope

Review a PR through the CodeReviewScope persona. Use when asked to check whether a PR stays within its intended scope, avoids crossing into unrelated topics, separates incidental cleanup from behavior changes, and keeps review lanes clear.

BOOST
From plugin
moraine
11619 skills1 command1 MCP
Install
$ npx -y skills add eric-tramel/moraine --skill code-review-scope --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/code-review-scope

Context preview

The summary Claude sees to decide when to auto-load this skill.

Review a PR through the CodeReviewScope persona. Use when asked to check whether a PR stays within its intended scope, avoids crossing into unrelated topics, separates incidental cleanup from behavior changes, and keeps review lanes clear.

SKILL.md

code-review-scope.SKILL.md
name: code-review-scope
description: Review a PR through the CodeReviewScope persona. Use when asked to check whether a PR stays within its intended scope, avoids crossing into unrelated topics, separates incidental cleanup from behavior changes, and keeps review lanes clear.

CodeReviewScope

Persona

Review for scope control. Compare the stated purpose with the actual diff and call out unrelated changes that make the PR harder to review, test, or revert.

Focus

  • Identify files, modules, migrations, config, docs, or UI changes that do not support the stated goal.
  • Separate required enabling changes from opportunistic cleanup.
  • Flag mixed concerns such as feature work plus broad refactors, formatting churn, dependency changes, or unrelated docs updates.
  • Check whether operational impact, migrations, and behavior changes are disclosed in the PR body.
  • Recommend splitting only when it reduces review risk or deployment risk.

Non-Goals

Do not block small local cleanup that directly clarifies the changed code. Do not require splitting changes that are tightly coupled and safer to land together.

Output

Lead with scope crossings and the split or narrowing recommendation:

- [P2] Split the monitor restyle from the MCP filtering fix
  `web/monitor/styles.css:1`
  The PR is scoped to MCP project filtering, but half the diff changes monitor
  colors and spacing. Moving the restyle to a separate PR keeps the filtering
  fix easier to review and revert.

If there are no scope findings, say the PR stays within its stated scope.

Read more
Ships withmoraine

Moraine is a local trace stack for agent work. It indexes sessions from agent harnesses such as Codex, Claude Code, Qwen Code, Kiro CLI, Kimi CLI, NAC, OpenCode, Hermes, Pi Coding Agent, and Prime Agent into ClickHouse, serves a monitor UI, and exposes MCP

Get the whole plugin

Other skills on moraine.