RE

requesting-code-review

Standardized review process for verifying code quality and task requirements.

Install

mkdir -p .claude/skills/requesting-code-review-lubonch && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/15668" && unzip -o skill.zip -d .claude/skills/requesting-code-review-lubonch && rm skill.zip

Installs to .claude/skills/requesting-code-review-lubonch

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Use when completing tasks, implementing major features, or before merging to verify work meets requirements
107 chars✓ has a “when” trigger
Beginner

Key capabilities

  • Identify the diff source for code review (commit range or working tree)
  • Run a structured code review checklist against requirements
  • Provide placeholders for describing implemented features, plans, and diff commands
  • Categorize feedback into Critical, Important, and Minor issues
  • Integrate code review into single-flow task execution and plan execution workflows
  • Handle disagreements with reviewers by providing technical reasoning

How it works

The skill facilitates a structured code review process by identifying diff sources, running a checklist against requirements, and categorizing feedback. It integrates into various development workflows.

Inputs & outputs

You give it
A completed task, major feature, or code changes before merging
You get back
A structured code review report with identified issues, assessment, and next steps

When to use requesting-code-review

  • Reviewing code before merge
  • Verifying feature implementation
  • Auditing commit ranges
  • Checking task requirements

About this skill

Requesting Code Review

Run a structured review pass to catch issues before they cascade.

Core principle: Review early, review often.

When to Request Review

Mandatory:

  • After each task in single-flow task execution
  • After completing major feature
  • Before merge to main

Optional but valuable:

  • When stuck (fresh perspective)
  • Before refactoring (baseline check)
  • After fixing complex bug

How to Request

1. Identify the diff source:

# Option A: commit range, only if commits exist and are relevant
BASE_SHA=$(git rev-parse HEAD~1)
HEAD_SHA=$(git rev-parse HEAD)

# Option B: working tree review when there are no intermediate commits
git diff --stat
git diff

2. Run structured code review checklist:

Use requesting-code-review/code-reviewer.md template and review the diff against requirements. In single-flow mode, do not dispatch generic coding agents.

Placeholders:

  • {WHAT_WAS_IMPLEMENTED} - What you just built
  • {PLAN_OR_REQUIREMENTS} - What it should do
  • {BASE_SHA} / {HEAD_SHA} - Starting and ending commits when reviewing a commit range
  • {DIFF_SOURCE} - Description of the diff source when reviewing the working tree
  • {DIFF_COMMANDS} - Exact diff commands used for the review
  • {DESCRIPTION} - Brief summary

3. Act on feedback:

  • Fix Critical issues immediately
  • Fix Important issues before proceeding
  • Note Minor issues for later
  • Push back if reviewer is wrong (with reasoning)

Example

[Just completed Task 2: Add verification function]

You: Let me request code review before proceeding.

[Use working tree diff because no task commit was created]
git diff --stat
git diff

[Run checklist-based review]
  WHAT_WAS_IMPLEMENTED: Verification and repair functions for conversation index
  PLAN_OR_REQUIREMENTS: Task 2 from docs/plans/deployment-plan.md
  DIFF_SOURCE: current working tree
  DIFF_COMMANDS: git diff --stat && git diff
  DESCRIPTION: Added verifyIndex() and repairIndex() with 4 issue types

[Review returns]:
  Strengths: Clean architecture, real tests
  Issues:
    Important: Missing progress indicators
    Minor: Magic number (100) for reporting interval
  Assessment: Ready to proceed

You: [Fix progress indicators]
[Continue to Task 3]

Integration with Workflows

Single-Flow Task Execution:

  • Review after EACH task
  • Catch issues before they compound
  • Fix before moving to next task

Executing Plans:

  • Review after each batch (3 tasks)
  • Get feedback, apply, continue

Ad-Hoc Development:

  • Review before merge
  • Review when stuck

Red Flags

Never:

  • Skip review because "it's simple"
  • Ignore Critical issues
  • Proceed with unfixed Important issues
  • Argue with valid technical feedback

If reviewer wrong:

  • Push back with technical reasoning
  • Show code/tests that prove it works
  • Request clarification

See template at: requesting-code-review/code-reviewer.md

When not to use it

  • When the user wants to skip review because 'it's simple'

Limitations

  • Never skip review because "it's simple"
  • Never ignore Critical issues
  • Never proceed with unfixed Important issues

How it compares

This skill provides a systematic and structured approach to code review, ensuring that work meets requirements and issues are caught early, unlike an informal or ad-hoc review.

Compared to similar skills

requesting-code-review side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
requesting-code-review (this skill)02moReviewBeginner
resolve-conflicts818moReviewIntermediate
dependency-upgrade265moReviewIntermediate
git-commits214moNo flagsBeginner

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry