mcpbeat Sign in

Reviewing Changes Agent Skill

Performs comprehensive code reviews for Bitwarden iOS projects, verifying architecture compliance, style guidelines, compilation safety, test coverage, and security requirements. Use when reviewing pull requests, checking commits, analyzing code changes, verifying Bitwarden coding standards, evaluating unidirectional data flow pattern, checking services container dependency injection usage, reviewing security implementations, or assessing test coverage. Automatically invoked by CI pipeline or manually for interactive code reviews.

11k tokens
context cost
the whole folder, loaded on every use
13
files
instructions only
0
copies elsewhere
how many repositories repackaged it
653
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/bitwarden/android --skill reviewing-changes

What comes with it

38 145 bytes besides the instruction
checklists/bug-fix.md
checklists/dependency-update.md
checklists/feature-addition.md
checklists/ui-change.md
examples/annotated-example.md
reference/common-issues.md
reference/feedback-psychology.md
reference/ios-architecture-patterns.md
reference/ios-security-patterns.md
reference/ios-style-patterns.md
reference/ios-testing-patterns.md
reference/priority-framework.md

The instruction itself

8 sections, as written by the author

Reviewing Changes — Bitwarden iOS

Instructions

Work systematically through each step before providing feedback. Each checklist loads only the relevant review strategy for the change type detected.

Step 1: Retrieve Additional Details

Fetch any additional context using available tools (JIRA MCP, GitHub API). If the PR title and description don't provide enough context, request:

  • A link to the JIRA ticket
  • A GitHub issue reference
  • More detail in the PR description

iOS-specific metadata checks:

  • Screenshots required for any *View.swift changes that affect visible UI — flag as ❓ if absent
  • If new *Processor.swift or *Service.swift is added with no test file, flag as ❓

Step 2: Detect Change Type

iOS-specific patterns:

  • Feature Addition: New *Coordinator.swift, *Processor.swift, *View.swift (full file-set); new screen or flow
  • Bug Fix: Targeted changes to existing *Processor.swift, *Service.swift, or *Repository.swift files
  • UI Change: Changes only to *View.swift files; no business logic changes
  • Refactoring: Renamed/restructured files without new user-visible behavior
  • Dependency Update: Changes to Mintfile, project-*.yml version references, Package.swift
  • Infrastructure: Changes to Scripts/, Configs/, .github/, fastlane/

Step 3: Load Appropriate Checklist

Based on detected type, read the relevant checklist file:

  • Dependency Updatechecklists/dependency-update.md (expedited review)
  • Bug Fixchecklists/bug-fix.md (focused: fix correctness + regression test)
  • Feature Additionchecklists/feature-addition.md (comprehensive: all areas)
  • UI Changechecklists/ui-change.md (UDF compliance + accessibility + snapshots)
  • Refactoring → Full architecture check: verify behavior-preserving via reference/ios-architecture-patterns.md
  • Infrastructure → Security review + deployment impact assessment

The checklist provides: multi-pass review strategy, type-specific focus areas, what to check and what to skip.

Step 4: Execute Review Following Checklist

Follow the checklist's review strategy, thinking through each pass systematically before writing feedback.

Step 5: Consult Reference Materials As Needed

Load reference files only when needed for specific questions:

  • Re-reviews (incremental) → invoke reviewing-incremental-changes agent skill; scope to changed lines only, do not flag new issues in unchanged code
  • Issue prioritizationreference/priority-framework.md (Critical vs Important vs Suggested)
  • Phrasing feedbackreference/feedback-psychology.md (questions vs commands, I-statements)
  • Architecture questionsreference/ios-architecture-patterns.md + Docs/Architecture.md
  • Security questionsreference/ios-security-patterns.md
  • Testing questionsreference/ios-testing-patterns.md
  • Style questionsreference/ios-style-patterns.md
  • Output formatexamples/annotated-example.md

Core Principles

  • Priority order: Security → Correctness → Breaking Changes → Performance → Maintainability
  • Appropriate depth: Match review rigor to change complexity and risk. A dependency update doesn't need architecture review.
  • Specific references: Always use file:line_number format for precise locations
  • Actionable feedback: Say what to change and why — not just what's wrong
  • Efficient reviews: Use the change-type checklist, skip what's not relevant
  • iOS patterns: Validate UDF, Has* DI, store.binding, Sourcery mock conventions, StateProcessor subclass

Other skills for the same job

different authors, same section of the catalogue
Performance Testing Review AI Review
by ComeOnOliver
×2

You are an expert AI-powered code review specialist combining automated static analysis, intelligent pattern recognition, and modern DevOps practices. Leverage AI tools (GitHub Copilot, Qodo, GPT-5, C

6k tokens
Ruby Pro
by ComeOnOliver
×2

Write idiomatic Ruby code with metaprogramming, Rails patterns, and performance optimization. Specializes in Ruby on Rails, gem development, and testing frameworks. Use PROACTIVELY for Ruby refactoring, optimization, or complex Ruby features.

3k tokens
Tdd Workflows Tdd Refactor
by ComeOnOliver
×2

Use when working with tdd workflows tdd refactor

4k tokens
Setup Pre Commit
by aiskillstore
×1

Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.

7k tokens
Pair Programming
by Microck
×1

AI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with truth-score verification.

6k tokens
Audit Prep Assistant
by christophacham
×1

Prepares codebases for security review using Trail of Bits' checklist. Helps set review goals, runs static analysis tools, increases test coverage, removes dead code, ensures accessibility, and generates documentation (flowcharts, user stories, inline comments).

2k tokens
Component Refactoring
by ComeOnOliver
×1

Refactor high-complexity React components in Dify frontend. Use when `pnpm analyze-component --json` shows complexity > 50 or lineCount > 300, when the user asks for code splitting, hook extraction, or complexity reduction, or when `pnpm analyze-component` warns to refactor before testing; avoid for simple/well-structured components, third-party wrappers, or when the user explicitly wants testing without refactoring.

20k tokens
Csharp Pro
by ComeOnOliver
×1

Write modern C# code with advanced features like records, pattern matching, and async/await. Optimizes .NET applications, implements enterprise patterns, and ensures comprehensive testing. Use PROACTIVELY for C# refactoring, performance optimization, or complex .NET solutions.

3k tokens

How to use it

Copy the folder

Take bitwarden/reviewing-changes from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.