
Code Review Excellence
Run structured, constructive PR and architecture reviews that catch bugs early and teach standards without slowing the team.
Overview
Code Review Excellence is an agent skill most often used in Ship (also Build, Operate) that teaches constructive PR review, standards, and mentoring practices to improve quality without harming morale.
Install
npx skills add https://github.com/wshobson/agents --skill code-review-excellenceWhat is this skill?
- Six explicit review goals (bugs, maintainability, knowledge share, standards, design, culture) versus anti-goals (nitpic
- Actionable feedback framework: specific, educational, code-focused, balanced praise, and critical vs nice-to-have priori
- When-to-use list spanning PR review, team standards, mentoring, architecture review, checklists, and cycle-time reductio
- Contrast templates for weak vs strong review comments to keep feedback professional
- Mindset shift from gatekeeping to collaborative knowledge sharing
Adoption & trust: 21.7k installs on skills.sh; 36.5k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
Your reviews are either too shallow to catch issues or too harsh and vague, which slows merges and does not spread team knowledge.
Who is it for?
Solo founders reviewing contractor PRs, small teams formalizing review culture, or agents asked to critique diffs with a consistent rubric.
Skip if: Fully automated lint-only gates with no human judgment, or situations where you need a security penetration test instead of collaborative code review.
When should I use this skill?
Reviewing pull requests and code changes, establishing code review standards, mentoring developers, or conducting architecture reviews.
What do I get? / Deliverables
Pull requests get prioritized, actionable feedback aligned to goals—not nitpicks—with clearer architecture and fewer escaped defects.
- Structured review comments with prioritized severity
- Review checklist or team guidelines draft
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Ship/review is the canonical shelf because the skill explicitly targets pull requests, review standards, and pre-merge quality gates. review subphase matches systematic PR analysis, feedback prioritization, and collaboration norms before release.
Where it fits
Prioritize critical vs nice-to-have comments on a feature PR before you merge to main.
Draft a team review checklist that defers formatting to linters and focuses on design risks.
Frame security findings as educational review notes without blocking on personal preference.
Review hotfix diffs quickly while still calling out edge cases and maintainability regressions.
How it compares
Use for human-centered review process and comment quality, not as a substitute for static analysis or CI test suites.
Common Questions / FAQ
Who is code-review-excellence for?
Builders and leads who review pull requests, set team standards, or mentor juniors and want the agent to apply a consistent review mindset.
When should I use code-review-excellence?
In Ship/review before merge; also in Build/pm when shaping team guidelines, and in Operate/iterate when tightening quality on ongoing changes.
Is code-review-excellence safe to install?
It is procedural guidance only; check the Security Audits panel on this page and avoid pasting secrets into review threads the skill helps you write.
SKILL.md
READMESKILL.md - Code Review Excellence
# Code Review Excellence Transform code reviews from gatekeeping to knowledge sharing through constructive feedback, systematic analysis, and collaborative improvement. ## When to Use This Skill - Reviewing pull requests and code changes - Establishing code review standards for teams - Mentoring junior developers through reviews - Conducting architecture reviews - Creating review checklists and guidelines - Improving team collaboration - Reducing code review cycle time - Maintaining code quality standards ## Core Principles ### 1. The Review Mindset **Goals of Code Review:** - Catch bugs and edge cases - Ensure code maintainability - Share knowledge across team - Enforce coding standards - Improve design and architecture - Build team culture **Not the Goals:** - Show off knowledge - Nitpick formatting (use linters) - Block progress unnecessarily - Rewrite to your preference ### 2. Effective Feedback **Good Feedback is:** - Specific and actionable - Educational, not judgmental - Focused on the code, not the person - Balanced (praise good work too) - Prioritized (critical vs nice-to-have) ```markdown ❌ Bad: "This is wrong." ✅ Good: "This could cause a race condition when multiple users access simultaneously. Consider using a mutex here." ❌ Bad: "Why didn't you use X pattern?" ✅ Good: "Have you considered the Repository pattern? It would make this easier to test. Here's an example: [link]" ❌ Bad: "Rename this variable." ✅ Good: "[nit] Consider `userCount` instead of `uc` for clarity. Not blocking if you prefer to keep it." ``` ### 3. Review Scope **What to Review:** - Logic correctness and edge cases - Security vulnerabilities - Performance implications - Test coverage and quality - Error handling - Documentation and comments - API design and naming - Architectural fit **What Not to Review Manually:** - Code formatting (use Prettier, Black, etc.) - Import organization - Linting violations - Simple typos ## Review Process ### Phase 1: Context Gathering (2-3 minutes) ```markdown Before diving into code, understand: 1. Read PR description and linked issue 2. Check PR size (>400 lines? Ask to split) 3. Review CI/CD status (tests passing?) 4. Understand the business requirement 5. Note any relevant architectural decisions ``` ### Phase 2: High-Level Review (5-10 minutes) ```markdown 1. **Architecture & Design** - Does the solution fit the problem? - Are there simpler approaches? - Is it consistent with existing patterns? - Will it scale? 2. **File Organization** - Are new files in the right places? - Is code grouped logically? - Are there duplicate files? 3. **Testing Strategy** - Are there tests? - Do tests cover edge cases? - Are tests readable? ``` ### Phase 3: Line-by-Line Review (10-20 minutes) ```markdown For each file: 1. **Logic & Correctness** - Edge cases handled? - Off-by-one errors? - Null/undefined checks? - Race conditions? 2. **Security** - Input validation? - SQL injection risks? - XSS vulnerabilities? - Sensitive data exposure? 3. **Performance** - N+1 queries? - Unnecessary loops? - Memory leaks? - Blocking operations? 4. **Maintainability** - Clear variable names? - Functions doing one thing? - Complex code commented? - Magic numbers extracted? ``` ### Phase 4: Summary & Decision (2-3 minutes) ```markdown 1. Summarize key concerns 2. Highlight what you liked 3. Make clear decision: - ✅ Approve - 💬 Comment (minor suggestions) - 🔄 Request Changes (must address) 4. Offer to pair if complex ``` ## Review Techniques ### Technique 1: The Checklist Method ```markdown ## Security Checklist - [ ] User input vali