
Code Reviewer
Run a single-pass senior-style review on PRs and file changes to catch bugs, security issues, smells, and architecture problems before merge.
Overview
Code Reviewer is an agent skill most often used in Ship (also Build architecture checks) that analyzes diffs and files to produce a prioritized review report covering bugs, security, performance, and maintainability.
Install
npx skills add https://github.com/jeffallan/claude-skills --skill code-reviewerWhat is this skill?
- Core workflow: Context → Change analysis → Security → Performance → Quality → Tests → Architecture → Report
- Broad-scope review: SQL injection, XSS, insecure deserialization, N+1 queries, naming, and architectural concerns
- Produces a structured report with prioritized, actionable feedback (report output-format)
- Complements security-reviewer and test-master for specialists while covering maintainability and coverage in one pass
- Triggers on code review, PR review, pull request, review code, and code quality phrases
- 8-step core workflow from Context through Architecture to Report
- Broad vulnerability coverage including SQL injection, XSS, and insecure deserialization
Adoption & trust: 3.6k installs on skills.sh; 9.7k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You are about to merge agent-written or rushed solo code without a consistent pass for security, smells, and test gaps.
Who is it for?
Indie devs reviewing PRs, conducting code quality audits, or validating architecture on small teams of one.
Skip if: Fully automated CI policy enforcement without human judgment, or when you only need deep pen-testing (prefer a dedicated security-reviewer skill).
When should I use this skill?
Reviewing pull requests, conducting code quality audits, identifying refactoring opportunities, checking security vulnerabilities, or validating architectural decisions.
What do I get? / Deliverables
You get a structured, prioritized review report with concrete fixes so you can merge confidently or send work back for refactor.
- Structured code review report with prioritized actionable feedback
- Security, performance, quality, test, and architecture findings grouped for follow-up
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Shipping safely depends on structured review of diffs and intent right before launch prep. Review subphase is the canonical shelf for PR audits, quality gates, and actionable feedback reports.
Where it fits
Run a full pass on a feature branch before merging your weekend SaaS shipping.
Flag SQL injection and XSS patterns in agent-generated API handlers.
Validate whether a new service boundary matches the stated PR problem.
Review a hotfix diff for regressions before pushing to paying users.
How it compares
Broad single-pass review report skill, not a deploy pipeline or MCP server integration.
Common Questions / FAQ
Who is code-reviewer for?
Solo builders and small teams who want thorough, constructive PR and file reviews from their coding agent without hiring a reviewer for every change.
When should I use code-reviewer?
In Ship during PR review and pre-merge audits; in Build when checking architectural decisions; anytime you need refactoring suggestions or security smell detection on changed files.
Is code-reviewer safe to install?
Metadata limits tools to Read, Grep, and Glob—no arbitrary shell—but you should still review the Security Audits panel on this Prism page before installing third-party skills.
SKILL.md
READMESKILL.md - Code Reviewer
# Code Reviewer Senior engineer conducting thorough, constructive code reviews that improve quality and share knowledge. ## When to Use This Skill - Reviewing pull requests - Conducting code quality audits - Identifying refactoring opportunities - Checking for security vulnerabilities - Validating architectural decisions ## Core Workflow 1. **Context** — Read PR description, understand the problem being solved. **Checkpoint:** Summarize the PR's intent in one sentence before proceeding. If you cannot, ask the author to clarify. 2. **Structure** — Review architecture and design decisions. Ask: Does this follow existing patterns in the codebase? Are new abstractions justified? 3. **Details** — Check code quality, security, and performance. Apply the checks in the Reference Guide below. Ask: Are there N+1 queries, hardcoded secrets, or injection risks? 4. **Tests** — Validate test coverage and quality. Ask: Are edge cases covered? Do tests assert behavior, not implementation? 5. **Feedback** — Produce a categorized report using the Output Template. If critical issues are found in step 3, note them immediately and do not wait until the end. > **Disagreement handling:** If the author has left comments explaining a non-obvious choice, acknowledge their reasoning before suggesting an alternative. Never block on style preferences when a linter or formatter is configured. ## Reference Guide Load detailed guidance based on context: <!-- Spec Compliance and Receiving Feedback rows adapted from obra/superpowers by Jesse Vincent (@obra), MIT License --> | Topic | Reference | Load When | |-------|-----------|-----------| | Review Checklist | `references/review-checklist.md` | Starting a review, categories | | Common Issues | `references/common-issues.md` | N+1 queries, magic numbers, patterns | | Feedback Examples | `references/feedback-examples.md` | Writing good feedback | | Report Template | `references/report-template.md` | Writing final review report | | Spec Compliance | `references/spec-compliance-review.md` | Reviewing implementations, PR review, spec verification | | Receiving Feedback | `references/receiving-feedback.md` | Responding to review comments, handling feedback | ## Review Patterns (Quick Reference) ### N+1 Query — Bad vs Good ```python # BAD: query inside loop for user in users: orders = Order.objects.filter(user=user) # N+1 # GOOD: prefetch in bulk users = User.objects.prefetch_related('orders').all() ``` ### Magic Number — Bad vs Good ```python # BAD if status == 3: ... # GOOD ORDER_STATUS_SHIPPED = 3 if status == ORDER_STATUS_SHIPPED: ... ``` ### Security: SQL Injection — Bad vs Good ```python # BAD: string interpolation in query cursor.execute(f"SELECT * FROM users WHERE id = {user_id}") # GOOD: parameterized query cursor.execute("SELECT * FROM users WHERE id = %s", [user_id]) ``` ## Constraints ### MUST DO - Summarize PR intent before rev