Principal Engineer Code Reviewer

Reviews code changes for correctness, security, and standards compliance with structured JSON findings.

Updated Jan 29, 2026
One-click install
npx skills add https://github.com/sparkst/sparkry-claude-skills --skill principal-engineer-code-reviewer-sparkst
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Principal Engineer Code Reviewer
Source: https://github.com/sparkst/sparkry-claude-skills/tree/main/plugins/dev-workflow/skills/quality/pe-reviewer
Command: npx skills add https://github.com/sparkst/sparkry-claude-skills --skill principal-engineer-code-reviewer-sparkst

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve? Code reviews often miss security vulnerabilities, complexity hotspots, and test gaps because reviewers lack a systematic process. This Skill enforces a multi-pass review covering correctness, security, UX, performance, and test quality, producing structured JSON findings with severity ratings and autofix diffs. ## Core Features & Use Cases - Multi-Pass Review: Systematically checks correctness, security (injection, auth, secrets, SSRF), UX, performance, simplicity, and test coverage against repository standards. - Deterministic Analysis Scripts: Runs cyclomatic complexity analysis, dependency vulnerability checks via npm audit, and Supabase RLS policy validation on SQL migrations. - Structured JSON Output: Emits findings with P0-P3 severity levels, file:line evidence, unified-diff autofixes, and CI commands. - Use Case: Before merging a Supabase Edge Function PR, run the review to verify pinned dependency versions, RLS policies on new tables, smoke test presence, and CORS headers—blocking P0 issues like version mismatches. ## Quick Start Review the current diff for security issues, complexity hotspots, and missing tests, then output findings as JSON with severity ratings and autofix suggestions.

Frequently Asked Questions about Principal Engineer Code Reviewer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate code review for Supabase Edge Functions?▼

Run the review against your diff to check pinned @supabase/supabase-js versions, CORS headers, auth validation, and smoke test presence. The supabase-rls-checker.py script validates that SQL migrations enable Row Level Security on all new tables.

How to check cyclomatic complexity in TypeScript functions?▼

Run scripts/cyclomatic-complexity.py with a file path to get McCabe complexity scores per function as JSON. Functions scoring above 10 are flagged as high risk and candidates for refactoring.

What severity levels does the code review output use?▼

Findings use four levels: P0 for critical issues like security breaches or data loss, P1 for broken functionality or performance regressions, P2 for technical debt, and P3 for style or documentation issues.

Does the review check for dependency vulnerabilities?▼

Yes, the dependency-risk.py script runs npm audit and parses vulnerability results with severity ratings. It also detects version mismatches of @supabase/supabase-js across edge functions, which is treated as a P0 blocker.

Why does the RLS checker fail on my SQL migration?▼

The checker fails when a CREATE TABLE statement lacks a matching ALTER TABLE ... ENABLE ROW LEVEL SECURITY statement or has no CREATE POLICY definitions. Add both RLS enablement and at least one access policy per table.

What are the limitations of automated code review output?▼

Autofix diffs are capped at 50 lines; larger fixes are described as manual steps instead. The review is non-destructive and read-only, so it cannot execute tests or apply fixes directly without user approval.