engineering-code-review

Review code changes for security, performance, correctness, and maintainability issues.

Updated May 26, 2026
One-click install
npx skills add https://github.com/avel123111/triplanio --skill engineering-code-review-avel123111
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: engineering-code-review
Source: https://github.com/avel123111/triplanio/tree/main/.claude/skills/engineering-code-review
Command: npx skills add https://github.com/avel123111/triplanio --skill engineering-code-review-avel123111

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Manually reviewing pull requests and diffs for security vulnerabilities, performance bottlenecks, and correctness bugs is time-consuming and error-prone, and critical issues like injection risks or N+1 queries are easy to miss. ## Core Features & Use Cases - Security Audit: Checks changes against OWASP top 10 risks including SQL injection, XSS, CSRF, auth flaws, hardcoded secrets, path traversal, and SSRF. - Performance & Correctness Analysis: Detects N+1 queries, memory leaks, algorithmic complexity issues, race conditions, edge cases, and error handling gaps. - Structured Review Output: Produces a formatted report with critical issues, suggestions, positive observations, and a verdict (Approve / Request Changes / Needs Discussion). - Use Case: Before merging a pull request that touches a payment flow, paste the PR URL or diff to get a severity-ranked table of security and correctness findings with actionable code suggestions. ## Quick Start Ask the assistant to review a PR URL, pasted diff, or file path before merging, optionally specifying a focus area like security or performance.

Frequently Asked Questions about engineering-code-review

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

FAQPage Schema
How do I review a pull request for security issues?

Provide the PR URL, pasted diff, or file path and request a review. The review checks for OWASP top 10 risks including SQL injection, XSS, CSRF, authentication flaws, hardcoded secrets, path traversal, and SSRF, then reports findings in a severity-ranked table.

How to check code for N+1 queries and performance problems?

Submit the diff or files and specify a performance focus. The review looks for N+1 queries, unnecessary memory allocations, O(n²) complexity in hot paths, missing database indexes, unbounded loops, and resource leaks.

Can I review a pasted diff instead of a PR URL?

Yes, the review works standalone with a pasted diff, a PR URL, or a direct file path. If source control connectors are available, the PR diff can be pulled automatically along with CI status.

What output format does a code review produce?

The output is a markdown report containing a summary, a critical issues table with file, line, and severity, a suggestions table, positive observations, and a final verdict of Approve, Request Changes, or Needs Discussion.

What are the limitations of automated code review?

The review relies on the provided diff or files, so missing context like surrounding architecture or runtime behavior can limit accuracy. Providing context such as hot paths or PII handling, and including tests, improves the review quality.