requesting-code-review

Review Git diffs for spec compliance and security with P0–P3 findings.

2|Updated Apr 26, 2026
One-click install
npx skills add https://github.com/iadr-dev/colab --skill requesting-code-review-iadr-dev
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: requesting-code-review
Source: https://github.com/iadr-dev/colab/tree/main/skills/requesting-code-review
Command: npx skills add https://github.com/iadr-dev/colab --skill requesting-code-review-iadr-dev

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps teams reliably review code changes with senior-engineer discipline, focusing first on whether the implementation meets the spec and only then expanding into architecture, security, reliability, and overall code quality.

Core Features & Use Cases

  • Spec compliance first: Compares the diff against success criteria in .ohc/plans/ and the user’s stated requirements, reporting Implemented vs Partial vs Missing.
  • Severity-structured findings (P0–P3): Produces a prioritized report where blocking issues (P0/P1) are clearly identified and must be resolved before merge.
  • Security + quality coverage: Evaluates the change against dedicated security and code-quality checklists, including common web vulnerabilities and reliability pitfalls.
  • Removal candidate identification: Flags dead/unreachable code and feature-flagged-off logic using a safe deletion vs defer plan approach.

Quick Start

Ask your AI agent to run a structured code review for the current git diff and return a P0-P3 severity report with spec compliance, security, and code-quality findings.

Frequently Asked Questions about requesting-code-review

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

FAQPage Schema
How do I perform a security-first code review on a git diff?

A security-first code review evaluates git diffs against spec compliance before architecture, producing P0–P3 severity findings. It prioritizes blocking issues and security vulnerabilities over general refactoring or quality improvements.

How do I generate a P0-P3 severity triage report for uncommitted changes?

P0-P3 severity triage reports categorize code review findings by blocking priority. P0 and P1 issues are identified as blocking and must be resolved before merge, while P2 and P3 cover quality and architecture improvements.

What is the best way to check spec compliance and identify dead code in a pull request?

Spec compliance checks compare active git diffs against success criteria in plan directories, reporting Implemented, Partial, or Missing. The review also flags dead or unreachable code as removal candidates using a safe deletion or defer plan.

Does this code review approach work with standard git workflows and checklists?

Yes, this review approach applies to Git diffs in active development workflows. It runs preflight git inspections and loads checklist references for SOLID principles, security vulnerabilities, and code quality during analysis.

When should I not use an automated severity triage for code reviews?

Automated severity triage is not suited for non-blocking, stylistic feedback. It enforces review-only defaults and focuses on structured security and spec compliance findings rather than subjective refactoring opinions.

How do I structure inline code comments for blocking issues found during code review?

Inline code comments for blocking issues are formatted within a structured summary output. The review identifies relevant files and line ranges, mapping P0 and P1 findings directly to the code segments requiring changes.