evaluate

Name: evaluate
Availability: InStock
Author: paycrux

Evaluate code quality against domain checklists and generate graded reports.

Updated Mar 30, 2026

Search Tags:#performance #checklist #security #react #evaluation #code-quality

Ready to run

npx skills add https://github.com/paycrux/ai-skills --skill evaluate-paycrux

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: evaluate
Source: https://github.com/paycrux/ai-skills/tree/main/.claude/skills/evaluate
Command: npx skills add https://github.com/paycrux/ai-skills --skill evaluate-paycrux

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

It addresses the need for fast, consistent code quality reviews across multiple domains (React, engineering, accessibility, security, performance) without spawning sub‑agents, letting developers get actionable feedback directly in the chat.

Core Features & Use Cases

Domain checklists for React accessibility, engineering performance, and security.
Automatic target detection via git diff, explicit file paths, or task‑plan references.
Graded reporting with CRITICAL, MAJOR, MINOR severity and overall grade.
User‑controlled fixing workflow that prompts before any modifications.

Quick Start

Ask the evaluate skill to review the latest changes in the repository.

Frequently Asked Questions about evaluate

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

FAQPage Schema

How do I run a code quality checklist evaluation on my recent git changes?▼

To run a code quality evaluation, target your recent git diff changes and the tool will automatically apply domain checklists for React, security, and performance, generating a graded report with severity levels.

What domains are covered by the code quality assessment checklists?▼

The code quality assessment covers multiple domains including React, engineering, accessibility, security, and performance, providing actionable feedback directly without spawning sub-agents.

Can I review specific file paths or task-plan folders instead of the entire git diff?▼

Yes, automatic target detection allows you to evaluate specified file paths or task-plan folder references within your Git repository instead of just using the latest git diff.

Does the code review tool apply automatic fixes to my files?▼

The tool uses a user-controlled fixing workflow that prompts you before making any modifications, ensuring you review the graded report and approve changes to fix CRITICAL or MAJOR issues first.

How does the graded reporting classify code quality issues?▼

The graded reporting classifies identified code quality issues using CRITICAL, MAJOR, and MINOR severity levels, alongside an overall grade to help prioritize your fixing workflow.

What is the best way to get consistent code reviews for React accessibility and security?▼

Using a checklist-based code quality assessment provides consistent reviews across React accessibility and security domains, letting developers get fast, actionable feedback directly in the chat.