improve

Audit software repositories and generate structured implementation plans for automated execution.

Updated Mar 5, 2026
One-click install
npx skills add https://github.com/zivtech/joyus-desktop --skill improve-zivtech
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: improve
Source: https://github.com/zivtech/joyus-desktop/tree/main/.claude/skills/improve
Command: npx skills add https://github.com/zivtech/joyus-desktop --skill improve-zivtech

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill addresses the challenge of maintaining large, complex codebases by providing a structured, read-only audit that identifies high-value improvements and generates actionable, self-contained implementation plans for other agents to execute.

Core Features & Use Cases

  • Deep Codebase Audit: Analyzes code for correctness, security, performance, and technical debt using a systematic playbook.
  • Implementation Planning: Produces detailed, step-by-step plans that allow less capable models to perform complex refactors or feature additions safely.
  • Use Case: Use this Skill when you need to audit a legacy project for security vulnerabilities or tech debt and require a clear, prioritized roadmap for your development team or AI agents to follow.

Quick Start

Use the improve skill to audit the current repository and generate a prioritized list of implementation plans for the top three identified issues.

Frequently Asked Questions about improve

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

FAQPage Schema
How do I audit a codebase for security vulnerabilities and technical debt?

To audit a codebase for security vulnerabilities and technical debt, this Skill performs a comprehensive read-only analysis of your repository, identifying architectural, security, and performance issues to produce a prioritized improvement roadmap.

Can I generate implementation plans for AI agents to refactor legacy code?

Yes, you can generate implementation plans for AI agents to refactor legacy code. This Skill produces detailed, self-contained, step-by-step plans that enable less capable secondary agents to safely execute complex refactors and feature additions.

What is the best way to analyze a repository without modifying the source code?

The best way to analyze a repository without modifying the source code is using a read-only audit approach. This Skill systematically reviews your codebase to evaluate correctness, security, performance, and technical debt without altering existing files.

Does the generated implementation plan include steps for fixing performance issues?

Yes, the generated implementation plan includes steps for fixing performance issues. The audit identifies high-value architectural and performance improvements, translating them into structured, actionable steps for your development team or automated agents.

How do I prioritize technical debt repayment for a development team?

To prioritize technical debt repayment for a development team, this Skill evaluates your codebase using a systematic playbook, generating a prioritized list of implementation plans targeting the top identified issues for immediate action.