improve

Audit the Carbon codebase and generate prioritized implementation plans.

2.3k|331|Updated Jun 3, 2024
One-click install
npx skills add https://github.com/crbnos/carbon --skill improve-crbnos
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: improve
Source: https://github.com/crbnos/carbon/tree/main/.ai/skills/improve
Command: npx skills add https://github.com/crbnos/carbon --skill improve-crbnos

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill serves as a senior advisor to survey the Carbon codebase and generate prioritized, executable implementation plans for OTHER models/agents.

Core Features & Use Cases

  • Codebase Audit: Deeply understand the Carbon codebase and identify improvement opportunities.
  • Prioritized Plans: Produce self-contained implementation plans for other agents to execute.
  • Read-Only Analysis: Perform read-only analysis, never modifying source code directly.
  • Use Case: When asked to audit Carbon for bugs, security vulnerabilities, performance issues, or to suggest new features, this Skill can generate detailed plans for implementation.

Quick Start

Use the improve skill to audit the Carbon codebase for security vulnerabilities.

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 performance issues?

A codebase audit identifies security vulnerabilities and performance issues through read-only analysis, generating prioritized implementation plans without modifying source code directly. It leverages parallel subagents for comprehensive analysis.

How do I generate prioritized implementation plans for other AI agents?

Prioritized implementation plans are generated by auditing the codebase to identify improvement opportunities, then producing self-contained execution plans for other models to implement.

Can I use this to suggest new features for a monorepo environment?

Yes, you can survey a monorepo environment to suggest new features. It operates within the Carbon monorepo, utilizing the .ai/rules/ knowledge base to understand the codebase and output detailed feature plans.

Does the codebase audit directly modify source code?

No, the codebase audit performs read-only analysis and never modifies source code directly. It ensures code quality by generating advisory implementation plans for other agents to execute.

What is the best way to find improvement opportunities in a large codebase?

The best way to find improvement opportunities is using parallel subagents for comprehensive analysis. This approach identifies bugs, security vulnerabilities, and performance issues, outputting prioritized plans for implementation.