skills.rest
MettaMazza
MettaMazzaCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

coding-agent

Delegate coding tasks to AI agents via background processes.

Updated Aug 23, 2026
Search Tags:#code review#refactoring#code generation#codex#claude#ai agent#coding
One-click install
npx skills add https://github.com/MettaMazza/ErnOS --skill coding-agent-mettamazza
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: coding-agent
Source: https://github.com/MettaMazza/ErnOS/tree/main/skills/coding-agent
Command: npx skills add https://github.com/MettaMazza/ErnOS --skill coding-agent-mettamazza

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill automates complex coding tasks, code reviews, and refactoring by delegating them to specialized AI agents like Codex, Claude Code, or Pi agents, freeing up developer time for higher-level problem-solving.

Core Features & Use Cases

  • Automated Code Generation: Build new features, applications, or refactor large codebases.
  • Code Review Assistance: Spawn agents in temporary directories to review Pull Requests.
  • Iterative Development: Facilitates exploration and modification of code within specified directories.
  • Use Case: When faced with a large, legacy codebase that needs modernization, you can use this skill to have an AI agent systematically refactor modules, ensuring functionality is preserved while improving code quality.

Quick Start

Use the coding-agent skill to have Codex refactor the authentication module in your project directory.

Frequently Asked Questions about coding-agent

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

FAQPage Schema
How do I delegate complex coding tasks to an AI agent for refactoring?▼

You can delegate complex coding tasks to an AI agent by spawning background processes via a bash tool, allowing agents like Codex to systematically refactor large codebases and build new features while preserving functionality.

Can I use AI agents to review pull requests in temporary directories?▼

Yes, AI agents can review pull requests by spawning into temporary directories, allowing them to evaluate changes in isolation before integrating feedback into your main branch.

What is the best way to automate code generation for new application features?▼

Automating code generation for new features is best handled by delegating the task to specialized AI agents, freeing up developer time for higher-level problem-solving while the agent builds the application.

Do I need a bash tool with pty support to run a coding agent?▼

Yes, you need a bash tool with pty:true support to run a coding agent, as delegating tasks to background processes requires pseudo-terminal support to execute properly.

Why should I not use an AI coding agent for simple one-liner fixes?▼

You should not use an AI coding agent for simple one-liner fixes because it is designed for complex, iterative development involving file exploration and large codebase refactoring, not trivial modifications.

Does this coding agent approach work with Claude Code and Pi agents?▼

Yes, this coding agent approach works with Claude Code and Pi agents, supporting delegation to these specialized AI models to automate complex code generation and review tasks.

Related Skills

Explore More Software Engineering Skills→
FlexasaurusrexFlexasaurusrex
16

coding-agent

Delegate coding tasks to AI agents via background processes.

Community
Advanced
a-tabijia-tabiji

merge

Merge reviewed pull requests into main with squash merge and branch cleanup.

Community
Intermediate
linuxhsjlinuxhsj
5.1k

coding-agent

Delegate coding tasks to AI agents via background processes.

Community
Advanced
Solitude01Solitude01

coding-agent

Delegate coding tasks to AI agents via a background PTY-enabled process.

Community
Advanced