skills.rest
ybsa
ybsaCOMMUNITY
Explore all skills by this author →
GitHub

coding-agent

Delegate coding tasks to AI agents via background processes.

3|Updated Feb 26, 2026
Search Tags:#developer tools#code review#refactoring#code generation#coding#ai assistant
One-click install
npx skills add https://github.com/ybsa/sovereign-kernel --skill coding-agent-ybsa
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: coding-agent
Source: https://github.com/ybsa/sovereign-kernel/tree/main/crates/sk-tools/skills/coding-agent
Command: npx skills add https://github.com/ybsa/sovereign-kernel --skill coding-agent-ybsa

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill automates complex coding tasks, such as building new features, reviewing code, and refactoring, by delegating them to specialized AI agents like Codex, Claude Code, or Pi.

Core Features & Use Cases

  • Automated Code Generation: Build new features or applications based on natural language prompts.
  • Code Review & Refactoring: Safely review Pull Requests or refactor large codebases in isolated environments.
  • Iterative Development: Explore file systems and perform complex coding tasks that require context.
  • Use Case: When faced with a large codebase that needs significant refactoring, spawn the coding-agent in a background process within the project's directory to handle the task iteratively.

Quick Start

Use the coding-agent skill to build a dark mode toggle for the current project.

Frequently Asked Questions about coding-agent

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

FAQPage Schema
How do I delegate coding tasks to an AI agent for background code generation?▼

You can delegate coding tasks to AI agents by spawning background processes using specific agent CLIs like Codex, Claude Code, or Pi. This allows you to automate code generation and build new features iteratively within your specified working directory.

Can I use AI to refactor a large codebase in an isolated environment?▼

Yes, you can refactor large codebases in isolated environments by spawning an AI coding agent within the project's directory. The agent handles the refactoring task iteratively in a background session, ensuring safe code review and execution.

How do I run parallel issue fixing using git worktrees with an AI assistant?▼

Parallel issue fixing is handled by utilizing git worktrees to create isolated working directories for the AI coding agent. This allows multiple background processes to address different issues simultaneously while providing progress updates and auto-notifications upon completion.

Do I need a pseudo-terminal to run interactive AI coding agents?▼

Yes, a pseudo-terminal with pty enabled is required to run interactive AI coding agents. This terminal environment supports various execution modes, including one-shot commands and monitored background sessions for building or reviewing code.

What is the best way to automate pull request reviews using an AI coding assistant?▼

Automating pull request reviews is best handled by delegating the task to a specialized AI agent like Claude Code or Pi in a background session. The agent safely reviews the code within the specified working directory and provides iterative feedback.

Related Skills

Explore More Software Engineering Skills→
cogpycogpy

coding-agent

Execute AI coding assistants like Codex and Claude Code in background processes.

Official
Advanced
ShinyGuaShinyGua

mm-progress-monitor

Monitor status.json and update TodoWrite checklists in real time.

Community
Intermediate
MeroZemoryMeroZemory
28

project-session-manager

Create git worktrees and tmux workspaces for parallel development contexts.

Community
Advanced
VYRE-StudiosVYRE-Studios

claude-code

Automate coding tasks with Claude Code CLI commands in a project directory.

Official
Intermediate