skills.rest
NJUxlj
NJUxljCOMMUNITY
Explore all skills by this author →
GitHub

coding-agent

Delegate coding tasks to AI agents like Codex or Claude Code via background processes.

Updated Feb 1, 2026
Search Tags:#automation#code review#refactoring#code generation#ai agent#coding
One-click install
npx skills add https://github.com/NJUxlj/openclaw --skill coding-agent-njuxlj
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: coding-agent
Source: https://github.com/NJUxlj/openclaw/tree/main/skills/coding-agent
Command: npx skills add https://github.com/NJUxlj/openclaw --skill coding-agent-njuxlj

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill automates complex coding tasks by delegating them to specialized AI agents like Codex, Claude Code, or Pi, reducing manual effort and accelerating development cycles.

Core Features & Use Cases

  • Automated Code Generation & Refactoring: Build new features, refactor large codebases, or create applications.
  • Automated Code Review: Review Pull Requests efficiently by spawning agents in temporary directories.
  • Iterative Development: Facilitates file exploration and iterative coding for complex projects.
  • Use Case: Delegate the task of building a new user authentication module to Codex, allowing it to handle file creation, function implementation, and basic testing.

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 automate code generation for new features using an AI agent?▼

Automate code generation by delegating complex coding tasks to specialized AI agents like Codex or Claude Code via background processes. This handles file creation and function implementation for new features without manual effort.

Can I use this coding-agent to review pull requests in a temporary directory?▼

Yes, you can use this coding-agent to review pull requests efficiently by spawning AI agents in temporary directories. This isolates the PR code for focused automated analysis and feedback.

What is the best way to refactor a large codebase with AI?▼

Refactoring a large codebase with AI involves delegating the task to agents like Pi or Claude Code, which explore files iteratively and execute structural changes within a specified workdir for focused execution.

Does this AI agent skill work with Claude Code and Codex?▼

Yes, this skill works with Claude Code and Codex. It requires specific execution modes, using PTY for Codex or Pi and the --print flag for Claude Code, to delegate and run background coding tasks.

When should I not use an AI coding agent for iterative development?▼

You should avoid using an AI coding agent if your iterative development task lacks a clear workdir or requires real-time interactive debugging, as this skill operates via background processes and respects focused execution boundaries.

Related Skills

Explore More Software Engineering Skills→
gitgoodordietryinggitgoodordietrying
1

coding-agent

Orchestrate coding agents via background processes in isolated workdirs.

Community
Advanced
p-o-ke-naep-o-ke-nae

github-flow

Guide GitHub Flow branching, commits, testing, pull requests, and squash merges.

Community
Intermediate
act70255act70255

code-reviewer

Automate code reviews with static analysis and AI vulnerability detection.

Community
Advanced
smallnestsmallnest
601

coding-agent

Control multiple AI coding assistants via shell commands and PTY.

Community
Advanced