ai-config

🥈Silver

A collection of skills and extensions for AI coding agents including Claude Code and Codex CLI, adding capabilities like web search and subagent orchestration.

1100Updated 2mo ago

Intermediate30min to implementautomation

Saves ~75 min per use

Quick InstallView Source

git clone https://github.com/dnouri/ai-config.git

Works with:

Claude

Overview

About This Skill

ai-config is a GitHub repository providing reusable skills and extensions for AI coding agents such as Claude Code, Codex CLI, and pi-coding-agent. It includes a web search skill that handles concurrent browser sessions, retries on failure, and cleans up zombie processes automatically. The repository also offers a subagent extension that enables orchestration of child agents with live streaming output, token usage stats, and session metadata display. An improve-agent skill helps teams refine their agent configurations by analyzing past failures and suggesting new skills or tool fixes. Developers building or customizing AI coding agent workflows benefit from these ready-made, battle-tested components.

Use Cases

Adding web search capability to Claude Code or Codex CLI agents with concurrent-access safety

Orchestrating subagents with live streaming output and cost tracking in a TUI

Automatically analyzing agent failures to suggest skill or tooling improvements

Extending pi-coding-agent with reusable, community-maintained skill modules

Setup & Installation

Quick Install

No install command available. Check the GitHub repository for manual installation instructions.

Alternative Install (Git Clone)

git clone https://github.com/dnouri/ai-config

Requirements

Claude Code or compatible AI agent
Works with: Claude

Quick Start Guide

Install the Skill

Copy the install command above and run it in your terminal.

Open Your AI Agent

Launch Claude Code, Cursor, or your preferred AI coding agent.

Try It Out

Use the prompt template or examples below to test the skill.

Customize

Adapt the skill to your specific use case and workflow.

Usage Examples

Prompt Template

Act as an AI configuration expert. I need to set up a [TOOL] for [TASK]. Provide a step-by-step guide with code snippets in [LANGUAGE] to configure it for [SPECIFIC USE CASE]. Include error handling and best practices.

Example Output

# AI Tool Configuration Guide

## Step 1: Install Dependencies
```bash
pip install pi-coding-agent claudecode codex-cli
```

## Step 2: Configure API Keys
```python
import os
os.environ['API_KEY'] = 'your_api_key_here'
```

## Step 3: Set Up Workflow
```yaml
workflow:
  - tool: pi-coding-agent
    parameters:
      task: 'code_review'
      language: 'python'
  - tool: claudecode
    parameters:
      model: 'code-davinci-002'
```

## Best Practices
- Always validate API keys before execution
- Use environment variables for sensitive data
- Implement retry logic for API calls
- Monitor tool usage and performance