llms

🥈Silver

Centralized LLM configuration and documentation management system. Enables operations teams to build and manage skills, commands, agents, and prompts. Supports multiple LLMs like Claude Code, Codex, and OpenCode. Integrates with MCP servers for deployment and management.

2110Updated 1mo ago

Intermediate30min to implementautomation

Saves ~150 min per use

Quick InstallView Source

git clone https://github.com/matteocervelli/llms.git

Works with:

Claude

Overview

About This Skill

llms is a production-ready configuration system for Claude Code and Codex that includes 39 pre-built skills, unified hook dispatchers, and 21 safety rules. The system organizes workflows across SDLC pipeline, quality assurance, Git operations, documentation, and metadata management. It provides ready-to-use skills for discovery, implementation, code review, security audits, PR management, and deployment. Teams can clone the repository and integrate skills into their projects or install globally, with Codex-specific configuration available for alternative LLM environments.

How to Use

Clone the repository, then copy the .claude/ directory to your project or install skills globally to ~/.claude/. For Codex users, use the .codex/ mirror with codex --config .codex/config.toml. Access the full skill catalog in docs/skill-catalog.md.

Use Cases

Accelerate development workflows with pre-built SDLC pipeline skills

Enforce code quality and security standards across teams

Automate Git operations, PR creation, and release management

Implement safety hooks to block dangerous commands and protect sensitive files

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/matteocervelli/llms

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

Create a centralized LLM configuration for [COMPANY] in the [INDUSTRY] sector. The configuration should include skills, commands, agents, and prompts. Support multiple LLMs like Claude Code, Codex, and OpenCode. Ensure integration with MCP servers for deployment and management. Document all configurations and provide a user-friendly interface for operations teams.

Example Output

# Centralized LLM Configuration for [COMPANY] in the [INDUSTRY] Sector

## Skills
- **Data Analysis**: Automates data analysis tasks using Claude Code.
- **Customer Support**: Manages customer queries with Codex.
- **Code Generation**: Generates and optimizes code with OpenCode.

## Commands
- `analyze_data`: Processes and analyzes data sets.
- `generate_report`: Creates comprehensive reports from analyzed data.
- `support_query`: Handles customer support queries efficiently.

## Agents
- **Data Agent**: Specializes in data-related tasks.
- **Support Agent**: Focuses on customer support.
- **Code Agent**: Handles code generation and optimization.

## Prompts
- **Data Analysis Prompt**: "Analyze the provided data set and generate insights."
- **Customer Support Prompt**: "Respond to the customer query with a detailed solution."
- **Code Generation Prompt**: "Generate optimized code for the given requirements."

## Integration with MCP Servers
- **Deployment**: Automated deployment of configurations to MCP servers.
- **Management**: Centralized management of all LLM configurations.

## Documentation
- **User Guide**: Comprehensive guide for operations teams.
- **API Documentation**: Detailed API documentation for developers.