LLM Gateway Skills

A collection of packaged instructions and guidelines for AI coding agents, optimized for use with LLM Gateway and the AI SDK.

Available Skills

Image Generation

Best practices for implementing image generation with LLM Gateway and the AI SDK. Covers API integration, frontend rendering, error handling, and performance optimization.

Repository Structure

llmgateway-skills/
├── packages/
│   └── skills-build/      # Build tooling for skills
├── skills/
│   └── image-generation/  # Image generation skill
│       ├── rules/         # Individual rule files
│       ├── AGENTS.md      # Compiled output (generated)
│       ├── SKILL.md       # Skill overview
│       └── metadata.json  # Version and metadata
└── README.md

Getting Started

Prerequisites

• Node.js 18+
• pnpm 9+

Installation

pnpm install

Build Skills

# Build all skills
pnpm build:all

# Build specific skill
pnpm build

# Validate rule files
pnpm validate

# Development mode (build + validate)
pnpm dev

Creating New Rules

1. Copy the template file in skills/[skill-name]/rules/_template.md
2. Name your file with the appropriate prefix (e.g., api-route-setup.md)
3. Fill in the frontmatter and content
4. Run pnpm build to regenerate the AGENTS.md file

Rule Format

Each rule follows a consistent structure:

---
title: Rule Title Here
impact: MEDIUM
impactDescription: Optional description
tags: tag1, tag2
---

## Rule Title Here

**Impact: MEDIUM (optional impact description)**

Brief explanation of the rule and why it matters.

**Incorrect (description):**

\`\`\`typescript
// Bad example
\`\`\`

**Correct (description):**

\`\`\`typescript
// Good example
\`\`\`

Reference: [Link](https://example.com)

Contributing

1. Fork the repository
2. Create your feature branch
3. Add or modify rules following the template
4. Run pnpm validate to check your changes
5. Run pnpm build to regenerate documentation
6. Submit a pull request

License

MIT