> For the complete documentation index, see [llms.txt](https://docs.megaeth.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.megaeth.com/developer-docs/build-with-ai.md).

# Build with AI

AI coding skills and tools for building on MegaETH with Claude Code, Cursor, Windsurf, and other AI assistants.

AI coding assistants can help you build on MegaETH faster — deploying contracts, integrating payments, interacting with DeFi protocols, and more. The community maintains a curated list of **AI coding skills** that teach your assistant MegaETH-specific patterns: the dual gas model, instant receipts via `realtime_sendRawTransaction`, mini-block subscriptions, and system contract usage.

Skills follow the [SKILL.md](https://docs.anthropic.com/en/docs/claude-code/skills) and [AGENTS.md](https://docs.agentsmd.dev) conventions and work with tools like Claude Code, Cursor, Windsurf, and OpenClaw.

## Available Skills

| Category               | Skills                                                                                        |
| ---------------------- | --------------------------------------------------------------------------------------------- |
| **General**            | End-to-end MegaETH development — Foundry setup, gas model, WebSocket subscriptions, debugging |
| **Payments**           | x402 HTTP payments, USDm stablecoin integration, Permit2 flows                                |
| **DeFi**               | Kumbaya DEX (Uniswap V3 fork) — swaps, quoting, liquidity, multi-hop routing                  |
| **Identity & Content** | .Mega Domains (naming service), WARREN (on-chain permanent web CMS)                           |
| **Agents**             | ERC-8004 Trustless Agents — on-chain identity, reputation, and validation                     |

For the full list with installation links and detailed descriptions, see the [**awesome-megaeth-ai**](https://github.com/megaeth-labs/awesome-megaeth-ai) repository.

## Getting Started

Most skills are single files you drop into your project. For example, with Claude Code:

```bash
# Add a MegaETH dev skill to your project
curl -o .claude/skills/megaeth-dev.md \
  https://raw.githubusercontent.com/0xBreadguy/megaeth-ai-developer-skills/main/SKILL.md
```

Your AI assistant will automatically pick up the skill and use it when relevant.

{% hint style="info" %}
These skills are community-contributed and are not endorsed by MegaETH Labs. Always review skill content before adding it to your project.
{% endhint %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.megaeth.com/developer-docs/build-with-ai.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.