Setup & Installation
openclaw skills install @jp4g/ethereum-wingman
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install ethereum-wingman
What This Skill Does
An AI agent skill for building Ethereum projects with Scaffold-ETH 2. Covers smart contract development, DeFi protocol patterns, security pitfalls, and the SpeedRun Ethereum challenge curriculum. Always runs against a forked live network rather than an empty local chain.
Fork mode gives contracts access to real token balances, live protocols, and whale accounts, eliminating the gap between local test results and mainnet behavior.
When to use it
- Scaffolding a new dApp project with fork mode configured from the start
- Building a DEX or lending protocol against real Uniswap and Aave state
- Working through SpeedRun Ethereum challenges with guided code examples
- Catching reentrancy and oracle manipulation bugs before deployment
- Deploying and browser-testing contracts on a local Base or Arbitrum fork
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: Build a token staking dApp on Base
AGENT
- 1Runs `npx create-eth@latest` and selects Foundry and Base as the target chain
- 2Sets polling interval to 3000ms in scaffold.config.ts
- 3Runs `yarn fork --network base` and `cast rpc anvil_setIntervalMining 1` to enable live state and block progression
- 4Writes staking contract with explicit liquidation incentives and reentrancy guard, then runs `yarn deploy`
- 5Starts frontend with `yarn start`, navigates to localhost:3000, funds burner wallet via faucet, and verifies staking flow
OUTPUT
Staking dApp running at localhost:3000 connected to a forked Base mainnet with real USDC and WETH available