Defi Protocols

DeFi Protocols Skill

Master DeFi protocol development including AMM mechanics, lending systems, yield optimization, and oracle integration.

Quick Start

# Invoke this skill for DeFi development
Skill("defi-protocols", protocol_type="amm", chain="ethereum")

Topics Covered

1. AMM (Automated Market Makers)

Build decentralized exchanges:

• Constant Product: x * y = k (Uniswap V2)
• Concentrated Liquidity: Tick-based (Uniswap V3)
• Stable Swaps: Curve invariant
• TWAP: Time-weighted average price

2. Lending Protocols

Create lending markets:

• Overcollateralized: Aave/Compound model
• Interest Rates: Utilization-based curves
• Liquidation: Health factor, incentives
• Isolated Markets: Risk segmentation

3. Yield Optimization

Maximize returns:

• Auto-compounding: Vault strategies
• Liquidity Mining: Reward distribution
• veTokens: Vote-escrowed governance
• Bribes: Gauge voting incentives

4. Oracle Integration

Secure price feeds:

• Chainlink: Decentralized oracles
• TWAP: Manipulation resistant
• Staleness Checks: Price freshness
• Fallbacks: Multi-oracle setups

Code Examples

AMM Swap Calculation

// SPDX-License-Identifier: MIT
pragma solidity ^0.8.24;

library SwapMath {
    uint256 constant FEE_NUMERATOR = 997;
    uint256 constant FEE_DENOMINATOR = 1000;

    /// @notice Calculate output amount for constant product AMM
    function getAmountOut(
        uint256 amountIn,
        uint256 reserveIn,
        uint256 reserveOut
    ) internal pure returns (uint256) {
        uint256 amountInWithFee = amountIn * FEE_NUMERATOR;
        uint256 numerator = amountInWithFee * reserveOut;
        uint256 denominator = reserveIn * FEE_DENOMINATOR + amountInWithFee;
        return numerator / denominator;
    }

    /// @notice Calculate price impact percentage (basis points)
    function getPriceImpact(
        uint256 amountIn,
        uint256 reserveIn
    ) internal pure returns (uint256) {
        return (amountIn * 10000) / (reserveIn + amountIn);
    }
}

Chainlink Oracle

// SPDX-License-Identifier: MIT
pragma solidity ^0.8.24;

import "@chainlink/contracts/src/v0.8/interfaces/AggregatorV3Interface.sol";

contract PriceOracle {
    AggregatorV3Interface public immutable priceFeed;
    uint256 public constant STALENESS_THRESHOLD = 1 hours;

    error StalePrice();
    error InvalidPrice();

    constructor(address feed) {
        priceFeed = AggregatorV3Interface(feed);
    }

    function getPrice() external view returns (uint256) {
        (, int256 price,, uint256 updatedAt,) = priceFeed.latestRoundData();

        if (block.timestamp - updatedAt > STALENESS_THRESHOLD) {
            revert StalePrice();
        }
        if (price <= 0) revert InvalidPrice();

        return uint256(price);
    }
}

Flash Loan Callback

// SPDX-License-Identifier: MIT
pragma solidity ^0.8.24;

import "@aave/v3-core/contracts/flashloan/base/FlashLoanSimpleReceiverBase.sol";

contract Arbitrage is FlashLoanSimpleReceiverBase {
    function executeOperation(
        address asset,
        uint256 amount,
        uint256 premium,
        address,
        bytes calldata
    ) external override returns (bool) {
        // Execute arbitrage logic here

        // Repay: amount + premium
        IERC20(asset).approve(address(POOL), amount + premium);
        return true;
    }
}

DeFi Math Formulas

Constant Product AMM

Invariant: x * y = k
Output: dy = y - k/(x + dx)
Price: p = y/x
Slippage: dx/(x + dx) * 100%

Interest Rates

Utilization: U = borrows / (deposits + borrows)
Borrow Rate: R = base + slope * U  (when U < optimal)
Supply Rate: R_supply = R_borrow * U * (1 - reserve_factor)

Health Factor

HF = (collateral * liquidation_threshold) / debt
Liquidation when HF < 1

Common Pitfalls

Security Checklist

• [ ] Oracle staleness validation
• [ ] Slippage protection
• [ ] Flash loan attack resistance
• [ ] Reentrancy guards
• [ ] Access control on admin
• [ ] Emergency pause mechanism
• [ ] Timelock on parameters

Troubleshooting

"Oracle price deviation"

# Compare oracle vs DEX price
cast call $ORACLE "latestRoundData()" --rpc-url $RPC
cast call $POOL "slot0()" --rpc-url $RPC

"Sandwich attack detected"

Add minimum output enforcement:

require(amountOut >= minAmountOut, "Slippage exceeded");

Protocol Addresses (Mainnet)

Cross-References

• Bonded Agent: 04-defi-specialist
• Related Skills: solidity-development, smart-contract-security

Version History

Defi Protocols Guide

Overview

This guide provides comprehensive documentation for the defi-protocols skill in the custom-plugin-blockchain plugin.

Category: General

Quick Start

Prerequisites

• Familiarity with general concepts
• Development environment set up
• Plugin installed and configured

Basic Usage

# Invoke the skill
claude "defi-protocols - [your task description]"

# Example
claude "defi-protocols - analyze the current implementation"

Core Concepts

Key Principles

1. Consistency - Follow established patterns 2. Clarity - Write readable, maintainable code 3. Quality - Validate before deployment

Best Practices

• Always validate input data
• Handle edge cases explicitly
• Document your decisions
• Write tests for critical paths

Common Tasks

Task 1: Basic Implementation

# Example implementation pattern
def implement_defi_protocols(input_data):
    """
    Implement defi-protocols functionality.

    Args:
        input_data: Input to process

    Returns:
        Processed result
    """
    # Validate input
    if not input_data:
        raise ValueError("Input required")

    # Process
    result = process(input_data)

    # Return
    return result

Task 2: Advanced Usage

For advanced scenarios, consider:

• Configuration customization via assets/config.yaml
• Validation using scripts/validate.py
• Integration with other skills

Troubleshooting

Common Issues

Related Resources

• SKILL.md - Skill specification
• config.yaml - Configuration options
• validate.py - Validation script

---

Last updated: 2025-12-30

Defi Protocols Patterns

Design Patterns

Pattern 1: Input Validation

Always validate input before processing:

def validate_input(data):
    if data is None:
        raise ValueError("Data cannot be None")
    if not isinstance(data, dict):
        raise TypeError("Data must be a dictionary")
    return True

Pattern 2: Error Handling

Use consistent error handling:

try:
    result = risky_operation()
except SpecificError as e:
    logger.error(f"Operation failed: {e}")
    handle_error(e)
except Exception as e:
    logger.exception("Unexpected error")
    raise

Pattern 3: Configuration Loading

Load and validate configuration:

import yaml

def load_config(config_path):
    with open(config_path) as f:
        config = yaml.safe_load(f)
    validate_config(config)
    return config

Anti-Patterns to Avoid

❌ Don't: Swallow Exceptions

# BAD
try:
    do_something()
except:
    pass

✅ Do: Handle Explicitly

# GOOD
try:
    do_something()
except SpecificError as e:
    logger.warning(f"Expected error: {e}")
    return default_value

Category-Specific Patterns: General

Recommended Approach

1. Start with the simplest implementation 2. Add complexity only when needed 3. Test each addition 4. Document decisions

Common Integration Points

• Configuration: assets/config.yaml
• Validation: scripts/validate.py
• Documentation: references/GUIDE.md

---

Pattern library for defi-protocols skill