New to Claude Skills? Learn how to install them →

Get Claude Skills
jeremylongshore on GitHub

Simulating Flash Loans

Free

Evaluate flash loan strategies without real transactions.

by jeremylongshore2.6k stars on jeremylongshore/claude-code-plugins-plus-skills
1 views
Updated Aug 10, 2026
Get this skill

Free · Opens the source repo

What Simulating Flash Loans does

Simulating Flash Loans is a Python-based skill designed for developers and financial analysts interested in decentralized finance (DeFi). This tool allows users to simulate various flash loan strategies across popular protocols such as Aave, dYdX, and Balancer. By providing profitability calculations, gas cost estimations, and risk assessments, it enables users to evaluate potential opportunities without the need to execute actual transactions on the blockchain.

The skill includes a variety of simulation options, allowing users to analyze arbitrage opportunities, evaluate liquidation scenarios, and compare different flash loan providers. For instance, users can simulate a two-DEX arbitrage to determine the best trading strategy or assess liquidation profitability on lending protocols. The output can be tailored to provide quick insights or detailed breakdowns of transaction flows, making it suitable for both quick assessments and comprehensive analyses.

To get started, users need to ensure they have Python 3.9+ installed along with specific libraries such as web3 and httpx. Configuration involves setting up an RPC endpoint, which can be done using public RPCs. The skill is triggered using simple command-line phrases, making it accessible even for those who may not be deeply familiar with programming or blockchain technology.

Overall, this skill is ideal for anyone looking to deepen their understanding of flash loans and DeFi strategies, whether they are developers building applications or analysts seeking to optimize trading strategies. It's particularly useful for those who want to explore the potential of flash loans without the risks associated with live transactions.

When to use it

Use this skill when you want to analyze flash loan opportunities, assess profitability, or compare providers in a risk-free environment.

When not to use it

This skill is not suitable for executing real transactions or for users looking for a simple, non-technical overview of flash loans.

What you can build with it

Arbitrage Simulation

Simulate a two-DEX arbitrage to find the best trading strategy without risking real funds.

Liquidation Analysis

Evaluate potential liquidation opportunities on lending protocols like Aave to identify profitable trades.

Provider Comparison

Compare flash loan providers to determine the most cost-effective option for your trading strategy.

How to install Simulating Flash Loans

View source

1. Install with the skills CLI

npx skills add jeremylongshore/claude-code-plugins-plus-skills/simulating-flash-loans --agent claude-code

2. Or install it manually

Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.

Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs

Inside SKILL.md

Written by jeremylongshore

Simulating Flash Loans

Contents

Overview | Prerequisites | Instructions | Output | Error Handling | Examples | Resources

Overview

Simulate flash loan strategies across Aave V3, dYdX, and Balancer with profitability calculations, gas cost estimation, and risk assessment. Evaluate flash loan opportunities without executing real transactions.

Prerequisites

  1. Install Python 3.9+ with web3, httpx, and rich packages
  2. Configure RPC endpoint access (free public RPCs via https://chainlist.org work fine)
  3. Optionally add Etherscan API key for better gas estimates
  4. Set RPC in ${CLAUDE_SKILL_DIR}/config/settings.yaml or use ETH_RPC_URL env var

Instructions

  1. Simulate a two-DEX arbitrage with automatic fee and gas calculation:

    python ${CLAUDE_SKILL_DIR}/scripts/flash_simulator.py arbitrage ETH USDC 100 \
  --dex-buy uniswap --dex-sell sushiswap

  2. Compare flash loan providers to find the cheapest for your strategy:

    python ${CLAUDE_SKILL_DIR}/scripts/flash_simulator.py arbitrage ETH USDC 100 --compare-providers

  3. Analyze liquidation profitability on lending protocols:

    python ${CLAUDE_SKILL_DIR}/scripts/flash_simulator.py liquidation \
  --protocol aave --health-factor 0.95

  4. Simulate triangular arbitrage with multi-hop circular paths:

    python ${CLAUDE_SKILL_DIR}/scripts/flash_simulator.py triangular \
  ETH USDC WBTC ETH --amount 50

  5. Add risk assessment (MEV competition, execution, protocol, liquidity) to any simulation:

    python ${CLAUDE_SKILL_DIR}/scripts/flash_simulator.py arbitrage ETH USDC 100 --risk-analysis

  6. Run full analysis combining all features:

    python ${CLAUDE_SKILL_DIR}/scripts/flash_simulator.py arbitrage ETH USDC 100 \
  --full --output json > simulation.json

Output

  • Quick Mode: Net profit/loss, provider recommendation, Go/No-Go verdict
  • Breakdown Mode: Step-by-step transaction flow with individual cost components
  • Comparison Mode: All providers ranked by net profit with fee differences
  • Risk Analysis: Competition, execution, protocol, and liquidity scores (0-100) with viability grade (A-F)

See ${CLAUDE_SKILL_DIR}/references/implementation.md for detailed output examples and risk scoring methodology.

Error Handling

ErrorCauseSolution
RPC Rate LimitToo many requestsSwitch to backup endpoint or wait
Stale PricesData older than 30sAuto-refreshes with warning
No Profitable RouteAll routes lose after costsTry different pairs or amounts
Insufficient LiquidityTrade exceeds pool depthReduce amount or split across pools

See ${CLAUDE_SKILL_DIR}/references/errors.md for comprehensive error handling.

Examples

Basic arbitrage simulation:

python ${CLAUDE_SKILL_DIR}/scripts/flash_simulator.py arbitrage ETH USDC 100 \
  --dex-buy uniswap --dex-sell sushiswap

Find cheapest provider:

python ${CLAUDE_SKILL_DIR}/scripts/flash_simulator.py arbitrage ETH USDC 100 --compare-providers

Liquidation opportunity scan:

python ${CLAUDE_SKILL_DIR}/scripts/flash_simulator.py liquidation --protocol aave --health-factor 0.95

See ${CLAUDE_SKILL_DIR}/references/examples.md for multi-provider comparison and backtesting examples.

Resources

  • ${CLAUDE_SKILL_DIR}/references/implementation.md - Provider comparison, strategy details, risk scoring, output modes
  • Aave V3 Flash Loans
  • dYdX Flash Loans
  • Balancer Flash Loans
  • Flashbots Protect

Frequently asked questions about Simulating Flash Loans

Similar skills

WinMD API Search

Easily find and explore Windows desktop APIs.

WebMCPify

Transform any web app into an agent-ready platform.

Phoenix Tracing

Instrument LLM applications with OpenInference tracing.

Foundry Hosted Agent CopilotKit

Guidance for developing agentic web apps on Azure.

Power Automate Foundation

Connect AI agents to Power Automate seamlessly.

Power Automate Flow Builder

Efficiently build and deploy Power Automate flows programmatically.