Connect to DeFi protocols for staking, lending, yield farming, and liquidity provision.

MITAuto-check passedBusiness, Finance & HR

Install Defi Connector

skills CLI
$ npx skills add Signal-Execution-Labs/forex-trading-ai-agent --skill defi-connector -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Signal-Execution-Labs/forex-trading-ai-agent defi-connector --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Signal-Execution-Labs/forex-trading-ai-agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/defi-connector .claude/skills/defi-connector && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
defi-connector
GitHub stars
162
Token cost
~2.4k tokens
SKILL.md length
158 words
Files
2 (incl. scripts)
Skills in repo
11
Repo updated
First seen
Licence
MIT

At a glance

Connect to DeFi protocols for staking, lending, yield farming, and liquidity provision.

  • Tasks that involve Crypto and DeFi analysis
  • SKILL.md covers Overview, 🤖 AUTO-PILOT MODE, Supported Protocols and Commands, plus 1 more section
  • Runs Python scripts from its folder; calls python3 and hf; reaches api.llama.fi and yields.llama.fi
  • Tasks that involve Banking and insurance

What it does

Defi Connector is an agent skill from Signal-Execution-Labs/forex-trading-ai-agent. Connect to DeFi protocols for staking, lending, yield farming, and liquidity provision. Full auto-compound support.

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/defi_monitor.py`).

It sits in Business, Finance & HR, covering Crypto and DeFi analysis and Banking and insurance. It works with Ethereum. The repository describes itself as: About AI quantitative trading platform for crypto, stocks, and forex with backtesting, live trading, market data, and multi-agent research.vibe-trading…. The licence is MIT.

When your agent uses it

  • Tasks that involve Crypto and DeFi analysis
  • Tasks that involve Banking and insurance

Example prompts

  • “/defi-connector”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit b8a6047. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3
    • hf

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • api.llama.fi
    • yields.llama.fi

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Defi Connector loads about 2.4k tokens when it runs. Until then it costs about 33 tokens; SKILL.md has 158 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~33
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from Signal-Execution-Labs/forex-trading-ai-agent at commit b8a6047, republished under its MIT licence (© Signal-Execution-Labs). 158 words, ~2,404 tokens.

Download SKILL.mdSave it as .claude/skills/defi-connector/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
defi-connector
description
Connect to DeFi protocols for staking, lending, yield farming, and liquidity provision. Full auto-compound support.

DeFi Connector

Vollautomatische DeFi-Strategien: Staking, Lending, Yield Farming.

Overview

  • Staking - ETH, SOL, ATOM und mehr
  • Lending - Aave, Compound, MakerDAO
  • Yield Farming - Liquidity Mining
  • Auto-Compound - Rewards automatisch reinvestieren

🤖 AUTO-PILOT MODE

python
# ~/.kit/config/defi-connector.json
{
  "auto_pilot": {
    "enabled": true,
    "wallets": {
      "ethereum": "0x...",
      "solana": "...",
      "cosmos": "cosmos1..."
    },
    "strategies": {
      "staking": {
        "enabled": true,
        "auto_stake_idle": true,
        "min_stake_amount": 0.1
      },
      "lending": {
        "enabled": true,
        "protocols": ["aave", "compound"],
        "max_ltv_pct": 50,
        "health_factor_min": 1.5
      },
      "yield_farming": {
        "enabled": false,
        "require_approval": true,
        "max_position_pct": 20
      },
      "auto_compound": {
        "enabled": true,
        "interval_hours": 24,
        "min_reward_usd": 10
      }
    },
    "risk_management": {
      "max_protocol_exposure_pct": 30,
      "require_audit": true,
      "min_tvl_usd": 100000000
    },
    "alerts": {
      "health_factor_warning": 1.3,
      "apy_change_pct": 20,
      "reward_claimed": true
    }
  }
}

Supported Protocols

ProtocolChainFeatures
AaveETH, Polygon, ArbitrumLending, Borrowing
CompoundEthereumLending
LidoETH, SOLLiquid Staking
Rocket PoolEthereumDecentralized Staking
UniswapETH, PolygonLP, Farming
CurveMulti-chainStablecoin LP
ConvexEthereumBoosted Curve
OsmosisCosmosLP, Staking

Commands

Check DeFi Positions
bash
python3 -c "
import requests

# DefiLlama API for protocol data
def get_protocol_tvl(protocol):
    r = requests.get(f'https://api.llama.fi/protocol/{protocol}')
    return r.json()

protocols = ['aave', 'lido', 'compound', 'uniswap']

print('🌾 DEFI PROTOCOL OVERVIEW')
print('=' * 60)

for p in protocols:
    try:
        data = get_protocol_tvl(p)
        tvl = data.get('tvl', [{}])[-1].get('totalLiquidityUSD', 0)
        print(f\"{p.upper():12} TVL: \${tvl/1e9:.2f}B\")
    except:
        print(f'{p.upper():12} Error fetching data')
"
ETH Staking Status (Lido)
bash
python3 -c "
from web3 import Web3

# Lido stETH contract
STETH_ADDRESS = '0xae7ab96520DE3A18E5e111B5EaijB6b7E49e9a5bf'
LIDO_APR = 3.8  # Current ~3.8%

# Mock wallet - replace with actual
wallet = '0x742d35Cc6634C0532925a3b844Bc9e7595f5bA12'
steth_balance = 2.5  # stETH

print('🥩 ETH STAKING (LIDO)')
print('=' * 50)
print(f'Wallet: {wallet[:10]}...{wallet[-6:]}')
print()
print(f'stETH Balance: {steth_balance:.4f}')
print(f'Current APR: {LIDO_APR}%')
print()

# Calculate rewards
daily_reward = steth_balance * (LIDO_APR / 100) / 365
monthly_reward = daily_reward * 30
yearly_reward = steth_balance * (LIDO_APR / 100)

print('📊 Projected Rewards:')
print(f'  Daily:   {daily_reward:.6f} ETH')
print(f'  Monthly: {monthly_reward:.6f} ETH')
print(f'  Yearly:  {yearly_reward:.4f} ETH')
"
Aave Lending Position
bash
python3 -c "
# Aave position tracker
position = {
    'supplied': {
        'USDC': {'amount': 10000, 'apy': 4.2},
        'ETH': {'amount': 1.0, 'apy': 1.8},
    },
    'borrowed': {
        'USDT': {'amount': 3000, 'apy': 5.5},
    },
    'health_factor': 2.1
}

print('🏦 AAVE POSITION')
print('=' * 50)

# Supplied
total_supplied = 0
print('📥 SUPPLIED:')
for asset, data in position['supplied'].items():
    value = data['amount'] if asset == 'USDC' else data['amount'] * 2500  # ETH price
    total_supplied += value
    print(f\"  {asset}: {data['amount']:,.2f} (APY: {data['apy']}%)\")

# Borrowed  
total_borrowed = 0
print()
print('📤 BORROWED:')
for asset, data in position['borrowed'].items():
    total_borrowed += data['amount']
    print(f\"  {asset}: {data['amount']:,.2f} (APY: {data['apy']}%)\")

# Health
hf = position['health_factor']
hf_status = '🟢 Safe' if hf > 1.5 else '🟡 Warning' if hf > 1.2 else '🔴 DANGER'

print()
print(f'Net Position: \${total_supplied - total_borrowed:,.2f}')
print(f'Health Factor: {hf} {hf_status}')
print(f'LTV: {(total_borrowed/total_supplied*100):.1f}%')

# Net APY
supply_yield = sum(d['amount'] * d['apy'] / 100 for d in position['supplied'].values())
borrow_cost = sum(d['amount'] * d['apy'] / 100 for d in position['borrowed'].values())
net_apy = (supply_yield - borrow_cost) / total_supplied * 100
print(f'Net APY: {net_apy:.2f}%')
"
Yield Farming Opportunities
bash
python3 -c "
import requests

# Get top yield opportunities from DefiLlama
url = 'https://yields.llama.fi/pools'

try:
    data = requests.get(url).json()['data']
    
    # Filter: TVL > $10M, APY > 5%
    good_farms = [p for p in data if 
                  p.get('tvlUsd', 0) > 10_000_000 and 
                  p.get('apy', 0) > 5 and
                  p.get('apy', 0) < 100]  # Filter unrealistic APY
    
    # Sort by APY
    good_farms.sort(key=lambda x: x.get('apy', 0), reverse=True)
    
    print('🌾 TOP YIELD FARMING OPPORTUNITIES')
    print('=' * 70)
    print(f'{\"Protocol\":15} {\"Pool\":20} {\"Chain\":10} {\"TVL\":>12} {\"APY\":>8}')
    print('-' * 70)
    
    for farm in good_farms[:15]:
        protocol = farm.get('project', 'Unknown')[:14]
        pool = farm.get('symbol', 'Unknown')[:19]
        chain = farm.get('chain', 'Unknown')[:9]
        tvl = farm.get('tvlUsd', 0)
        apy = farm.get('apy', 0)
        
        print(f'{protocol:15} {pool:20} {chain:10} \${tvl/1e6:>10.1f}M {apy:>7.1f}%')

except Exception as e:
    print(f'Error: {e}')
"
Auto-Compound Rewards
bash
python3 -c "
from datetime import datetime, timedelta

# Pending rewards to compound
rewards = [
    {'protocol': 'Aave', 'token': 'AAVE', 'amount': 0.5, 'value_usd': 45},
    {'protocol': 'Curve', 'token': 'CRV', 'amount': 150, 'value_usd': 75},
    {'protocol': 'Convex', 'token': 'CVX', 'amount': 25, 'value_usd': 62},
]

print('🔄 AUTO-COMPOUND CHECK')
print('=' * 50)
print(f'Time: {datetime.now().isoformat()}')
print()

total_pending = sum(r['value_usd'] for r in rewards)
min_compound = 10  # Minimum $10 to compound (gas efficiency)

print('Pending Rewards:')
for r in rewards:
    print(f\"  {r['protocol']:10} {r['amount']:>8.2f} {r['token']:5} (\${r['value_usd']:.2f})\")

print()
print(f'Total Pending: \${total_pending:.2f}')
print()

if total_pending >= min_compound:
    print('🤖 AUTO-COMPOUND: Executing...')
    print('  1. Claim all rewards')
    print('  2. Swap to base asset (ETH/USDC)')
    print('  3. Re-deposit to protocols')
    print('  ✅ Compounded!')
else:
    next_check = datetime.now() + timedelta(hours=24)
    print(f'⏳ Below threshold (\${min_compound})')
    print(f'   Next check: {next_check.strftime(\"%Y-%m-%d %H:%M\")}')
"
Health Factor Monitor
bash
python3 -c "
import time
from datetime import datetime

positions = [
    {'protocol': 'Aave', 'health_factor': 1.85, 'liquidation_threshold': 1.0},
    {'protocol': 'Compound', 'health_factor': 2.1, 'liquidation_threshold': 1.0},
    {'protocol': 'MakerDAO', 'health_factor': 1.45, 'liquidation_threshold': 1.0},
]

print('🏥 HEALTH FACTOR MONITOR')
print('=' * 50)
print(f'Check: {datetime.now().isoformat()}')
print()

for pos in positions:
    hf = pos['health_factor']
    
    if hf < 1.2:
        status = '🔴 CRITICAL'
        action = '⚠️ REPAY DEBT IMMEDIATELY'
    elif hf < 1.5:
        status = '🟡 WARNING'
        action = 'Consider repaying'
    else:
        status = '🟢 SAFE'
        action = 'No action needed'
    
    print(f\"{pos['protocol']:12} HF: {hf:.2f} {status}\")
    if hf < 1.5:
        print(f'             Action: {action}')
    print()

# Auto-protect logic
critical = [p for p in positions if p['health_factor'] < 1.2]
if critical:
    print('🚨 AUTO-PROTECT TRIGGERED')
    print('   Initiating emergency debt repayment...')
"
Auto-Pilot: Full DeFi Automation
bash
python3 -c "
from datetime import datetime

print('🤖 DEFI AUTO-PILOT')
print('=' * 50)
print(f'Running: {datetime.now().isoformat()}')
print()

tasks = [
    ('🏥 Check health factors', 'All positions safe'),
    ('💰 Check pending rewards', '\$182 pending'),
    ('🔄 Auto-compound check', 'Compounded \$182 -> staking'),
    ('📊 Yield optimization', 'No better opportunities found'),
    ('🔔 Update yield rates', 'Aave USDC: 4.2% -> 4.5%'),
    ('📈 Track total DeFi value', '\$45,230 across 5 protocols'),
]

for task, result in tasks:
    print(f'{task}')
    print(f'  ✅ {result}')
    print()

print('Next cycle: In 24 hours')
"

Workflow

DeFi Risk Tiers
TierRiskAPY RangeProtocols
1 - Blue ChipLow2-6%Aave, Compound, Lido
2 - EstablishedMedium5-15%Curve, Convex, Uniswap
3 - DegenHigh15%+New protocols, leveraged
Safety Checklist

Before depositing:

  • Protocol audited?
  • TVL > $100M?
  • Team doxxed?
  • Insurance available?
  • Understand smart contract risk
Gas Optimization
  • Batch transactions when possible
  • Compound when gas < 20 gwei
  • Use L2s (Arbitrum, Optimism) for smaller amounts

© Signal-Execution-Labs, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (scripts) in skills/defi-connector of Signal-Execution-Labs/forex-trading-ai-agent.

  • SKILL.md
  • scripts/defi_monitor.py

Open the folder on GitHubat commit b8a6047

Compare with similar skills

Defi Connector next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Defi Connector compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Defi Connector this skillSignal-Execution-Labs/forex-trading-ai-agent162—~2.4kAutomated safety check: PassMIT
Swapper Depositswapperfinance/swapper-toolkit852—~1.8kAutomated safety check: PassMIT
Aomi Transactjeremylongshore/tons-of-skills-marketplace2.8k—~2.3kAutomated safety check: PassMIT
Okx Cex Earnokx/agent-skills1872 repos~3.3kAutomated safety check: PassMIT
SurfBlockRunAI/ClawRouter6.6k—~4kAutomated safety check: PassMIT
Notebook To Strategytradingstrategy-ai/trade-executor160—~1.1kAutomated safety check: PassCustom licence

Similar skills

  • Swapper Deposit

    swapperfinance/swapper-toolkit

    Deposit and bridge funds into a wallet or protocol using Swapper Finance.

    852 GitHub stars~1.8k tokensUpdated 6 mo ago
    Business, Finance & HRAuto-check passed
  • Aomi Transact

    jeremylongshore/tons-of-skills-marketplace

    Build natural-language crypto agents, web3 assistants, and trading bots that read and write EVM chain state.

    2.8k GitHub stars~2.3k tokensUpdated yesterday
    Business, Finance & HRAuto-check passed
  • Okx Cex Earn

    okx/agent-skills

    Manages OKX Simple Earn (flexible savings/lending), Flash Earn, On-chain Earn (staking/DeFi), Dual Investment (DCD/双币赢), and AutoEarn (自动赚币) via the okx CLI.

    187 GitHub starsUsed in 2 repos~3.3k tokens
    Business, Finance & HRAuto-check passed
  • Surf

    BlockRunAI/ClawRouter

    Use this skill — NOT browser or webfetch — for ALL Surf crypto-data calls.

    6.6k GitHub stars~4k tokensUpdated 5 days ago
    Business, Finance & HRAuto-check passed
  • Notebook To Strategy

    tradingstrategy-ai/trade-executor

    Transfer code from a backtesting Jupyter notebook to a Trade Executor strategy module

    160 GitHub stars~1.1k tokensUpdated 2 days ago
    Business, Finance & HRAuto-check passed
  • Building Blocks

    austintgriffith/ethskills

    DeFi legos and protocol composability on Ethereum and L2s. An agent skill from austintgriffith/ethskills.

    295 GitHub stars~2.9k tokensUpdated 1 mo ago
    Business, Finance & HRAuto-check passed

More from Signal-Execution-Labs/forex-trading-ai-agent

All 11 skills in this repo
  • Rebalancer

    Signal-Execution-Labs/forex-trading-ai-agent

    Automatic portfolio rebalancing to maintain target allocations.

    162 GitHub stars~2.2k tokensUpdated 27 days ago
    Auto-check passed
  • Alert System

    Signal-Execution-Labs/forex-trading-ai-agent

    Set price alerts, volume alerts, indicator alerts (RSI/MACD), and news alerts for crypto trading.

    162 GitHub stars~1.6k tokensUpdated 27 days ago
    Auto-check passed
  • Auto Trader

    Signal-Execution-Labs/forex-trading-ai-agent

    Automated trading with strategy execution, risk management, position sizing, and stop-loss/take-profit.

    162 GitHub stars~2.1k tokensUpdated 27 days ago
    Auto-check passed
  • Backtester

    Signal-Execution-Labs/forex-trading-ai-agent

    Backtest trading strategies with historical data. An agent skill from Signal-Execution-Labs/forex-trading-ai-agent.

    162 GitHub stars~2.7k tokensUpdated 27 days ago
    Auto-check passed
  • Dividend Manager

    Signal-Execution-Labs/forex-trading-ai-agent

    Track dividends, manage DRIP (reinvestment), forecast income, and optimize dividend portfolio.

    162 GitHub stars~2.1k tokensUpdated 27 days ago
    Auto-check passed
  • Exchange Connector

    Signal-Execution-Labs/forex-trading-ai-agent

    Connect to crypto exchanges (Binance, Kraken, Coinbase, etc.).

    162 GitHub stars~1k tokensUpdated 27 days ago
    Auto-check passed

Works with

Questions about Defi Connector

What does Defi Connector do?

Connect to DeFi protocols for staking, lending, yield farming, and liquidity provision. Defi Connector is an agent skill from Signal-Execution-Labs/forex-trading-ai-agent. Connect to DeFi protocols for staking, lending, yield farming, and liquidity provision.

When should I use Defi Connector?

Defi Connector fits situations like: tasks that involve Crypto and DeFi analysis; tasks that involve Banking and insurance.

How do I install Defi Connector in Claude Code?

Run `npx skills add Signal-Execution-Labs/forex-trading-ai-agent --skill defi-connector -a claude-code`. Or copy the skill folder (skills/defi-connector in Signal-Execution-Labs/forex-trading-ai-agent) into .claude/skills/defi-connector in your project. Claude Code loads it when a task matches its description.

How do I install Defi Connector in Codex?

Run `npx skills add Signal-Execution-Labs/forex-trading-ai-agent --skill defi-connector -a codex`. Or copy the skill folder (skills/defi-connector in Signal-Execution-Labs/forex-trading-ai-agent) into .agents/skills/defi-connector in your project. Codex loads it when a task matches its description.

Can I use Defi Connector in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Signal-Execution-Labs/forex-trading-ai-agent --skill defi-connector -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/defi-connector, .gemini/skills/defi-connector, .github/skills/defi-connector and .opencode/skills/defi-connector in your project.

What does Defi Connector need to run?

Going by SKILL.md and its folder, Defi Connector needs Python for the scripts in its folder and the command-line tools its instructions call (python3 and hf). Our summary lists: Python 3.

Does Defi Connector access the network?

SKILL.md names 2 domains. In commands or code: api.llama.fi and yields.llama.fi; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Defi Connector safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Defi Connector use?

Defi Connector is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Defi Connector use?

About 2.4k tokens (SKILL.md is roughly 9.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Defi Connector?

Skills that share tags, products or a category with Defi Connector: Swapper Deposit (swapperfinance/swapper-toolkit, 852 stars), Aomi Transact (jeremylongshore/tons-of-skills-marketplace, 2.8k stars), Okx Cex Earn (okx/agent-skills, 187 stars) and Surf (BlockRunAI/ClawRouter, 6.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Defi Connector?

Signal-Execution-Labs (a GitHub organization) maintains it in Signal-Execution-Labs/forex-trading-ai-agent, which has 162 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on September 14, 2026.

Source: Signal-Execution-Labs/forex-trading-ai-agent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.