Aave Liquidation Monitor logo

Aave Liquidation Monitor

Community
lxyeternal
aave-liquidation-monitor

Proactive monitoring of Aave V3 borrow positions with liquidation alerts. Queries user collateral, debt, and health factor across chains (Ethereum, Polygon, Arbitrum, etc.). Sends urgent alerts to Telegram/Discord/Slack when health factor drops below configurable thresholds (critical at 1.05, warning at 1.2). Use when you need continuous monitoring of Aave positions, want alerts before liquidation risk occurs, or need periodic summaries of your borrowing health.

Overview

Publisherlxyeternal
RepositoryMalSkillBench
Skill nameaave-liquidation-monitor
Stars
64
Forks
14
Bundled files
1
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by lxyeternal on GitHub. Read the source before you install it.

Installation

Install the Aave Liquidation Monitor AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/lxyeternal/MalSkillBench/tree/main/Dataset/Skills/benign/aave-liquidation-monitor
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/lxyeternal/MalSkillBench.git /tmp/MalSkillBench
mkdir -p .claude/skills
cp -r /tmp/MalSkillBench/Dataset/Skills/benign/aave-liquidation-monitor .claude/skills/aave-liquidation-monitor
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Aave Liquidation Monitor in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Aave Liquidation Monitor on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Aave Liquidation Monitor is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Aave Liquidation Monitor

Quick Start

Configure your wallet and thresholds once, then the skill runs automatically every 6 hours (configurable).

Step 1: Initialize Your Config

Run /aave-config init to set up:

  • Your Ethereum wallet address (read-only; no private keys required)
  • Health factor thresholds (default: critical 1.05, warning 1.2, stable >1.5)
  • Check interval in hours (default: 6)
  • Notification verbosity (verbose = daily summaries even if stable; quiet = only alerts)
  • Preferred notification channel (Telegram default, or specify Discord/Slack)

Example:

/aave-config init
→ Wallet: 0x1234...5678
→ Thresholds: 1.05 (critical), 1.2 (warning)
→ Interval: 6 hours
→ Verbosity: quiet (alerts only)
→ Channel: telegram

Step 2: Test the Monitor

Run /aave-monitor check to fetch your position immediately and see the alert format:

/aave-monitor check
→ Fetching position for 0x1234...5678 on Ethereum...
→ Health Factor: 2.31 (Stable ✓)
→ Total Collateral: $50,342.12
→ Total Debt: $21,804.00
→ Borrowed Assets: USDC (15,000), WETH (0.5), USDT (6,804)
→ Supplied Assets: WETH (10), USDC (20,000), DAI (30,000)

Step 3: Enable Proactive Monitoring

Run /aave-monitor enable to start automatic checks every 6 hours. The skill registers a cron job that silently runs in the background and alerts you only when health factor drops below threshold.

For manual override:

/aave-monitor enable --interval 4   # Check every 4 hours
/aave-monitor disable               # Stop monitoring
/aave-monitor status                # See current config + last check result

Configuration Reference

See references/config-guide.md for detailed config options, chain support, and threshold guidance.

See references/aave-api.md for Aave V3 GraphQL schema and query patterns.

Security & Credentials: See SECURITY.md for how credentials are handled and threat model.

For auditors: See SECURITY.md for code review checklist and architecture details.

How It Works

  1. Query Phase: Calls Aave V3 GraphQL API with your wallet address
  2. Analysis Phase: Extracts health factor, collateral, debt, borrowed/supplied assets
  3. Alert Logic:
    • If HF < 1.05 → CRITICAL (red alert, send immediately)
    • If HF < 1.2 → WARNING (yellow alert, send immediately)
    • If HF > 1.5 → STABLE (no alert, unless verbose mode enables daily summary)
  4. Notification Phase: Posts alert to your configured channel with clear summary
  5. Retry Logic: If API fails, retries up to 3 times with exponential backoff

Error Handling

  • Invalid wallet address → Logs error, skips check, retries next interval
  • API timeout → Retries up to 3x with exponential backoff (2s, 4s, 8s)
  • Malformed response → Alerts you to API changes, logs full response for debugging
  • Network errors → Silently retries; alerts only if all retries fail

Security & Credentials

NO private keys are requested or stored — this is read-only monitoring only.

How messaging credentials work

The skill uses OpenClaw's built-in message routing — it does NOT store Telegram, Discord, or Slack tokens.

  1. You configure your messaging channel in OpenClaw (outside this skill)
  2. The skill calls OpenClaw's messaging API with just the alert text
  3. OpenClaw routes the message using your configured channels

Example:

/aave-config set channel telegram
→ OpenClaw sends alerts via your pre-configured Telegram channel

You must have a messaging channel already set up in OpenClaw. See OpenClaw docs for setting up Telegram/Discord/Slack integrations.

Data handling

  • Wallet address: Stored in OpenClaw's encrypted config (never sent to external services except Aave's public API)
  • API responses: Parsed for health factor only; sensitive position data is NOT logged
  • Credentials: Managed by OpenClaw, never stored in skill files

What the skill accesses

✅ Aave GraphQL API (public) — reads your position data
✅ OpenClaw message routing — sends formatted alerts to your configured channel
✅ Cron scheduler — runs background checks on your interval

❌ Does NOT:

  • Request private keys
  • Store API tokens
  • Execute transactions
  • Modify your positions

Examples

Alert Examples

Critical Alert (HF < 1.05):

🚨 AAVE LIQUIDATION RISK – CRITICAL
Health Factor: 1.02 (Liquidation threshold: 1.0)
⏰ Action required immediately!

📊 Position Summary:
Total Collateral: $50,000
Total Debt: $48,000
Debt Ratio: 96%

Borrowed (at risk):
- USDC: 40,000
- WETH: 8 ETH (~$31k)

Suggested Actions:
1. Repay debt (especially WETH)
2. Supply more collateral
3. Enable eMode if available (higher LTV on correlated assets)

Last checked: 2026-02-11 08:15 UTC

Warning Alert (HF < 1.2):

⚠️ AAVE WARNING
Health Factor: 1.15 (Approaching 1.2 threshold)

Position approaching liquidation. Consider:
- Repaying $2,000 USDC or
- Adding $5,000 collateral (WETH or stETH)

Stable Position (HF > 1.5, verbose mode only):

✅ AAVE POSITION HEALTHY
Health Factor: 2.31
Total Collateral: $50,342.12
Total Debt: $21,804.00

All clear. Check again tomorrow.

Command Examples

bash
# One-time position check
/aave-monitor check

# Start automatic monitoring
/aave-monitor enable

# Change thresholds (e.g., earlier warning at HF 1.3)
/aave-config set thresholds 1.05 1.3

# Check monitoring status
/aave-monitor status

# View last 5 check results with alerts
/aave-monitor history 5

# Disable monitoring temporarily
/aave-monitor disable

Chains Supported

Primary: Ethereum mainnet

Also works (with same config address where applicable):

  • Polygon
  • Arbitrum
  • Optimism
  • Base
  • Avalanche
  • Gnosis

Edit scripts/monitor.js to add chains or customize per-chain endpoints.

Customization

Change check interval:

/aave-config set interval 4  # Check every 4 hours

Change alert thresholds:

/aave-config set thresholds 1.1 1.25  # Critical at 1.1, warning at 1.25

Enable verbose mode (daily summaries even if stable):

/aave-config set verbosity verbose

Switch notification channel:

/aave-config set channel discord

Implementation Details

See scripts/monitor.js for the core monitoring logic (GraphQL queries, health factor calculation, alert formatting).

See scripts/cron-runner.js for cron job integration with OpenClaw's cron scheduler.

Troubleshooting

"Invalid wallet address" → Check format: must be 0x... format. Try /aave-config view to see current config.

"Health factor not returned by API" → Wallet may not have Aave position. Try /aave-monitor check for immediate response.

"API endpoint unreachable" → Aave API may be down. Skill retries automatically. Check https://status.aave.com.

"No notifications sent" → Check that your notification channel is active. Run /aave-monitor check to test delivery.

Notes

  • Health factor = Total Collateral / Total Debt (net of liquidation threshold ratios)
  • Liquidation occurs when HF ≤ 1.0
  • Variable debt accrues interest; stable debt is fixed-rate
  • eMode allows higher LTV for correlated assets (e.g., stablecoins, ETH-LSTs)
  • Supplied assets are collateral; they earn interest but can be seized if you're liquidated

Last Updated: 2026-02-11 | Status: Ready for configuration

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Aave Liquidation Monitor AI skill do?

Proactive monitoring of Aave V3 borrow positions with liquidation alerts. Queries user collateral, debt, and health factor across chains (Ethereum, Polygon, Arbitrum, etc.). Sends urgent alerts to Telegram/Discord/Slack when health factor drops below configurable thresholds (critical at 1.05, warning at 1.2). Use when you need continuous monitoring of Aave positions, want alerts before liquidation risk occurs, or need periodic summaries of your borrowing health.

Why use Aave Liquidation Monitor on TypingMind?

Because you install it once and use it with any model. Aave Liquidation Monitor is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Aave Liquidation Monitor in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/lxyeternal/MalSkillBench/tree/main/Dataset/Skills/benign/aave-liquidation-monitor. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Aave Liquidation Monitor?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Aave Liquidation Monitor?

As many as you like. As long as a model supports skills, you can use Aave Liquidation Monitor with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Aave Liquidation Monitor AI skill free?

It is published on GitHub by lxyeternal. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇