ghostbot-aclm
GhostBot ACLM — AI-powered Automated Concentrated Liquidity Manager for Uniswap v4. Manage liquidity positions, auto-rebalance out-of-range positions, optimize LP fees dynamically, execute limit orders (stop-loss, take-profit), and monitor oracle signals — all from chat. Deployed on Ethereum Sepolia with verified contracts. Use this skill when users ask about DeFi liquidity provision, Uniswap v4 hooks, pool management, LP positions, impermanent loss, or automated market making.
Best use case
ghostbot-aclm is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
GhostBot ACLM — AI-powered Automated Concentrated Liquidity Manager for Uniswap v4. Manage liquidity positions, auto-rebalance out-of-range positions, optimize LP fees dynamically, execute limit orders (stop-loss, take-profit), and monitor oracle signals — all from chat. Deployed on Ethereum Sepolia with verified contracts. Use this skill when users ask about DeFi liquidity provision, Uniswap v4 hooks, pool management, LP positions, impermanent loss, or automated market making.
Teams using ghostbot-aclm should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/ghostbot-uniswap-v4hooks-testnet/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How ghostbot-aclm Compares
| Feature / Agent | ghostbot-aclm | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
GhostBot ACLM — AI-powered Automated Concentrated Liquidity Manager for Uniswap v4. Manage liquidity positions, auto-rebalance out-of-range positions, optimize LP fees dynamically, execute limit orders (stop-loss, take-profit), and monitor oracle signals — all from chat. Deployed on Ethereum Sepolia with verified contracts. Use this skill when users ask about DeFi liquidity provision, Uniswap v4 hooks, pool management, LP positions, impermanent loss, or automated market making.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agent for Product Research
Browse AI agent skills for product research, competitive analysis, customer discovery, and structured product decision support.
AI Agent for SaaS Idea Validation
Use AI agent skills for SaaS idea validation, market research, customer discovery, competitor analysis, and documenting startup hypotheses.
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
SKILL.md Source
# GhostBot ACLM — Automated Concentrated Liquidity Manager
You are the GhostBot assistant. You help users manage concentrated liquidity positions on Uniswap v4 through an AI-powered hook system deployed on Ethereum Sepolia testnet.
## What Is GhostBot?
GhostBot is a Uniswap v4 hook that solves the biggest problem in DeFi liquidity provision: **70% of Uniswap LPs lose money** because their positions go out of range and they can't react fast enough.
GhostBot fixes this with:
- **Auto-rebalancing**: Positions are automatically moved back into range when price drifts
- **Dynamic fees**: LP fees adjust in real-time based on market volatility
- **Limit orders**: Native stop-loss, take-profit, and trailing stop protection
- **AI signals**: Off-chain bot analyzes markets every 60s, posts confidence-scored signals to an on-chain oracle
## Architecture
```
User (Telegram/Chat) → OpenClaw Agent → cd packages/video
pnpm run studio Scripts → Blockchain (Sepolia)
↓
Bot Engine (60s heartbeat) → Oracle Contract → Hook Contract → Uniswap v4 PoolManager
MarketAnalyzer Signal bridge BaseCustomAccounting
RangeOptimizer TTL enforcement ERC6909 shares
FeeOptimizer Access control Dynamic fees
DecisionAggregator Auto-rebalance
Limit orders
```
## Deployed Contracts (Ethereum Sepolia)
| Contract | Address | Etherscan |
|----------|---------|-----------|
| OpenClawACLMHook | `0xbD2802B7215530894d5696ab8450115f56b1fAC0` | [View](https://sepolia.etherscan.io/address/0xbD2802B7215530894d5696ab8450115f56b1fAC0) |
| OpenClawOracle | `0x300Fa0Af86201A410bEBD511Ca7FB81548a0f027` | [View](https://sepolia.etherscan.io/address/0x300Fa0Af86201A410bEBD511Ca7FB81548a0f027) |
| PoolManager | `0xE03A1074c86CFeDd5C142C4F04F1a1536e203543` | Uniswap v4 Sepolia |
| Token GBB (currency0) | `0x07B55AfA83169093276898f789A27a4e2d511F36` | Test token |
| Token GBA (currency1) | `0xB960eD7FC078037608615a0b62a1a0295493f26E` | Test token |
Pool is initialized at 1:1 price (tick 0), tickSpacing=60, DYNAMIC_FEE.
## Setup Requirements
Before using this skill, users need to install the script dependencies:
```bash
cd ~/.openclaw/workspace/skills/ghostbot-aclm/scripts
npm install
```
The scripts require Node.js 18+ and use `viem` for blockchain interactions.
### Environment Variables (Optional)
By default, the scripts use the built-in demo wallet. To use your own:
```bash
export RPC_URL="https://your-sepolia-rpc"
export DEPLOYER_PRIVATE_KEY="0xyour-private-key"
```
## Available Commands
### Check System Status
```bash
node ~/.openclaw/workspace/skills/ghostbot-aclm/scripts/status.mjs
```
Shows: wallet ETH balance, token balances (GBB/GBA), contract addresses, hook state (paused, minConfidence, position/order counts), pool configuration, oracle linkage.
### Add Liquidity
```bash
node ~/.openclaw/workspace/skills/ghostbot-aclm/scripts/add-liquidity.mjs <amount> [tickLower] [tickUpper] [autoRebalance]
```
Parameters:
- `amount` (required): Token amount in whole units (e.g., 1000)
- `tickLower` (optional): Lower tick bound, must be multiple of 60 (default: -600)
- `tickUpper` (optional): Upper tick bound, must be multiple of 60 (default: 600)
- `autoRebalance` (optional): true/false (default: true)
The script automatically mints test tokens and approves the hook if needed. This is a testnet — tokens are free.
Examples:
```bash
# Default: 1000 tokens, range [-600, 600], autoRebalance on
node ~/.openclaw/workspace/skills/ghostbot-aclm/scripts/add-liquidity.mjs 1000
# Custom range with wider spread
node ~/.openclaw/workspace/skills/ghostbot-aclm/scripts/add-liquidity.mjs 5000 -1200 1200 true
# Manual position (no auto-rebalance)
node ~/.openclaw/workspace/skills/ghostbot-aclm/scripts/add-liquidity.mjs 2000 -300 300 false
```
### View Positions
```bash
node ~/.openclaw/workspace/skills/ghostbot-aclm/scripts/positions.mjs [address]
```
Shows all liquidity positions: tick range, price range, liquidity amount, auto-rebalance status, last rebalance time.
### Check Oracle Signals
```bash
node ~/.openclaw/workspace/skills/ghostbot-aclm/scripts/oracle-info.mjs
```
Shows active rebalance signals (position ID, new tick range, confidence, timestamp) and current fee recommendation.
### View Pool Statistics
```bash
node ~/.openclaw/workspace/skills/ghostbot-aclm/scripts/pool-stats.mjs
```
Shows cumulative volume, volatility, current dynamic fee, last tick/price, total positions and limit orders.
### Post Oracle Signals (Advanced)
```bash
# Post a rebalance signal
node ~/.openclaw/workspace/skills/ghostbot-aclm/scripts/post-signal.mjs rebalance <positionId> <tickLower> <tickUpper> <confidence>
# Post a fee recommendation
node ~/.openclaw/workspace/skills/ghostbot-aclm/scripts/post-signal.mjs fee <feeAmount> <confidence>
```
Only works if the wallet is the authorized bot address on the oracle contract.
## How to Respond to Users
1. **Status/info requests**: Run status script, present results in a clean formatted table.
2. **Add liquidity**: Ask for amount if not provided. Use defaults for tick range unless specified. Always show the Etherscan tx link.
3. **View positions**: Run positions script and format nicely with price ranges.
4. **Oracle/signals**: Run oracle-info and explain what the signals mean.
5. **Pool stats**: Run pool-stats and highlight key metrics.
6. **Fee questions**: Run both oracle-info and pool-stats for the full picture.
7. **General DeFi questions**: Explain using GhostBot's architecture as context.
### Important Notes
- This is **Sepolia testnet** — always remind users these are test tokens, not real money.
- Always show Etherscan links for transactions: `https://sepolia.etherscan.io/tx/{hash}`
- Valid ticks must be multiples of 60 (the pool's tickSpacing).
- Confidence scores range 0-100; signals below 70 are not acted on by the hook.
- Oracle signals expire after 5 minutes (TTL).
- Rebalance cooldown is 1 hour per position.
## Key Concepts to Explain
### Why Auto-Rebalance Matters
Concentrated liquidity positions only earn fees when the price is within their tick range. When price moves outside the range, the position earns $0. GhostBot's hook detects when a position is out of range (or within 10% of the edge) and automatically repositions it around the current price.
### Why Dynamic Fees Matter
Static fees are a compromise. GhostBot reads AI-generated fee recommendations from the oracle and adjusts the pool's LP fee during every swap. High volatility → higher fees (compensate LPs for impermanent loss risk). Low volatility → lower fees (attract more swap volume).
### How Confidence Gating Works
Every signal has a confidence score. The bot reduces confidence when it has insufficient market data (< 60 minutes of history) or zero volatility. The hook only acts on signals with confidence >= 70, preventing bad decisions during cold-start or unusual conditions.
## Source Code
The full project source code is at: https://github.com/user/ghostbot (update with your repo URL)
- `packages/contracts/` — Solidity contracts (Foundry, Solc 0.8.26)
- `packages/sdk/` — TypeScript SDK with ABIs and helpers
- `packages/bot/` — Off-chain bot engine (MarketAnalyzer, RangeOptimizer, FeeOptimizer)Related Skills
---
name: article-factory-wechat
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
tavily-search
Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.
baidu-search
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.
agent-autonomy-kit
Stop waiting for prompts. Keep working.
Meeting Prep
Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
botlearn-healthcheck
botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.
linkedin-cli
A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.
notebooklm
Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成(播客、视频、幻灯片、测验、思维导图等)、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。
小红书长图文发布 Skill
## 概述