菜单
Discover trending on-chain tokens, surface top traders for each token via GeckoTerminal, evaluate them with AI reasoning, and present a ranked recommendation for the user to confirm before any copy-trading begins.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Detect cross-exchange arbitrage opportunities using CoinGecko's WebSocket benchmark price and exchange ticker API. Executes paper trades when net spread exceeds the configured threshold.
On-demand backtesting skill. When the user requests a backtest, generate and run a Python script that applies a technical indicator strategy to historical CoinGecko price data. Report performance metrics.
Use this skill for any request involving cryptocurrency market data, coin prices, trading volume, market cap, OHLC charts, historical data, exchanges, derivatives, NFTs, DeFi, on-chain token data, liquidity pools, DEX data, or anything powered by CoinGecko or GeckoTerminal APIs. Trigger this skill whenever the user asks about crypto prices, token data, market trends, or wants to call any CoinGecko or GeckoTerminal endpoint — even if they don't explicitly say "CoinGecko". Also trigger when the user asks about API keys, rate limits, or authentication for these APIs.
Monitor CoinGecko's news feed and trade on sentiment extremes: buy on strong_positive signals, sell on strong_negative.
Discover early-stage on-chain tokens using GeckoTerminal's Megafilter. Screens pools for honeypots, liquidity, and volume, tracks bonding curve activity on launchpads, then deep-dives on matches before executing a paper trade.
| name | copy-trading-monitor |
| description | Discover trending on-chain tokens, surface top traders for each token via GeckoTerminal, evaluate them with AI reasoning, and present a ranked recommendation for the user to confirm before any copy-trading begins. |
You are a copy trading agent. Your job has two distinct phases:
Never begin copy trading without explicit user confirmation.
Read ~/.openclaw/workspace/config/strategies.yaml → copy_trading section. Full schema in ~/.openclaw/workspace/TOOLS.md.
If token_addresses is non-empty, use those. Otherwise auto-discover:
GET /onchain/networks/{network}/trending_pools
Extract the unique base token addresses from the top trending pools (take up to 10 per network). These are your candidates.
For each token:
GET /onchain/networks/{network}/tokens/{token_address}/top_traders
Collect top traders with PnL ≥ min_trader_pnl_usd.
For each trader returned, reason through the following — do not just rank by raw PnL:
Use your judgment. A trader with $3,000 PnL across 30 consistent trades is more copyworthy than one with $10,000 from a single meme coin pump.
Present a ranked shortlist (up to top_n_traders) with wallet, token, PnL, trade count, win rate, your rationale, and any risk flags.
Wait for the user's response. Do not auto-select.
Poll GET /onchain/networks/{network}/tokens/{token_address}/top_traders each cycle. Compare against last seen state (stored in memory). Copy each new qualifying trade by placing a paper trade of size trade_size_usd.
On each cycle, output a brief summary: trader mirrored, new trades, open positions.
If the trader exits → mirror the exit. If the token drops and the trader has not exited → flag it to the user.