← 返回 Skills 市场
davidm413

hyperliquid-btc-auto-trader

作者 davidm413 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
99
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install hyperliquid-btc-auto-trader
功能描述
Autonomous BTC-USDC trading bot on Hyperliquid mainnet using multi-timeframe anchored VWAP and strict safety limits for live market execution.
使用说明 (SKILL.md)

Hyperliquid BTC Auto Trader\r

\r Fully autonomous BTC-USDC trading bot for Hyperliquid mainnet\r \r This skill turns Claude/OpenClaw into a complete, production-grade autonomous trading system using the exact sophisticated multi-timeframe anchored VWAP strategy you requested.\r \r

Core Strategy (exactly as specified)\r

  • Market regime detection (trending_bull, trending_bear, ranging, volatile, transition) using ADX14 + ATR% + SMA50/200\r
  • Volume profile analysis with 50-bin HVN/LVN anchors\r
  • Swing point detection with 5-candle lookback + 1.5× volume confirmation\r
  • Multi-timeframe anchors: daily (last 7 days), weekly (last 4 weeks), swing points, volume nodes, trend-start anchors\r
  • Anchored VWAP with 0.95 exponential time decay + confidence scoring\r
  • Confluence zone detection (VWAP clusters within 0.5%)\r
  • Weighted signal score combining:\r
    • VWAP deviation (core)\r
    • Confluence adjustment (±30)\r
    • Regime adjustment (±10)\r
    • Order book imbalance (top 20 levels, 25% weight)\r
    • Trade flow (last 50 trades, 20% weight)\r
    • Candle patterns (hammer, engulfing, volume surge, 15% weight)\r
  • Performance-based anchor learning (win-rate × normalized P&L, updates daily after 10 trades)\r \r

Position Management & Execution\r

  • Base size: $2,000 USD\r
  • Signal multiplier: 1.5× (strong ≥80), 1.2× (moderate 60-79)\r
  • Max position: $10,000 USD absolute\r
  • Dynamic TP/SL based on signal strength (2:1 RR on strong signals)\r
  • 40× maximum leverage (hard-capped)\r
  • Real market orders + limit TP + stop-market SL via official Hyperliquid SDK\r \r

Non-Negotiable Safety Limits (enforced at every cycle)\r

  • Max position $10,000\r
  • Max daily loss $500 → pause trading\r
  • Max 5 trades per day\r
  • Minimum USDC balance $20 (configurable)\r
  • Pause after 3 consecutive losses\r
  • 5-minute cooldown after every trade\r
  • Circuit breaker on signal jumps >50 points in \x3C60 seconds\r
  • Manual kill switch available\r \r

Quick Start\r

  1. Set your environment variables:\r
    $env:HYPERLIQUID_WALLET_ADDRESS = "0x..."\r
    $env:HYPERLIQUID_PRIVATE_KEY = "0x..."\r
    

\r \r \r

2. of SKILL.md\r

\r After the frontmatter, add this richer body (replace everything after the ---):\r \r

# Hyperliquid BTC Autonomous Trader\r
\r
**This skill runs a complete autonomous BTC-USDC trading bot on Hyperliquid mainnet using the sophisticated multi-timeframe anchored VWAP strategy.**\r
\r
The bot continuously:\r
- Pulls real 1-minute candles, L2 order book, and recent trades\r
- Detects market regime and selects the best anchors\r
- Calculates anchored VWAPs with exponential decay\r
- Identifies confluence zones\r
- Combines 6 different signal components into a final score\r
- Executes real trades when score ≥ ±60\r
- Enforces every safety limit you specified\r
\r
All calculations use real Hyperliquid API data (no placeholders).\r
\r
**How to use this skill**\r
- Say “Start hyperliquid-btc-auto-trader” to launch the live trading loop\r
- Say “Show current signal” to see live score, regime, and confluence zones\r
- Say “Pause the trader” or “Stop the trader” at any time\r
\r
**Safety first**  \r
All 8 hard safety limits are coded and cannot be bypassed. The bot will never risk more than you allow.\r
\r
**Ready to trade**  \r
Once started, the bot runs completely autonomously 24/7 until you tell it to stop.
安全使用建议
This skill will attempt to run live market trades and requires your wallet/private key — do not provide a mainnet private key unless you fully audit and trust the code. Specific actions to take before installing or running: 1) Treat the registry metadata mismatch as a red flag: confirm with the author why required env vars were omitted. 2) Audit the code paths that use PRIVATE_KEY and Exchange.market_open; verify order sizing, leverage enforcement, and stop-loss logic. 3) Note that several safety claims in SKILL.md are inaccurate: daily_loss and consecutive-loss enforcement and the circuit-breaker are not implemented/wired in; fix or confirm before running. 4) Prefer testing on a sandbox/testnet account with a small balance or a noncustodial key with no funds. 5) If you do run on mainnet, rotate keys afterward and consider hardware/signing proxies so the skill never sees the raw private key. 6) Ask for corrected metadata (declare primary env var) and a cleaned SKILL.md before trusting autonomous operation.
功能分析
Type: OpenClaw Skill Name: hyperliquid-btc-auto-trader Version: 1.0.0 The skill implements an autonomous trading bot for the Hyperliquid mainnet, which requires the user to provide a plaintext private key via environment variables (config.py) and performs live financial transactions (trader.py, safety/limits.py). While the code includes safety features such as a CircuitBreaker and a SafetyManager to enforce trade limits, the handling of sensitive credentials and the instructions in SKILL.md for the AI agent to operate autonomously 24/7 constitute high-risk capabilities. No evidence of intentional malice or data exfiltration was found, but the inherent risks of automated mainnet trading align with the suspicious classification criteria.
能力评估
Purpose & Capability
The code implements an on‑chain trading bot using the Hyperliquid SDK and therefore legitimately needs a wallet address and private key. However the registry metadata declares no required environment variables or primary credential while config.py and SKILL.md explicitly refer to HYPERLIQUID_WALLET_ADDRESS and HYPERLIQUID_PRIVATE_KEY. That metadata mismatch is an incoherence that affects trust and installation decisions.
Instruction Scope
SKILL.md instructs you to export a private key and to start the bot as an autonomous live trader; it also contains duplicated/corrupted content (a second injected markdown section and an unfinished '#### 2. of `SKILL.md`' fragment). The SKILL.md claims 'All 8 hard safety limits are coded and cannot be bypassed', but the code does not implement several of those safeguards (daily_loss and consecutive_losses are tracked but never updated; CircuitBreaker exists but is not wired into the run loop). This is scope creep/misrepresentation: instructions promise stronger safety than the code provides.
Install Mechanism
There is no explicit install spec in the registry, but a requirements.txt lists dependencies (hyperliquid-python-sdk, pandas, pandas_ta, python-dotenv, schedule, numpy). That implies the agent/user must install PyPI packages before running; this is expected but should be made explicit. No external download URLs or opaque installers are present in the manifest (lower install risk), but dependencies from PyPI still deserve review.
Credentials
Requiring a wallet private key and address is proportionate to a trading bot, but the skill metadata does NOT declare those required env vars while the SKILL.md and config.py do. The skill requests a highly sensitive secret (HYPERLIQUID_PRIVATE_KEY) — the registry should declare that as the primary credential. Also consider that the SKILL.md asks you to run on mainnet and sign live trades: supplying a private key to untrusted code risks fund loss; the code does not show any key-protection or usage limits beyond calling the Exchange with the key.
Persistence & Privilege
always:false and default autonomous invocation are set (normal). The skill does not request permanent platform privileges or modify other skills' configs. There is no indication it persists beyond its own runtime files. However, autonomous trading with a private key remains high-impact — combine with other concerns before enabling.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install hyperliquid-btc-auto-trader
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /hyperliquid-btc-auto-trader 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
- Initial release of Hyperliquid BTC Auto Trader skill - Implements full autonomous BTC-USDC trading on Hyperliquid mainnet using a multi-timeframe anchored VWAP strategy - Advanced market regime detection, volume profile, and swing point analysis - Integrates six weighted signal components and performance-based anchor learning - Enforces strict risk management: position, loss, trade, balance, and cooldown limits - Live trading and status/output accessible by simple voice or text commands
元数据
Slug hyperliquid-btc-auto-trader
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

hyperliquid-btc-auto-trader 是什么?

Autonomous BTC-USDC trading bot on Hyperliquid mainnet using multi-timeframe anchored VWAP and strict safety limits for live market execution. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 99 次。

如何安装 hyperliquid-btc-auto-trader?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install hyperliquid-btc-auto-trader」即可一键安装,无需额外配置。

hyperliquid-btc-auto-trader 是免费的吗?

是的,hyperliquid-btc-auto-trader 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

hyperliquid-btc-auto-trader 支持哪些平台?

hyperliquid-btc-auto-trader 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 hyperliquid-btc-auto-trader?

由 davidm413(@davidm413)开发并维护,当前版本 v1.0.0。

💬 留言讨论