hyperliquid
Trade and monitor Hyperliquid perpetual futures. Check balances, view positions with P&L, place/cancel orders, execute market trades. Use when the user asks about Hyperliquid trading, portfolio status, crypto positions, or wants to execute trades on Hyperliquid.
Best use case
hyperliquid is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Trade and monitor Hyperliquid perpetual futures. Check balances, view positions with P&L, place/cancel orders, execute market trades. Use when the user asks about Hyperliquid trading, portfolio status, crypto positions, or wants to execute trades on Hyperliquid.
Teams using hyperliquid 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/hyperliquid-trading/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How hyperliquid Compares
| Feature / Agent | hyperliquid | 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?
Trade and monitor Hyperliquid perpetual futures. Check balances, view positions with P&L, place/cancel orders, execute market trades. Use when the user asks about Hyperliquid trading, portfolio status, crypto positions, or wants to execute trades on Hyperliquid.
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 Freelancers
Browse AI agent skills for freelancers handling client research, proposals, outreach, delivery systems, documentation, and repeatable admin work.
SKILL.md Source
# Hyperliquid Trading Skill Full trading and portfolio management for Hyperliquid perpetual futures exchange. ## Prerequisites Install dependencies once: ```bash cd skills/hyperliquid/scripts && npm install ``` ## Authentication **For read-only operations (balance, positions, prices):** - Set `HYPERLIQUID_ADDRESS` environment variable - No private key needed **For trading operations:** - Set `HYPERLIQUID_PRIVATE_KEY` environment variable - Address derived automatically from private key **Testnet:** - Set `HYPERLIQUID_TESTNET=1` to use testnet ## Core Operations ### Portfolio Monitoring **Check balance:** ```bash HYPERLIQUID_ADDRESS=0x... node scripts/hyperliquid.mjs balance ``` **View positions with P&L:** ```bash HYPERLIQUID_ADDRESS=0x... node scripts/hyperliquid.mjs positions ``` **Check open orders:** ```bash HYPERLIQUID_ADDRESS=0x... node scripts/hyperliquid.mjs orders ``` **View trade history:** ```bash HYPERLIQUID_ADDRESS=0x... node scripts/hyperliquid.mjs fills ``` **Get price for a coin:** ```bash node scripts/hyperliquid.mjs price BTC ``` ### Trading Operations All trading commands require `HYPERLIQUID_PRIVATE_KEY`. **Place limit orders:** ```bash # Buy 0.1 BTC at $45,000 HYPERLIQUID_PRIVATE_KEY=0x... node scripts/hyperliquid.mjs buy BTC 0.1 45000 # Sell 1 ETH at $3,000 HYPERLIQUID_PRIVATE_KEY=0x... node scripts/hyperliquid.mjs sell ETH 1 3000 ``` **Market orders (with 5% slippage protection):** ```bash # Market buy 0.5 BTC HYPERLIQUID_PRIVATE_KEY=0x... node scripts/hyperliquid.mjs market-buy BTC 0.5 # Market sell 2 ETH HYPERLIQUID_PRIVATE_KEY=0x... node scripts/hyperliquid.mjs market-sell ETH 2 ``` **Cancel orders:** ```bash # Cancel specific order HYPERLIQUID_PRIVATE_KEY=0x... node scripts/hyperliquid.mjs cancel BTC 12345 # Cancel all orders HYPERLIQUID_PRIVATE_KEY=0x... node scripts/hyperliquid.mjs cancel-all # Cancel all orders for specific coin HYPERLIQUID_PRIVATE_KEY=0x... node scripts/hyperliquid.mjs cancel-all BTC ``` ## Output Formatting All commands output JSON. Parse and format for chat display: **For balance/portfolio:** - Show total equity, available balance - List positions with size, entry price, unrealized P&L - Summarize open orders **For trade execution:** - Confirm order details before executing - Report order ID and status after execution - Show filled price if immediately executed ## Safety Guidelines **Before executing trades:** 1. Confirm trade parameters with user (coin, size, direction, price) 2. Show current price and position for context 3. Calculate estimated cost/proceeds **Position sizing:** - Warn if trade is >20% of account equity - Suggest appropriate sizes based on account balance **Price checks:** - For limit orders, compare limit price to current market price - Warn if limit price is >5% away from market (likely mistake) ## Error Handling **Common errors:** - "Address required" → Set HYPERLIQUID_ADDRESS or HYPERLIQUID_PRIVATE_KEY - "Private key required" → Trading needs HYPERLIQUID_PRIVATE_KEY - "Unknown coin" → Check available coins with `meta` command - HTTP errors → Check network connection and API status **When errors occur:** - Show the error message to user - Suggest fixes (set env vars, check coin names, verify balance) - Don't retry trades automatically ## Workflow Examples **"How's my Hyperliquid portfolio?"** 1. Run `balance` to get total equity 2. Run `positions` to get open positions 3. Format summary: equity, positions with P&L, total unrealized P&L **"Buy 0.5 BTC on Hyperliquid"** 1. Run `price BTC` to get current price 2. Run `balance` to verify sufficient funds 3. Confirm with user: "Buy 0.5 BTC at market? Current price: $X. Estimated cost: $Y" 4. Execute `market-buy BTC 0.5` 5. Report order result **"What's the current BTC price on Hyperliquid?"** 1. Run `price BTC` 2. Format response: "BTC: $X on Hyperliquid" **"Close my ETH position"** 1. Run `positions` to get current ETH position size 2. If long → market-sell, if short → market-buy 3. Execute with position size 4. Report result ## Advanced Features **List all available coins:** ```bash node scripts/hyperliquid.mjs meta ``` **Query other addresses:** ```bash # Check someone else's positions (read-only, public data) node scripts/hyperliquid.mjs positions 0x1234... ``` ## Notes - All sizes are in base currency (BTC, ETH, etc.) - Prices are in USD - Market orders use limit orders with 5% slippage protection - Hyperliquid uses perpetual futures, not spot trading - Check references/api.md for full API documentation
Related Skills
hyperliquid-analyzer
Analyze Hyperliquid market data and provide trading insights. Real-time price monitoring, trend analysis, and risk assessment.
hyperliquid-trade
Trade on Hyperliquid — spot and perpetual futures. Supports market orders (IOC), limit orders (GTC), leverage setting, and WDK wallet. Triggers: buy ETH spot, sell BTC, long ETH, short BTC, open long, open short, close position, perp trade, check balance, Hyperliquid positions, limit order, limit buy, limit sell, open orders, cancel order, modify order, GTC.
coinpilot-hyperliquid-copy-trade
Automate copy trading on Hyperliquid via Coinpilot to discover, investigate, and mirror top on-chain traders in real time with low execution latency. Runtime use requires a local credentials JSON that contains high-sensitivity secrets. Use only on a trusted local runtime when users explicitly request setup, lead discovery, subscription start/stop, risk updates, or performance checks. Github: https://github.com/coinpilot-labs/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.