hl-privateer
Access HL Privateer, an open agentic Hyperliquid discretionary trading desk. Read live positions, AI analysis, copy-trade signals, and risk state via x402 pay-per-call endpoints. No API keys. No sign-ups. Just x402 on Base (USDC).
Best use case
hl-privateer is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Access HL Privateer, an open agentic Hyperliquid discretionary trading desk. Read live positions, AI analysis, copy-trade signals, and risk state via x402 pay-per-call endpoints. No API keys. No sign-ups. Just x402 on Base (USDC).
Teams using hl-privateer 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/hl-privateer-fund/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How hl-privateer Compares
| Feature / Agent | hl-privateer | 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?
Access HL Privateer, an open agentic Hyperliquid discretionary trading desk. Read live positions, AI analysis, copy-trade signals, and risk state via x402 pay-per-call endpoints. No API keys. No sign-ups. Just x402 on Base (USDC).
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 Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
Best AI Agents for Marketing
A curated list of the best AI agents and skills for marketing teams focused on SEO, content systems, outreach, and campaign execution.
Best AI Skills for ChatGPT
Find the best AI skills to adapt into ChatGPT workflows for research, writing, summarization, planning, and repeatable assistant tasks.
SKILL.md Source
# HL Privateer -- Agent Skill
HL Privateer is an open, agentic discretionary trading desk on Hyperliquid. A fund of autonomous agents making discretionary long/short calls -- positions, analysis, signals, and risk state are all accessible via paid x402 endpoints.
You are an agent. You can follow our trades, read our analysis, copy our positions, or integrate our signals into your own strategy. Pay per call. No API keys. No sign-ups. Just x402.
## Skill Files
This skill package contains the following files, all served at `https://hlprivateer.xyz/skills/`:
| File | Purpose |
|------|---------|
| `hl-privateer.md` | This file. Primary skill definition with full instructions. |
| `llms.txt` | Agent-oriented quick start and endpoint catalog. |
| `api.md` | Complete REST + WebSocket API reference. |
| `x402.md` | x402 payment quickstart with example flows. |
| `agents.json` | Machine-readable OpenAgents v1 discovery document. |
## Quick Start
1. Hit any agent endpoint: `GET https://api.hlprivateer.xyz/v1/agent/stream/snapshot`
2. Receive `402 Payment Required` with `PAYMENT-REQUIRED` header containing payment instructions
3. Decode the header (Base64 JSON) to get price, network, payTo address, and facilitator URL
4. Create and sign an x402 payment payload for the specified amount (USDC on Base)
5. Retry the same request with the `PAYMENT-SIGNATURE` header containing the signed payment (Base64 JSON)
6. Receive data in the `200` response plus `PAYMENT-RESPONSE` settlement header
## Base URLs
- REST API: `https://api.hlprivateer.xyz`
- WebSocket: `wss://ws.hlprivateer.xyz`
- Web UI: `https://hlprivateer.xyz`
## x402 Payment Details
- **Network**: Base (eip155:8453)
- **Asset**: USDC (`0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913`)
- **Facilitator**: `https://facilitator.payai.network`
- **Protocol**: x402 v2 (exact scheme)
See `x402.md` in this directory for the full payment flow with curl examples.
## Paid Endpoints (x402)
All endpoints are GET requests against `https://api.hlprivateer.xyz`. Pay per call via x402.
### $0.01/call
| Endpoint | What You Get |
|----------|-------------|
| `/v1/agent/stream/snapshot` | Mode, PnL%, health, open positions, recent ops tape |
| `/v1/agent/positions` | Full position array -- symbols, sides, sizes, entries, PnL |
| `/v1/agent/orders` | Open orders on the book |
| `/v1/agent/analysis?latest=true` | Latest AI strategist analysis with thesis and signals |
| `/v1/agent/analysis` | Analysis history (paginated, filterable by correlationId) |
### $0.02/call
| Endpoint | What You Get |
|----------|-------------|
| `/v1/agent/insights?scope=market` | Risk config, signal timeline, account snapshot |
| `/v1/agent/insights?scope=ai` | Full dashboard: floor state, risk, analysis, copy summary |
### $0.03/call
| Endpoint | What You Get |
|----------|-------------|
| `/v1/agent/copy/trade?kind=signals` | Audit trail of proposals, analysis, risk decisions, basket events |
| `/v1/agent/copy/trade?kind=positions` | Position data formatted for copy-trading |
## Free Endpoints (no payment required)
| Endpoint | What You Get |
|----------|-------------|
| `/v1/public/pnl` | Current PnL% and runtime mode |
| `/v1/public/floor-snapshot` | Mode, PnL%, health, account value, positions, ops tape |
| `/v1/public/floor-tape` | Recent ops log lines from all agent roles |
| `/healthz` | Service health check |
### Example: Check Current PnL (free)
```bash
curl https://api.hlprivateer.xyz/v1/public/pnl
```
```json
{
"pnlPct": 1.92,
"mode": "READY",
"updatedAt": "2026-02-13T16:20:00Z"
}
```
## Agent Use Cases
### Copy Trading
Read positions and signals to mirror trades on your own account.
1. Poll `/v1/agent/positions` for current positions ($0.01)
2. Poll `/v1/agent/copy/trade?kind=signals` for entry/exit signals ($0.03)
3. Poll `/v1/agent/copy/trade?kind=positions` for copy-formatted position data ($0.03)
### Signal Integration
Consume analysis and risk signals to inform your own strategy.
1. Read `/v1/agent/analysis?latest=true` for the latest strategist thesis ($0.01)
2. Read `/v1/agent/insights?scope=ai` for full AI floor summary ($0.02)
3. Subscribe to WebSocket at `wss://ws.hlprivateer.xyz` for real-time floor tape
### Monitoring / Dashboard
Build a monitoring view or alerting system.
1. Free: Poll `/v1/public/floor-snapshot` for mode, PnL, positions
2. Paid: Read `/v1/agent/stream/snapshot` for richer health and ops data ($0.01)
3. Paid: Read `/v1/agent/insights?scope=market` for risk config and signal timeline ($0.02)
### Portfolio Composition Research
Understand how the desk constructs and manages its basket.
1. Read `/v1/agent/analysis` for historical analysis entries ($0.01)
2. Read `/v1/agent/insights?scope=ai` for the full AI dashboard ($0.02)
3. Read `/v1/agent/copy/trade?kind=signals` for the full proposal audit trail ($0.03)
## WebSocket Protocol
Connect to `wss://ws.hlprivateer.xyz` for real-time events.
### Subscribe to channels
```json
{ "type": "sub.add", "channel": "public.tape" }
```
### Receive events
```json
{
"type": "event",
"channel": "public.tape",
"payload": {
"eventType": "FLOOR_TAPE",
"role": "strategist",
"line": "LONG HYPE -- momentum breakout, funding neutral"
}
}
```
### Client message types
| Type | Purpose |
|------|---------|
| `sub.add` | Subscribe to a channel |
| `sub.remove` | Unsubscribe from a channel |
| `cmd.exec` | Execute a command (requires auth) |
| `ping` | Keepalive |
### Server message types
| Type | Purpose |
|------|---------|
| `sub.ack` | Subscription confirmed |
| `event` | Channel event payload |
| `cmd.result` | Command execution result |
| `error` | Error response |
| `pong` | Keepalive response |
## How The Desk Works
HL Privateer runs autonomous agents on a single Hyperliquid account:
- **Strategist**: scans 50+ perp markets, generates long/short proposals with thesis and sizing
- **Research**: regime hypotheses, macro context, funding analysis, social sentiment
- **Risk**: explains risk posture (advisory only -- hard-gated by deterministic risk engine)
- **Execution**: suggests tactics, annotates slippage expectations
- **Ops**: monitors feeds, service health, circuit breakers (3s heartbeat)
- **Market Data**: detects stale feeds, regime shifts, funding divergences
- **Scribe**: produces audit narratives for each proposal cycle
All proposals pass through a deterministic risk engine (fail-closed) before execution. No agent can bypass risk limits. The human operator holds kill-switch authority.
## Runtime Modes
| Mode | Meaning |
|------|---------|
| `INIT` | Starting up, loading keys and config |
| `WARMUP` | Collecting initial market data window |
| `READY` | Flat, watching for opportunities |
| `IN_TRADE` | Active long/short positions |
| `REBALANCE` | Adjusting position weights for parity |
| `HALT` | Operator-initiated stop |
| `SAFE_MODE` | Automatic safety stop (dependency or data failure) |
## Error Responses
All errors follow a standard envelope:
```json
{
"error": {
"code": "RISK_DENY",
"message": "Proposal denied by max drawdown rule",
"requestId": "req_01J..."
}
}
```
Common error codes:
| Code | Meaning |
|------|---------|
| `PAYMENT_REQUIRED` | x402 payment needed (HTTP 402) |
| `UNAUTHORIZED` | Missing or invalid authentication |
| `FORBIDDEN` | Insufficient tier or capability |
| `RISK_DENY` | Risk engine denied the action |
| `RATE_LIMITED` | Too many requests |
| `INTERNAL_ERROR` | Server error |
## Further Reading
- Full API reference: https://hlprivateer.xyz/skills/api.md
- x402 payment guide: https://hlprivateer.xyz/skills/x402.md
- Machine-readable discovery: https://hlprivateer.xyz/skills/agents.json
- Agent-oriented quick start: https://hlprivateer.xyz/skills/llms.txt
- Root agent index: https://hlprivateer.xyz/AGENT.md
- Root LLM map: https://hlprivateer.xyz/llms.txtRelated 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