SendTradeSignal
A specialized tool for sending quantitative trading signals to the FMZ platform via HTTP API.
About this skill
This skill acts as a crucial bridge, allowing an AI agent to programmatically interact with the FMZ Quantum Trading Platform. By invoking this tool, the AI can transmit structured JSON signals, representing definitive trade actions (buy, sell, wait, close), directly to a designated robot instance on FMZ. It facilitates real-time execution of AI-driven trading decisions, making it invaluable for algorithmic trading systems by ensuring instant command transmission upon AI analysis. Its primary use case is automating trading strategies where an AI's market analysis translates directly into actionable trading signals. The skill ensures secure communication using a user-defined UUID and transmits comprehensive trade details, including action type, target symbol, reference price, and reasoning, all compatible with standard web protocols. Users would leverage this skill to empower their AI agents with the ability to directly influence trading operations on the FMZ platform, ensuring rapid and precise execution of complex quantitative strategies without manual intervention. The secure, structured data transmission guarantees reliable communication between the AI and the trading platform.
Best use case
The primary use case for SendTradeSignal is to enable AI agents to automate quantitative trading strategies on the FMZ Quantum Trading Platform. It's most beneficial for quantitative analysts, algorithmic traders, and developers building AI-driven trading bots who need a reliable and secure method to translate AI-generated insights directly into market actions.
A specialized tool for sending quantitative trading signals to the FMZ platform via HTTP API.
A specified trading action (buy, sell, wait, or close) will be transmitted to your designated FMZ robot instance via HTTP API, potentially triggering a corresponding trade on the platform.
Practical example
Example input
Send a buy signal for BTC_USDT at 65000.0, because MACD golden cross detected on 4H chart.
Example output
Trade signal successfully sent to FMZ platform for BTC_USDT (action: buy, price: 65000.0).
When to use this skill
- When an AI's market analysis concludes with a definitive trading action (buy, sell, wait, close).
- To automate the execution of quantitative trading strategies on the FMZ platform.
- When rapid and programmatic transmission of trading signals is required.
- To integrate AI-driven decision-making directly into a live trading environment.
When not to use this skill
- If you are not using the FMZ Quantum Trading Platform.
- For tasks unrelated to sending trading signals, such as data analysis or general research.
- When manual approval or human oversight is strictly required before executing trades.
- If you lack an active FMZ robot instance configured to receive signals.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/send-signal/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How SendTradeSignal Compares
| Feature / Agent | SendTradeSignal | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | medium | N/A |
Frequently Asked Questions
What does this skill do?
A specialized tool for sending quantitative trading signals to the FMZ platform via HTTP API.
How difficult is it to install?
The installation complexity is rated as medium. You can find the installation instructions above.
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 Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
SKILL.md Source
# SendTradeSignal (FMZ Connector)
## Overview
This skill serves as a bridge between the OpenClaw AI agent and the FMZ Quantum Trading Platform. It enables the AI to execute trade decisions (Buy/Sell/Wait) programmatically by sending structured JSON signals to a specific robot instance running on FMZ.
## Features
- **Real-time Signal Transmission:** Sends trading commands instantly upon AI decision.
- **Secure Communication:** Uses a user-defined UUID to verify the source of the signal, preventing unauthorized access.
- **Structured Data:** Transmits comprehensive trade details including action type, target symbol (e.g., BTC_USDT), reference price, and reasoning.
- **HTTP/HTTPS Support:** Compatible with standard web protocols for broad compatibility.
## Usage
The AI should invoke this tool when a market analysis concludes with a definitive trading action.
### Parameters
| Parameter | Type | Description |
| :--- | :--- | :--- |
| `action` | string | The specific trading action to take. Accepted values: `buy`, `sell`, `wait`, `close`. |
| `symbol` | string | The trading pair symbol, formatted as `BASE_QUOTE` (e.g., `BTC_USDT`, `ETH_USDT`). |
| `price` | float | The current market price or limit price for the order. |
| `reason` | string | A brief explanation of why this trade decision was made (e.g., "RSI overbought", "Breaking support"). |
## Example
When the AI detects a buying opportunity for Bitcoin at 65000 USDT due to a positive trend:
```python
handler(
action="buy",
symbol="BTC_USDT",
price=65000.0,
reason="MACD golden cross detected on 4H chart."
)Related Skills
simple-tech-analyzer - 简易技术分析器
**版本**: 1.0.0
polymarket-sports-edge
Find odds divergence between sportsbook consensus and Polymarket sports markets, then trade the gap.
jarvis-stock-monitor
全功能智能股票监控预警系统 Pro 版。支持成本百分比、均线金叉死叉、RSI 超买超卖、成交量异动、跳空缺口、动态止盈等 7 大预警规则。基础功能免费，高级功能 SkillPay 付费。
---
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.