Finance Trading Skill for Openclaw

An automated quantitative strategy skill designed for simulated BTC/USDT paper trading using technical indicators and strict risk protocols.

brioche-bit
v1.0.0
Mar 17, 2026
0
2k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install finance-trading

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install finance-trading using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is Finance Trading Skill?

The Finance Trading skill is a specialized module for Openclaw Skills that enables AI agents to execute quantitative trading strategies in a simulated environment. Focused on the BTC/USDT pair, it utilizes multi-timeframe analysis (1h and 15min) to identify market trends and momentum. This skill is designed for developers and traders who want to test automated strategies without financial risk, leveraging industry-standard indicators like Exponential Moving Averages and the Relative Strength Index.

By integrating this skill, users can automate the tedious process of market monitoring and technical analysis. It bridges the gap between raw market data and actionable insights, ensuring that every simulated trade follows a disciplined, data-driven approach governed by pre-defined technical signals and professional-grade risk management parameters.

Finance Trading Skill Use Cases

  • Automating paper trading sessions for BTC/USDT to test quantitative theories.
  • Monitoring market momentum using RSI and EMA crossovers without manual charting.
  • Generating automated daily performance reports and trading logs for strategy backtesting.
  • Implementing disciplined risk management protocols in a simulated trading environment.

How Finance Trading Skill Works

  1. The skill fetches market data for BTC/USDT across 1h and 15min timeframes.
  2. It calculates technical indicators, specifically the EMA 20, EMA 50, and RSI.
  3. The agent evaluates buy signals (EMA 20 > EMA 50 with RSI between 40-60) or sell signals (EMA 20 < EMA 50 or RSI > 80).
  4. If a signal is triggered, it executes a paper trade limited to 5% of the virtual capital.
  5. Automated Stop Loss (2%) and Take Profit (6%) orders are set immediately.
  6. Every action is recorded in a local log file, and a performance summary is generated daily.

Finance Trading Skill Setup

To deploy this skill within your Openclaw Skills environment, ensure your CLI is configured and run the following sequence:

# Install the finance-trading skill components
openclaw install finance-trading

# Initialize the market data fetcher
fetch market-data BTC/USDT --timeframes 1h 15min

# Verify indicator calculation engine
calculate-indicators --ema-20 --ema-50 --rsi

Finance Trading Skill Data Schema & Taxonomy

The Finance Trading skill maintains a structured record of all activities to ensure transparency and auditability:

File / Data Point Description Format
trading_log.md A continuous journal of every trade executed, including entry/exit prices. Markdown
Daily Report Generated at 18:00 containing Balance, PnL, Win Rate, and Market Sentiment. Markdown
Market Data Cached OHLCV data for 1h and 15min intervals. JSON/CSV
Indicators Computed values for EMA 20, EMA 50, and RSI. Metadata

Finance Trading Skill Advanced Features

  • Multi-timeframe synchronization for high-precision entry signals.
  • Automated daily reporting at 18:00 for performance tracking.
  • Integrated risk management module with hardcoded Stop Loss and Take Profit safety nets.
  • Continuous 15-minute market polling for real-time paper trading execution.
  • Detailed PnL and Win Rate analytics within the Openclaw Skills ecosystem.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*