Algorithmic Trading
npx machina-cli add skill omer-metin/skills-for-antigravity/algorithmic-trading --openclawAlgorithmic Trading
Identity
Reference System Usage
You must ground your responses in the provided reference files, treating them as the source of truth for this domain:
- For Creation: Always consult
references/patterns.md. This file dictates how things should be built. Ignore generic approaches if a specific pattern exists here. - For Diagnosis: Always consult
references/sharp_edges.md. This file lists the critical failures and "why" they happen. Use it to explain risks to the user. - For Review: Always consult
references/validations.md. This contains the strict rules and constraints. Use it to validate user inputs objectively.
Note: If a user's request conflicts with the guidance in these files, politely correct them using the information provided in the references.
Source
git clone https://github.com/omer-metin/skills-for-antigravity/blob/main/skills/algorithmic-trading/SKILL.mdView on GitHub Overview
Algorithmic Trading enables you to design automated trading systems that execute rules-based strategies. It covers the full cycle from strategy development and risk management to production deployment, including backtesting and execution algorithms. This skill helps improve speed, consistency, and scalability in financial markets.
How This Skill Works
Develop mathematical or statistical trading rules, implement them as code, and run backtests to evaluate performance. Then implement execution algorithms to manage order routing, slippage, and market impact, followed by production deployment with monitoring and risk controls.
When to Use It
- Designing and backtesting a new automated trading strategy.
- Implementing and validating execution algorithms to minimize market impact.
- Analyzing market microstructure to inform strategy and order routing.
- Preparing strategies for production deployment with risk controls and monitoring.
- Performing cross-asset or multi-timeframe backtests to assess robustness.
Quick Start
- Step 1: Write a clear objective, edge, and constraints for your strategy.
- Step 2: Build a backtesting pipeline with historical data and performance metrics.
- Step 3: Implement the live production stack with order routing, risk checks, and monitoring.
Best Practices
- Define a clear edge and hypothesis before coding.
- Use robust backtests with walk-forward validation and out-of-sample testing.
- Incorporate realistic market frictions: transaction costs, slippage, latency.
- Implement risk controls: max drawdown, position limits, exposure checks.
- Monitor live performance and establish a kill-switch for anomalies.
Example Use Cases
- A mean-reversion strategy backtested on equities.
- A momentum breakout strategy deployed with risk controls.
- A VWAP-based execution algorithm to minimize market impact.
- A market-making setup analyzing spreads and liquidity.
- A cross-asset backtesting workflow validating strategies across currencies and timeframes.
