home / skills / omer-metin / skills-for-antigravity / algorithmic-trading

algorithmic-trading skill

safe

This skill helps you design, backtest, and deploy algorithmic trading strategies with risk controls and performance insights for reliable live execution.

npx playbooks add skill omer-metin/skills-for-antigravity --skill algorithmic-trading

Review the files below or copy the command above to add this skill to your agents.

Files (4)

SKILL.md

1.1 KB

---
name: algorithmic-trading
description: Use when building trading systems, backtesting strategies, implementing execution algorithms, or analyzing market microstructure - covers strategy development, risk management, and production deploymentUse when ", " mentioned. 
---

# Algorithmic 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.

Overview

This skill helps build, test, and deploy algorithmic trading systems with a focus on strategy development, execution algorithms, risk management, and production hardening. It enforces established construction patterns, highlights critical failure modes, and validates designs against strict operational constraints. Use this skill to get actionable guidance grounded in tested patterns, sharp-edge diagnostics, and objective validations.

How this skill works

I inspect your strategy design, backtest setup, execution logic, and risk controls against a canonical pattern library for how systems should be built. I then run diagnostic checks that surface common and severe failure modes, and finally validate configuration and inputs against a ruleset of required constraints. If your request conflicts with the patterns, risks, or validations, I will correct it and propose compliant alternatives.

When to use it

Designing or implementing a new trading strategy or execution algorithm
Setting up backtests and forward tests to avoid lookahead bias and mis-specified fills
Reviewing production deployment plans for latency, resilience, and observability
Performing risk assessments and failure-mode analysis before go-live
Validating inputs, parameter ranges, and operational constraints prior to deployment

Best practices

Follow prescribed design patterns for modular strategy, execution, and risk components
Run deterministic backtests with explicit data hygiene, slippage, and realistic fills
Include explicit, tested risk limits and automated kill-switches in execution paths
Instrument production code with metrics, tracing, and alerting for business and tech KPIs
Validate inputs and parameter ranges programmatically to prevent invalid deployments

Example use cases

Converting a research signal into a production-ready strategy that isolates alpha, execution, and risk
Diagnosing sudden PnL drawdowns by mapping them to known sharp-edge failure modes
Hardening a low-latency execution routine for resilience under market stress
Validating backtest configuration to ensure no lookahead, correct fills, and realistic transaction costs
Auditing a deployment pipeline to ensure proper monitoring, canarying, and rollback capabilities

FAQ

What if my requested approach contradicts the recommended patterns?

I will point out the conflict, explain the risks, and suggest compliant alternatives that achieve the same goals while respecting construction patterns and validations.

Can you check my backtest for realistic assumptions?

Yes — I review data usage, survivorship bias, slippage models, and execution assumptions and flag deviations from robust backtest practices.