Quant Analyst
Implement backtests, risk metrics, and portfolio math for trading or analytics side projects with validated data pipelines.
Overview
quant-analyst is an agent skill most often used in Build (also Validate scope, Operate iterate) that guides financial modeling, backtesting, and risk metrics for trading strategies.
Install
npx skills add https://github.com/sickn33/antigravity-awesome-skills --skill quant-analystWhat is this skill?
- Covers VaR, Sharpe ratio, max drawdown, and options Greeks outputs
- Emphasizes data cleaning, transaction costs, slippage, and out-of-sample tests
- Portfolio optimization patterns (Markowitz, Black-Litterman) and pairs trading
- Five-step approach: validate inputs, robust backtests, risk-adjusted focus, OOS testing, research vs production split
- Five-step approach including out-of-sample testing and research versus production separation
Adoption & trust: 607 installs on skills.sh; 40.1k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You have market data and a strategy idea but no disciplined backtest, risk metrics, or separation between research scripts and shippable code.
Who is it for?
Indie devs building trading bots, portfolio analyzers, or quant research tools who need structured quant workflows in agent sessions.
Skip if: General spreadsheet budgeting, pure chart UI with no models, or regulated investment advice without human review and compliance.
When should I use this skill?
Working on quant analyst tasks: financial models, backtesting trading strategies, or analyzing market data with risk and portfolio methods.
What do I get? / Deliverables
After the skill runs, you get vectorized strategy code, backtest outputs with costs and slippage, and documented risk metrics ready for further Operate hardening.
- Strategy implementation with vectorized operations
- Backtest result summaries with risk metrics
- Documented validation and OOS test protocol
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Strategy code and vectorized backtests land in Build, while research framing spans Validate; Build is the canonical shelf for production-oriented quant modules. Backend subphase fits numerical engines, strategy modules, and separation of research versus production code—not storefront UI.
Where it fits
Define strategy constraints, data sources, and out-of-sample rules before writing execution code.
Implement vectorized backtests with slippage and produce Sharpe and drawdown tables.
Refactor research notebooks into monitored production jobs with clearer research versus prod boundaries.
How it compares
Methodology skill for modeling and backtests—not a live brokerage integration or MCP market-data feed by itself.
Common Questions / FAQ
Who is quant-analyst for?
Solo builders and technical founders implementing quant strategies, risk dashboards, or backtest tooling with agent assistance.
When should I use quant-analyst?
In Validate (scope) to frame strategy constraints; in Build (backend) to code backtests; in Operate (iterate) when promoting research code toward production monitoring.
Is quant-analyst safe to install?
It is marked community-sourced with safe risk in metadata—still review Security Audits on this page and never pipe live secrets or unvetted data vendors without your own compliance check.
SKILL.md
READMESKILL.md - Quant Analyst
## Use this skill when - Working on quant analyst tasks or workflows - Needing guidance, best practices, or checklists for quant analyst ## Do not use this skill when - The task is unrelated to quant analyst - You need a different domain or tool outside this scope ## Instructions - Clarify goals, constraints, and required inputs. - Apply relevant best practices and validate outcomes. - Provide actionable steps and verification. - If detailed examples are required, open `resources/implementation-playbook.md`. You are a quantitative analyst specializing in algorithmic trading and financial modeling. ## Focus Areas - Trading strategy development and backtesting - Risk metrics (VaR, Sharpe ratio, max drawdown) - Portfolio optimization (Markowitz, Black-Litterman) - Time series analysis and forecasting - Options pricing and Greeks calculation - Statistical arbitrage and pairs trading ## Approach 1. Data quality first - clean and validate all inputs 2. Robust backtesting with transaction costs and slippage 3. Risk-adjusted returns over absolute returns 4. Out-of-sample testing to avoid overfitting 5. Clear separation of research and production code ## Output - Strategy implementation with vectorized operations - Backtest results with performance metrics - Risk analysis and exposure reports - Data pipeline for market data ingestion - Visualization of returns and key metrics - Parameter sensitivity analysis Use pandas, numpy, and scipy. Include realistic assumptions about market microstructure. ## Limitations - Use this skill only when the task clearly matches the scope described above. - Do not treat the output as a substitute for environment-specific validation, testing, or expert review. - Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.