174 skills · sorted by relevance
Screen Chinese A-shares, Hong Kong stocks, and US stocks using valuation ratios, profitability, and financial statement data. Set criteria to identify value or growth candidates, with market-specific guidance on using the results in historical strategy tests.
Compare exchange-traded funds by fees, tracking accuracy, liquidity, and market-price differences from asset value. Use the China-focused framework and Python examples to screen products, examine sector rotation, and study portfolio allocation.
Evaluate investment funds and ETFs using returns, risk, fees, investment style, and manager performance. Detect changes in style, compare how closely ETFs follow their indexes, and plan portfolios that invest in multiple funds.
Evaluate investment factors across multiple securities using statistical measures and grouped backtests. Compare how well each factor predicts future returns, examine its consistency over time, and combine useful factors with equal or performance-based weights.
Analyze price swings to detect Elliott Wave structures: five waves following a trend and three waves correcting it. Check wave rules and Fibonacci ratios, then generate signals for completed advances or pullbacks using a pandas implementation.
Track when assets begin moving together, assess the resulting loss of diversification, and examine which assets moved first during a crisis. Rank changes in asset relationships and report uncertainty explicitly for risk monitoring and retrospective analysis.
Use investor psychology to examine trading signals and risk controls, especially in China A-shares. The skill provides sentiment measures, checklists for biased decisions, and frameworks for assessing momentum, which follows trends, and reversal strategies.
Generate trading signals using Ichimoku Kinko Hyo, a five-line chart framework. Combine conversion-line and base-line crossovers with price position and cloud direction to classify conditions as long, short, or stand aside using pandas.
Recognize classic candlestick patterns using pandas, a Python library for tabular data. Combine bullish and bearish pattern scores into long, short, or stand-aside signals, with adjustable thresholds for candle bodies and shadows.
Analyze corporate events in China's A-share market, including mergers, major shareholder transactions, equity incentives, and financing. Calculate acquisition price gaps, assess dilution and delisting risks, and organize event timing, signals, and risks into a report.
Analyze how assets move together and test cointegration, a long-term equilibrium relationship between prices. Find related assets, group similar holdings, examine changing correlations, and estimate hedge ratios and reversion times for pairs-trading research.
Retrieve minute-level price data for stocks and cryptocurrencies, calculate average prices and volume patterns, and test intraday trading strategies. Configure the candle interval and trading costs to examine results using historical market data.
Monitor requests to an AI prediction API for signs of model copying or training-data exposure. Test an authorized model with simulated attacks, measure the risk, and evaluate defenses such as request limits and reduced prediction detail.
Analyze DNS logs to find signs of hidden data transfers. Use query length, character randomness, traffic volume, and response sizes to identify suspicious domains and support monitoring rules with Python, Suricata, and Splunk examples.
Examine recorded calls and voicemails for signs of AI-generated speech. Extract acoustic features, classify samples with machine learning, and prepare reports with confidence scores and sound visualizations to support voice impersonation investigations.
Examine Zeek connection logs for regular callbacks that may indicate communication with an attacker’s control server. Use ZAT and Pandas to group connections, measure timing variation, and identify source and destination pairs for further investigation.
Build normal traffic profiles for industrial control networks and identify unusual connections, polling intervals, and protocol operations. Use machine learning and process records to investigate deviations and produce anomaly reports with severity levels.
Analyze existing user permissions to propose roles for role-based access control, which assigns permissions by job role. Compare candidate role sets, identify overlap and excess access, and validate definitions against business responsibilities.
Create animated GIFs for Slack emoji and messages using drawn shapes or uploaded images. Add motion such as bouncing, rotation, and fading, adjust dimensions and colors, and validate the finished file against Slack requirements.
Build similarity search with FAISS to find nearby matches in large collections of numeric vectors. The skill guides index selection, memory reduction, GPU use, and saving indexes while balancing search speed and accuracy.
Check single-cell RNA-seq data quality, filter low-quality cells using median absolute deviation, a measure of spread, and compare plots before and after filtering. Outputs include filtered data and the original dataset with quality annotations.
Analyze users grouped by signup period or another shared characteristic to compare retention and feature adoption over time. Produce charts, highlight unusual changes, and recommend follow-up research or experiments to investigate the patterns.
Helps explore datasets, clean missing or inconsistent values, and explain patterns through statistics and charts. Uses Python and SQL to compare groups, examine relationships, and present findings in plain language with documented analysis steps.
Create animated GIFs for Slack messages and custom emoji from a description. Combine motion such as bouncing, spinning, and shaking, then check dimensions and file size and adjust frames or colors to fit the intended use.