數據科學

Analytics and data analysis workflow skill

Systematically discover edge cases through boundary analysis and input space exploration. Use when: (1) asked to find edge cases or validate correctness, (2) correctness claims rest on happy-path testing without boundary exploration, (3) code accepts inputs with implicit assumptions about range, format, or type that have not been verified, (4) code is about to ship or correctness is claimed without having mapped the boundary surface.

Consciousness simulation framework with Kuramoto oscillators, APL operators, and K-formation dynamics. Use for physics simulations, phase transitions, coherence analysis, and cloud training via GitHub Actions. Requires numpy and requests packages.

Transform CSV/Excel data into narrative reports with auto-generated insights, visualizations, and PDF export. Auto-detects patterns and creates plain-English summaries.

Analyzes long straddle volatility plays with ATM call and put at same strike. Requires numpy>=1.24.0, pandas>=2.0.0, matplotlib>=3.7.0, scipy>=1.10.0. Use when expecting large price movement in either direction, analyzing earnings plays, evaluating volatility opportunities, or assessing binary event outcomes on high IV stocks.

This skill should be used when writing test cases, fixing bugs, analyzing code for potential issues, or improving test coverage for JavaScript/TypeScript applications. Use this for unit tests, integration tests, end-to-end tests, debugging runtime errors, logic bugs, performance issues, security vulnerabilities, and systematic code analysis.

Perform comprehensive data analysis, statistical modeling, and data visualization by writing and executing self-contained Python scripts. Use when you need to analyze datasets, perform statistical tests, create visualizations, or build predictive models with reproducible, code-based workflows.

Deep code intelligence via Narsil MCP providing 76 tools for security scanning (OWASP, CWE, taint analysis), call graph analysis (CFG, DFG, callers/callees), structural queries (symbols, definitions, references), and supply chain security (SBOM, license compliance). Accessed via Code Mode for token efficiency.

Copilot agent that assists with comprehensive code review focusing on code quality, SOLID principles, security, performance, and best practices Trigger terms: code review, review code, code quality, best practices, SOLID principles, code smells, refactoring suggestions, code analysis, static analysis Use when: User requests involve code reviewer tasks.

This skill should be used when the user asks to "work with polars", "create a dataframe", "use lazy evaluation", "migrate from pandas", "optimize data pipelines", "read parquet files", "group by operations", or needs guidance on Polars DataFrame operations, expression API, performance optimization, or data transformation workflows.

Autonomous AI-powered pull request reviewer with multi-agent analysis and comprehensive feedback

Apply Paul Graham's principles when exploring ideas, evaluating opportunities, building products, or making important decisions. Use this skill when brainstorming, validating ideas, planning ventures, thinking through problems, or needing a framework for clear thinking. Triggers include "evaluate this idea", "should I pursue this", "help me think through", "is this worth doing", "startup idea", "opportunity analysis", or any creative/strategic thinking task.

Python and R programming for data analysis, automation, and reproducible analytics

Processes CSV files and pandas DataFrames. Use when working with CSV files, tabular data, spreadsheets, or when the user asks to query, analyze, or manipulate structured data.

Copilot agent that assists with bug investigation, root cause analysis, and fix generation for efficient debugging and issue resolution Trigger terms: bug fix, debug, troubleshoot, root cause analysis, error investigation, fix bug, resolve issue, error analysis, stack trace Use when: User requests involve bug hunter tasks.

Conduct systematic trade study analyses using the DAU 9-Step Trade Study Process. Guides engineers through problem definition, root cause analysis (5 Whys, Fishbone), data collection from alternatives and datasheets, normalization calculations, weighted scoring, sensitivity analysis, and professional report generation with visualizations and decision matrices. Use when evaluating alternatives, comparing solutions, conducting trade-offs, or making engineering decisions.

Systematic data validation, error detection, cross-source reconciliation, and query correctness checking for analytical work. Use when validating Snowflake queries, catching calculation errors, reconciling metrics across different data sources, checking for null values, ensuring date range validity, detecting statistical anomalies, validating metric calculations (median vs mean, rate normalization), checking aggregation grain (per-record vs per-entity), validating contribution analysis for non-additive metrics, or validating consistency across analysis sections. Essential when reviewing analysis before publication, debugging unexpected results, or ensuring data quality in reports. Triggers include "validate this query", "check for errors", "why don't these numbers match", "should I use median or mean", "why don't contributions sum to 100%", "reconcile these metrics", "verify data quality", or any request to catch potential issues in data or calculations.

Database query analysis, optimization, and best practices

Price fixed income securities using present value, yield-to-maturity, and market conventions. Handles treasuries, corporates, municipals with various coupon frequencies. Requires numpy>=1.24.0, pandas>=2.0.0, scipy>=1.10.0. Use when valuing bonds, calculating accrued interest, or analyzing price sensitivity to yield changes.

Comprehensive code quality validation using Solargraph, Sorbet, and Rubocop for A+ Rails code. Trigger keywords: quality gates, validation, solargraph, sorbet, rubocop, type checking, linting, code quality, static analysis