數據科學

Diagnose and debug issues in the vehicle insurance data analysis platform. Use when user encounters errors, data not refreshing, filters not working, charts not displaying, API failures, or performance issues. Provides quick diagnostic checklists and proven troubleshooting steps specific to this Vue 3 + Flask + Pandas stack.

Generates comprehensive interview preparation materials including STAR stories, talking points, mock questions, and company research. Receives job analysis, career history, and portfolio data. Returns structured interview prep content. Data-agnostic - no file I/O.

Python backend developer for FastAPI, Django, Flask APIs with SQLAlchemy, Django ORM, Pydantic validation. Implements REST APIs, async operations, database integration, authentication, data processing with pandas/numpy, machine learning integration, background tasks with Celery, API documentation with OpenAPI/Swagger. Activates for Python, Python backend, FastAPI, Django, Flask, SQLAlchemy, Django ORM, Pydantic, async Python, asyncio, uvicorn, REST API Python, authentication Python, pandas, numpy, data processing, machine learning, ML API, Celery, Redis Python, PostgreSQL Python, MongoDB Python, type hints, Python typing.

PolicyEngine vectorization patterns - NumPy operations, where/select usage, avoiding scalar logic with arrays

Comprehensive toolkit for analyzing and anticipating Nvidia and semiconductor supply chain stock movements. Use when users need to (1) analyze Nvidia ecosystem dependencies and correlations, (2) identify trading opportunities across the supply chain, (3) track earnings catalysts and events, (4) understand bottlenecks and risk factors, (5) develop supply chain investment strategies, or (6) monitor technical indicators and momentum across semiconductor names. Provides real-time data fetching, technical analysis, fundamental relationships mapping, and predictive signals based on supply chain dynamics.

Enhanced WasteWise Complete Analysis with comprehensive validation framework. Validates all requirements before output including contract tab generation, clause extraction, optimization criteria, formula accuracy, and data completeness. Produces detailed validation report showing which checks passed/failed. Use when rigorous quality control is needed for waste management analysis.

Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks

Use this skill when the user asks about Rust module dependencies, dependency graphs,architecture visualization, cycle detection, DAG analysis, or module structure. Activatewhen you see phrases like "show module structure", "dependency graph", "visualizearchitecture", "check for circular dependencies", or "Mermaid diagram of modules".

Use this skill for requests to retrieve hydrology basins in the USA as a GeoDataFrame in GeoPandas. Note that this skill is able to fetch all basins intersecting some states directly.

Plausible Analytics API for querying website statistics and managing sites. Use this skill to get visitor counts, pageviews, traffic sources, and manage analytics sites.

Bayesian meta-analysis models including fixed effects, random effects, and network meta-analysis with Stan and JAGS implementations.

Generate comprehensive tests for architectural layers with coverage-first analysis.Use when testing specific layers (core, domain, application, infrastructure, boundary).Reads testing strategy from playbook or uses interactive template selection.

Generates professional technical reports from performance analysis data. Creates investor and client-ready documents with executive summaries, visualizations, and actionable recommendations.

Generate DuckDB SQL queries. Use when user asks about DuckDB queries, data analysis, exploring .ddb database files, CSV files, Parquet files, wants help editing/improving SQL, asks to use the duckdb skill, references duckdb assets, or wants to initialize/setup duckdb analysis.

Guide conversations through dynamic shifts between zoom levels (scale) and connecting/exploring (intent) to unlock creative breakthroughs and prevent rigid thinking. Use when the user is stuck or needs to develop an idea or when there is a sense of too much repetition or dispersion. Takes the user through several stages of thinking — from idea genesis, to development, to questioning, to disruptive thinking. Identifies structural gaps between idea clusters as spaces for innovation. Tracks temporal dwelling patterns and manages cognitive energy expended. Uses playfulness for difficult transitions from chaos to clarity. Maximum creative potential lives in gaps and dissipative states. Apply for complex analysis, brainstorming, being stuck, breakthroughs, decision paralysis, group facilitation, breaking repetitive patterns, or when grammatical patterns reveal cognitive issues.

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas

Audit an Anthropic Cookbook notebook based on a rubric. Use whenever a notebook review or audit is requested.

Generate production-quality Python code for robot simulations that run in Pyodide (browser).Supports simplified physics simulations using NumPy, Matplotlib, and basic physics calculations.Creates educational code for teaching robot kinematics, dynamics, and control without requiringheavy simulation engines (PyBullet/MuJoCo/Gazebo are not Pyodide-compatible).Focuses on 2D/3D visualizations, kinematic chains, and simplified dynamics for educational purposes.

Migrate Python modules from SDR_stochastic research code to vrp-toolkit architecture. Use when migrating files from the old codebase structure to the new three-layer architecture (Problem/Algorithm/Data layers), refactoring paper-specific code into generic implementations, or converting research notebooks into educational tutorials.

This skill should be used when the user asks to "review the analysis", "check methodology", "validate results", or as Phase 4 of the /ds workflow. Reviews methodology, data quality, and statistical validity.