Technical Skills

LLM-friendly Excel operations via the `xl` CLI. Read cells, view ranges, search, evaluate formulas, export (CSV/JSON/PNG/PDF), style cells, modify rows/columns. Use when working with .xlsx files or spreadsheet data.

R-based econometric analysis for academic research. Use when writing R code for panel data, difference-in-differences, instrumental variables, spatial econometrics, or regression analysis. Covers data.table, fixest, sf, modelsummary, and publication-ready outputs.

A comprehensive skill to test, analyze, and fix the PropertyIQ graphs page.

Perform survival analysis on TCGA cancer data using cBioPortal API and lifelines. Use when user wants to analyze gene expression and survival outcomes, create Kaplan-Meier curves, run Cox proportional hazards models, or study specific genes (like TP53, KRAS, EGFR) in cancer cohorts (LUAD, LUSC, BRCA, etc.). Triggers on keywords like "TCGA", "survival analysis", "Kaplan-Meier", "hazard ratio", or cancer type abbreviations.

Access advanced SpreadJS functionality not covered by the standard API. Use when you need low-level spreadsheet operations like sparklines, slicers, cell buttons, advanced conditional formatting, outline groups, or any SpreadJS-specific features.

Summarizes weekly trends for 'AI Agent Tools', providing a Top 10 table with names, official links, core capabilities, and application scenarios, along with reusable research steps.

NetSuite data analysis for professional services organizations. Use when analyzing project profitability, resource utilization, billable hours, project margins, cost overruns, capacity planning, or resource allocation in NetSuite. Leverages NetSuite MCP tools for querying and analysis.

ClickHouse database patterns for high-performance analytics.

Automated 2-AI verification result documentation and export workflow. Triggers when user requests AI verification report export, documentation of findings, or saving cross-validation results. Use after completing Codex/Gemini analysis.

Use PROACTIVELY when users need guaranteed schema compliance or validated tool inputs from Anthropic's structured outputs feature. Expert advisor for choosing between JSON outputs (data extraction/formatting) and strict tool use (agentic workflows). Analyzes requirements, explains trade-offs, and delegates to specialized implementation skills. Not for simple text responses or unstructured outputs.

Query Developer Experience (DX) data via the DX Data MCP server PostgreSQL database. Use this skill when analyzing developer productivity metrics, team performance, PR/code review metrics, deployment frequency, incident data, AI tool adoption, survey responses, DORA metrics, or any engineering analytics. Triggers on questions about DX scores, team comparisons, cycle times, code quality, developer sentiment, AI coding assistant adoption, sprint velocity, or engineering KPIs.

Summarize code, documentation, or findings into a concise format. Use after exploration to distill key information.

Unified math capabilities - computation, solving, and explanation. I route to the right tool.

Transforming raw data into actionable insights through reporting, analytics, and visualization using BI tools like Tableau, Looker, Power BI, and Metabase to support data-driven decision making.

Running controlled experiments comparing two variants to determine which performs better for specific metrics, with statistical significance testing and data-driven decision making.

Tracking player behavior and game performance through metrics, event tracking, funnel analysis, retention metrics, and integration with analytics platforms for data-driven game development.

Custom metrics system, metric definitions, data ingestion, and aggregation. Use when working with metric tracking, data collection, or the metrics API.

Expert guide to the auto-generated GraphQL API (Queries, Mutations, Aggregations).

Guide for debugging X-Fidelity analysis issues. Use when troubleshooting analysis failures, rule evaluation problems, VSCode extension issues, or unexpected results.

Specialized AI assistant for DSPy development with deep knowledge of predictors, optimizers, adapters, and GEPA integration. Provides session management, codebase indexing, and command-based workflows.

MATLAB and GNU Octave numerical computing for matrix operations, data analysis, visualization, and scientific computing. Use when writing MATLAB/Octave scripts for linear algebra, signal processing, image processing, differential equations, optimization, statistics, or creating scientific visualizations. Also use when the user needs help with MATLAB syntax, functions, or wants to convert between MATLAB and Python code. Scripts can be executed with MATLAB or the open-source GNU Octave interpreter

Detection rules and grep patterns for database performance anti-patterns. Use when scanning codebase for N+1 queries, sequential queries, or connection pool issues.

코드 탐색, 코드 분석, 탐색, 코드 구조, 심볼 분석 - Use when exploring or analyzing code. Systematic code exploration workflow using Serena MCP tools for symbol navigation and reference tracking.

Generate and update HTML dashboards for LLM usage (Claude, Gemini, Kiro, VS code, Cline, etc). Use when the user wants to visualize their AI coding assistant usage statistics, view metrics in a web interface, or analyze historical trends.

Master Power BI development including DAX formulas, Power Query M, data modeling, and report optimization

BI tools, dashboards, and enterprise analytics platforms

Master statistical analysis with hypothesis testing, A/B testing, regression, and statistical methods for data-driven decisions.

Statistical analysis methods, hypothesis testing, and probability for data analytics

Specialized skill for analyzing personal health data, medical records, lab results, and supplement protocols. Use when working with health records, clinical data, lab values, or health optimization planning.

Expert assistant for Kumo's Query Module (src/features/query). Use when working with SQL Editor, Monaco editor integration, query execution, result grids, tabs management, AI features, or any query-related components. Provides architecture patterns, component APIs, hooks, utilities, and examples.

Analyzes ICU clinical data using the Common Longitudinal ICU data Format (CLIF) and clifpy Python library. Loads and filters CLIF tables (vitals, labs, medications, respiratory support, microbiology) by hospitalization_id and category columns. Computes clinical scores including SOFA, Charlson Comorbidity Index (CCI), and Elixhauser. Creates wide datasets and performs data transformations. Use when working with ICU data, CLIF format, clifpy, clinical scoring, ventilator data, sepsis research, or

Complete data analysis workflow including EDA, Table One, descriptive statistics, and correlation analysis using MCP AutoML tools. Use when analyzing CSV data, exploring datasets, generating summary statistics, or creating publication-ready Table One reports. Triggers: 分析資料, analyze data, EDA, 探索資料, 資料分析, describe data, 資料探索, 基本統計, summary statistics, Table One, 敘述統計, 看看資料, 快速分析, quick analysis, 分析一下, 幫我分析.

Advanced statistical analysis including survival analysis (Kaplan-Meier, Cox), propensity score matching (PSM), ROC curve analysis, and power/sample size calculations. Use when doing clinical research analysis, comparing treatment effects, evaluating diagnostic tests, or planning study sample sizes. Triggers: 統計分析, 存活分析, 傾向分數, ROC, power analysis, Kaplan-Meier, Cox, survival, PSM, 配對, AUC, sensitivity, specificity, 敏感度, 特異度, sample size, 樣本數.

Skill professionnel pour Claude Code permettant d'accéder, télécharger et analyser les données ouvertes françaises via data.gouv.fr. Inclut une librairie Python complète, des exemples de code, et une documentation détaillée des datasets les plus utilisés.

AGGRESSIVELY use TOON v2.0 format for biggish regular data (≥5 items, ≥60% uniform). Auto-applies to tables, logs, events, transactions, analytics, API responses, database results. Supports 3 array types (inline, tabular, expanded), 3 delimiters (comma, tab, pipe), key folding for nested objects. Triggers on structured data, arrays, repeated patterns. Use TOON by default when tokens matter - RAG pipelines, tool calls, agents, benchmarks. Keywords "data", "array", "list", "table", "log", "transac

Эксперт анализа распределений. Используй для statistical distributions, data analysis и hypothesis testing.

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.

Expert business analysis for B2B SaaS platforms. Activated for data analysis, requirements gathering, process optimization, business metrics calculation, ROI analysis, and business case development.

Complete MXQL (Metrics Query Language) toolkit for generating, analyzing, validating, and testing queries. Supports conversational query generation, automated validation, comprehensive analysis with optimization suggestions, and test query generation with sample data. Use this for all MXQL-related tasks including creating queries, debugging, optimization, and testing.

Expert in Apache Ray distributed computing. Use when converting Python code to Ray workloads, debugging Ray applications, optimizing Ray performance, or working with Ray Core, Ray Data, Ray Train, Ray Serve, or Ray Tune. Automatically fetches relevant documentation from Ray, HuggingFace, PyTorch, and other ML/distributed frameworks based on code context.