Data Science

データ分析・可視化・レポート作成。pandas、SQL、BigQuery、スプレッドシート操作、統計分析、グラフ作成。「データ分析」「SQL」「BigQuery」「pandas」「集計」「可視化」「レポート」に関する質問で使用。

Expert in creating database diagrams and visual representations. Use when generating ERDs, schema diagrams, or visualizing database relationships with Mermaid.js.

Use when investigating test suite issues, reducing CI/CD time, identifying brittle tests, finding test duplication, or analyzing test maintenance burden - reveals test code quality problems through git history analysis

Deep code review with web research to verify against latest ecosystem. Use when user says 'double check against latest', 'verify versions', 'check security', 'review against docs', or needs deep analysis beyond automatic quality hook.

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Codex 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

Technical analysis with TA-Lib - Moving averages, RSI, MACD, Bollinger Bands, Stochastic, ATR, candlestick patterns, and strategy signals using OpenAlgo market data

Comprehensive multi-AI code review system for Python, JavaScript, and TypeScript. Use when reviewing code for quality, security, performance, or best practices. Includes automated analysis scripts, language-specific patterns, and AI collaboration workflows for complex decisions.

Deep code review with web research to verify against latest ecosystem. Use when user says 'double check against latest', 'verify versions', 'check security', 'review against docs', or needs deep analysis beyond automatic quality hook.

Pentest Android and iOS mobile applications including APK analysis, dynamic analysis, SSL pinning bypass, root/jailbreak detection bypass, and mobile-specific vulnerabilities. Use when testing mobile app security or performing mobile pentesting.

Comprehensive architectural analysis and evaluation framework for system architecture assessment. Use for architecture pattern identification, SOLID principles evaluation, coupling/cohesion analysis, scalability assessment, performance characteristics, security architecture, data architecture, microservices vs monolith, technical debt quantification, and ADRs. Includes C4 model, 4+1 views, QAW, ATAM, architectural fitness functions, and visualization tools.

Deep research specialist for finding GitHub repos, tools, AI models, APIs, and real data sources. Searches repositories, compares libraries, researches latest AI benchmarks, discovers APIs, locates datasets, and performs competitive analysis to accelerate development.

Intelligent POC-to-production code extraction with architectural awareness. Analyzes dependencies, adapts patterns, makes extraction strategy decisions (copy/adapt/rewrite), maintains system coherence. Performs pre-extraction analysis, transformation reasoning, quality gate enforcement, evidence-based commits. Use when extracting code requires understanding architecture, adapting patterns, threading parameters, or maintaining coherence across modules. Triggers on understand and extract, analyze dependencies, adapt pattern, extraction strategy, architectural extraction, intelligent migration.

GitHub CLI (gh) tool for retrieving and analyzing GitHub data including pull requests, issues, code search, workflow runs, releases, and repository information. Use when needing to read GitHub PRs, view comments, check CI/CD status, search code across repos, analyze issues, inspect action logs, or query any GitHub data. Focuses on information retrieval and analysis rather than modifications.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions

Use when editing docs/index.html, creating charts with Plot, adding SQL cells, loading data with FileAttachment, or building visualizations. Triggers on any editing of docs/index.html, Observable notebooks, or front-end visualization work.

Generate comprehensive test suites including static analysis, unit tests, integration tests, E2E tests, and coverage reports. Triggers: TG, test, 測試, 寫測試, coverage, 覆蓋率, pytest, unittest, 驗證.

Analyze GitHub Issues and automatically infer appropriate labels from CCAGI's label system. Use when creating or triaging Issues, or when label inference is needed.

Performs quality control on single-cell RNA-seq data (.h5ad or .h5 files) using scVerse best practices with MAD-based filtering and comprehensive visualizations. Use when users request QC analysis, filtering low-quality cells, assessing data quality, or following scVerse/Scanpy best practices for single-cell analysis.

Advanced indexing techniques including slicing, fancy indexing, and boolean masks, along with memory implications of views vs. copies. Triggers: indexing, slicing, fancy indexing, boolean mask, np.where, np.ix_.

竞争情报数据分析方法，包括对比分析框架、图表类型选择、可视化规范和输出格式