數據科學

Research GitHub, GitLab, and Bitbucket repositories using DeepWiki MCP server. Use when exploring unfamiliar codebases, understanding project architecture, or asking questions about how a specific open-source project works. Provides AI-powered repo analysis and RAG-based Q&A about source code. NOT for fetching library API docs (use fetching-library-docs instead) or local files.

Systematic project review framework with issue analysis, task breakdown, conflict detection, and resolution. Use when reviewing project state, identifying problems, creating actionable issues, and resolving conflicts to maintain system health.

Master SQL for data analysis with complex queries, joins, aggregations, window functions, and query optimization.

Comprehensive performance specialist covering analysis, optimization, load testing, and framework-specific performance. Use when identifying bottlenecks, optimizing code, conducting load tests, analyzing Core Web Vitals, fixing memory leaks, or improving application performance across all layers (application, database, frontend). Includes React-specific optimization patterns.

Identify security vulnerabilities, performance issues, and code quality problems through systematic analysis adapted to project's technology stack and domain. Use when reviewing code, assessing security, auditing. Triggers: 'security', 'vulnerability', 'audit', 'review', 'OWASP', 'injection', 'authentication', 'authorization', 'XSS', 'CSRF', 'secure', '보안', '취약점', '검토', '리뷰', '감사', '인증', '인가', '보안검사'.

Enhanced dependency analyzer with comprehensive markdown reporting and actionable recommendations. Use when you need to optimize frontend project dependencies, detect security vulnerabilities, identify unused packages, find duplicate functionality, analyze dependency impact, generate cleanup scripts, or produce detailed Markdown reports. Supports JavaScript, TypeScript, Vue, React, Angular, and modern build tools with parallel processing and incremental analysis capabilities.

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

Comprehensive debugging specialist for errors, test failures, log analysis, and system problems. Use when encountering issues, analyzing error logs, investigating system anomalies, debugging production issues, analyzing stack traces, or identifying root causes. Combines general debugging workflows with error pattern detection and log analysis.

Systematic CSV import process - discover structure, design schema, standardize formats, import to database, detect quality issues (component skill for DataPeeker analysis sessions)

Write, run, and analyze component tests using Vitest and React Testing Library with coverage analysis and accessibility validation

Deep performance analysis for Rails 8 applications focusing on N+1 queries, database indexing, and caching strategies. Use when investigating slow endpoints, detecting N+1 queries, optimizing database indexes, or reviewing caching before deployment.

Analyzes Stellaris save data by creating and running python code using a MCP tool providing a sandboxed environment. The Python code retrieves data from Stellaris saves by accessing GraphQL API.

Strategic thinking framework integrating First Principles Analysis, Stanford Design Thinking, and MIT Systems Engineering for deeper problem-solving and decision-making

Research legal technology topics for blog posts on alt-counsel (Ang Hou Fu's blog). Use when the user asks to research topics, find sources, fact-check claims, gather statistics, or find expert opinions for blog content. Prioritizes Singapore/ASEAN perspectives and flags US/EU-centric information. Outputs research findings to research.md in the post folder with proper citations.

Detect framework and tooling issues then suggest creating REPAIR- tasks to address them systematically - ANALYSIS-ONLY skill that identifies problems and proposes structured fixes

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

Response-Aware Development (RAD) - Systematic verification of code assumptions using multi-model AI analysis. Auto-activates on keywords assumption, verify assumptions, list assumptions, RAD, response-aware, assumption tags, critical assumptions, assumption verification. Routes to verification, listing, and testing workflows.

Expert speech-language pathologist specializing in AI-powered speech therapy, phoneme analysis, articulation visualization, voice disorders, fluency intervention, and assistive communication technology. Activate on 'speech therapy', 'articulation', 'phoneme analysis', 'voice disorder', 'fluency', 'stuttering', 'AAC', 'pronunciation', 'speech recognition', 'mellifluo.us'. NOT for general audio processing, music production, or voice acting coaching without clinical context.

Break complex problems into manageable components for systematic analysis. Use when: (1) explicit request to decompose, break down, or identify component parts of a system or problem, (2) problems feel overwhelming as single units due to interdependencies or unclear boundaries, (3) before planning work to identify what can proceed in parallel versus sequentially, (4) debugging multi-layered issues or explaining complex systems where natural boundaries would clarify understanding.

Evaluates market bubble risk through quantitative data-driven analysis using the revised Minsky/Kindleberger framework v2.1. Prioritizes objective metrics (Put/Call, VIX, margin debt, breadth, IPO data) over subjective impressions. Features strict qualitative adjustment criteria with confirmation bias prevention. Supports practical investment decisions with mandatory data collection and mechanical scoring. Use when user asks about bubble risk, valuation concerns, or profit-taking timing.