Data Science

Comprehensive AI ethics and responsible AI development specialist. Use PROACTIVELY for bias assessment, fairness evaluation, ethical AI implementation, community impact analysis, and regulatory compliance. Expert in AI safety, alignment, and equitable systems design. Scales from quick audits to full ethical impact assessments.

Senior Backend Code Reviewer with 12+ years Java experience. Use when reviewing Java/Spring code, checking code quality and style, identifying code smells and anti-patterns, verifying security practices, ensuring test coverage, or configuring static analysis tools (Checkstyle, SpotBugs, SonarQube).

专业数据可视化专家，精通现代图表库、仪表板设计和交互式数据展示。能够将复杂数据转化为直观、美观且富有洞察力的可视化作品。

Systematic fact-checking, source verification, and quality assurance for competitive research deliverables. This skill ONLY activates when explicitly requested - it does not auto-trigger. Use this skill when you explicitly ask to review competitive research, fact-check claims, verify sources, validate consistency, or assess quality of completed analysis documents. Example requests that activate this skill "review this competitive analysis", "fact-check these findings", "verify the sources", "quality check this report", "are these claims accurate", or "validate this analysis".

Process vehicle insurance Excel data using Pandas - file handling, data cleaning, merging, validation. Use when processing Excel/CSV files, handling data imports, implementing business rules (negative premiums, zero commissions), debugging data pipelines, or optimizing Pandas performance. Keywords: data_processor.py, Excel, CSV, Pandas, merge, deduplication, date normalization.

Universal functions (ufuncs) for vectorization, including reductions, in-place operations, and custom Python-function wrapping. Triggers: ufunc, vectorize, reduce, accumulate, frompyfunc, in-place.

Autonomous Freedom to Operate analysis agent. Identifies blocking patents, assesses infringement risk, and recommends mitigation strategies for product commercialization.

Bitcoin trading simulation with technical analysis (EMA/RSI/Bollinger), Monte Carlo projections, and Telegram alerts. Cambodian market focus (USD/KHR 4050).TRIGGERS: BTC backtesting, indicator calculations, Fear & Greed integration, crypto strategy development, CoinGecko/Alternative.me APIs, portfolio simulation, trailing stop optimization, Sharpe/drawdown metrics.ENTRY POINTS: btc_trader.py (365d backtest), btc_simulation.py (60d Monte Carlo), backtest_runner.py (advanced metrics).

⚡ PRIMARY TOOL for: 'how does X work', 'find implementation of', 'trace data flow', 'where is X defined', 'audit integrations', 'find all usages'. Uses claudemem v0.3.0 AST with callers/callees analysis. GREP/FIND/GLOB ARE FORBIDDEN.

Create a new underwriting agent (assets, credit, collateral) following established patterns. Use when implementing new agents, extending the system with new document analysis capabilities, or understanding how agents work.

Conducts user experience research and analysis to inform design decisions. Reviews first-party and third-party user data, analyzes industry trends from UX and visual design perspectives, and plans user research studies. Creates personas, customer segments, design principles, design roadmaps, and research discussion guides.

Implement PostHog analytics for PhotoVault with dual tracking (client + server). Use when working with event tracking, funnel analysis, user identification, TypeScript event schemas, ad-blocker-proof server-side tracking, or debugging missing analytics data. Includes PhotoVault event definitions and privacy defaults.

Statistical analysis strategies and data exploration techniques

Enhanced skill creation framework emphasizing philosophy-first design, anti-pattern prevention, and variation encouragement. Use when creating new skills, improving existing skills, analyzing skill quality, or when users request help designing effective skills that unlock capabilities rather than constraining them. Includes analysis tools and upgrade suggestions for existing skills.

Analyze llm-compact-logger test output and configure enhancements. Use when user shares debug-compact.json or debug-report.json files.

Preview and analyze git diffs with AI explanations. Use to understand changes before committing, get impact analysis, and compare branches or commits.

Automated analysis of patent claims for USPTO compliance with 35 USC 112(b) requirements - antecedent basis, definiteness, claim structure

Analyzes a codebase to generate comprehensive architectural documentation including technologies used, data flows, functional components, APIs, external dependencies, commit history analysis, and complexity hotspots.

Comprehensive ESLint agent for JavaScript/TypeScript code quality. Use when setting up ESLint, configuring linting rules, analyzing code for issues, fixing violations, or integrating ESLint into development workflows. Triggers on requests involving code quality, linting, static analysis, or ESLint configuration for JavaScript, TypeScript, React, or Node.js projects.

Analyzes pricing strategies, competitive pricing benchmarks, pricing models, value metrics, and willingness-to-pay to optimize pricing and positioning. Use when the user requests pricing analysis, competitive pricing comparison, pricing strategy, pricing model evaluation, or wants to optimize pricing decisions.