Data Science

Executes OpenAI Codex CLI for code analysis, refactoring, and automated editing. Activates when users mention codex commands, code review requests, or automated code transformations requiring advanced reasoning models.

Provides reverse engineering analysis support including function identification, data structure analysis, and behavior understanding. Use when analyzing unknown binaries, understanding program structure, or investigating binary behavior.

分析结构化数据并生成统计报告和可视化建议

AI-powered content drafting, quality analysis, and optimization for presentation slides. Generates titles, bullets, speaker notes, and graphics descriptions.

Comprehensive Ruby and Rails code review using Sandi Metz rules and SOLID principles. Automatically runs rubycritic and simplecov, analyzes changed files in current branch vs base branch, identifies OOP violations, Rails anti-patterns, security issues, and test coverage gaps. Outputs REVIEW.md with VSCode-compatible file links. Use when reviewing Ruby/Rails code, conducting code reviews, checking for design issues, or when user mentions code review, pull request review, or code quality analysis.

Convert docstrings to NumPy/Sphinx style with proper Parameters, Returns, and Examples sections. This skill should be used when improving documentation quality across Python modules.

Optimize educational content specifically for Google NotebookLM processing, book generation, quiz creation, and flashcard development with enhanced metadata, cross-references, and AI-friendly formatting.

Connect Supabase databases to Claude Desktop artifacts with read-only queries and live data visualization.

This skill should be used when performing exhaustive code reviews using multi-agent analysis, ultra-thinking, and Git worktrees for deep local inspection. It applies to PR reviews, branch comparisons, and comprehensive code quality assessments.

This skill should be used when the user asks to "run multiple agents", "parallel review", "comprehensive analysis", "full review", "multi-agent workflow", or needs to coordinate multiple specialized agents working simultaneously. Provides patterns for launching agents in parallel and synthesizing results.

Create clear, well-structured mermaid diagrams for documentation and visualization.

Recharts for React data visualization. Covers line, bar, area, pie charts with responsive containers and customization. Triggers on recharts, chart, LineChart, BarChart.

Comprehensive PostgreSQL configuration and usage analysis for Rails applications. Use when Claude Code needs to analyze a Rails codebase for database performance issues, optimization opportunities, or best practice violations. Detects N+1 queries, missing indexes, suboptimal database configurations, anti-patterns, and provides actionable recommendations. Ideal for performance audits, optimization tasks, or when users ask to "analyze the database", "check for N+1 queries", "optimize PostgreSQL", "review database performance", or "suggest database improvements".

Extract and analyze security controls from OSCAL catalogs, profiles, and SSPs. Use this skill to get detailed information about control hierarchies, statements, parameters, and implementation status for compliance analysis.

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. Provides intelligent header detection and semantic column mapping for robust data import.

Analyze training patterns, performance, and physiological data using advanced computational models.AUTO-ACTIVATES when user asks about:- Training status/progress ("How am I doing?", "How's my training?")- Load/overtraining ("Am I overtraining?", "Is my load too high?")- Performance questions ("Why did I fade?", "What's limiting me?")- Specific run analysis ("Why was my HR high?", "What happened yesterday?")- Race readiness ("Am I ready?", "Will I make my goal?")- Physiological zones ("What are my zones?", "What's my threshold?")- Recovery/freshness ("Should I run today?", "Am I recovered?")- Patterns/causation ("What's causing...", "What predicts my best runs?")PROACTIVELY WARNS when detecting:- ACWR > 1.3 (load spike)- TSB < -25 (fatigue accumulation)- Correlation shifts (relationship changes)- Form breakpoints earlier than usual- Recovery decline between intervals

Production monitoring, observability, SLO/SLI management, and incident response.Trigger terms: monitoring, observability, SRE, site reliability, alerting, incident response,SLO, SLI, error budget, Prometheus, Grafana, Datadog, New Relic, ELK stack, logs, metrics,traces, on-call, production monitoring, health checks, uptime, availability, dashboards,post-mortem, incident management, runbook.Completes SDD Stage 8 (Monitoring) with comprehensive production observability:- SLI/SLO definitions and tracking- Monitoring stack setup (Prometheus, Grafana, ELK, Datadog, etc.)- Alert rules and notification channels- Incident response runbooks- Observability dashboards (logs, metrics, traces)- Post-mortem templates and analysis- Health check endpoints- Error budget trackingUse when: user needs production monitoring, observability platform, alerting, SLOs,incident response, or post-deployment health tracking.

Interactive data exploration and visualization skill. Use when users ask to visualize data, analyze datasets, create charts, or explore data files (CSV, Excel, Parquet, JSON). This skill guides through data exploration, proposes visualization strategies based on data characteristics, creates interactive Plotly charts in marimo notebooks, and generates analytical conclusions.

Evaluate LLM benchmark outputs against quality rubrics for STPA-Sec analysis. Use when comparing model outputs, assessing component extraction quality, UCA analysis correctness, or scenario generation completeness.

Integrate RubyCritic to analyze Ruby code quality and maintain high standards throughout development. Use when working on Ruby projects to check code smells, complexity, and duplication. Triggers include creating/editing Ruby files, refactoring code, reviewing code quality, or when user requests code analysis or quality checks.