數據科學

Analyzes test directory structure, coverage gaps, and helper consolidation opportunities. Produces coverage reports and refactoring recommendations. Use when auditing test suites, planning test improvements, or identifying coverage gaps.

Assess error handling, isolation boundaries, and recovery mechanisms in agent frameworks. Use when (1) tracing error propagation paths, (2) evaluating sandboxing for code execution, (3) understanding retry and fallback mechanisms, (4) assessing production readiness, or (5) identifying failure modes and recovery patterns.

Generate and optimize SQL queries for data retrieval and analysis

Comprehensive guide to RDC's Snowflake data warehouse for marketing and consumer analytics. Use when querying clickstream data, lead attribution, marketing spend analysis, campaign performance, or revenue metrics. Triggers include queries about EFR, leads, spend, campaigns, clickstream, user journeys, SEM, app installs, paid social, or any Snowflake table exploration.

Comprehensive personal finance management system for analyzing transaction data, generating insights, creating visualizations, and providing actionable financial recommendations. Use when users need to analyze spending patterns, track budgets, visualize financial data, extract transactions from PDFs, calculate savings rates, identify spending trends, generate financial reports, or receive personalized budget recommendations. Triggers include requests like "analyze my finances", "track my spending", "create a financial report", "extract transactions from PDF", "visualize my budget", "where is my money going", "financial insights", "spending breakdown", or any finance-related analysis tasks.

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 tracking Use when: user needs production monitoring, observability platform, alerting, SLOs, incident response, or post-deployment health tracking.

Automatically activated when user asks about test quality, code coverage, test reliability, test maintainability, or wants to analyze their test suite. Provides framework-agnostic test quality analysis and improvement recommendations. Does NOT provide framework-specific patterns - use jest-testing or playwright-testing for those.

Creates blueprint-driven skills for infrastructure and deployment tasks. This skill should be used when creating new skills that require templates, patterns, or reference configurations (e.g., Dockerfiles, Helm charts, Kubernetes manifests, CI/CD pipelines). It enforces impact analysis before containerization, identifies environment requirements, network topology changes, and auth/CORS implications. Use this skill when building deployment-related skills or when containerizing applications.

R 4.4+ development specialist covering tidyverse, ggplot2, Shiny, and data science patterns. Use when developing data analysis pipelines, visualizations, or Shiny applications.

8-dimensional quantitative complexity analysis with domain detection. Analyzes specifications across structural, cognitive, coordination, temporal, technical, scale, uncertainty, dependency dimensions producing 0.0-1.0 scores. Detects domains (Frontend, Backend, Database, etc.) with percentages. Use when: analyzing specifications, starting projects, planning implementations, assessing complexity quantitatively.

Locates, lists, filters, and extracts structured data from Claude Code native session logs. Supports both single and multiple session analysis.

Organizes, cleans, and optimizes Jupyter notebooks - removes empty cells, adds structure, extracts functions, generates documentation. Use when user asks to "clean notebook", "organize jupyter", "refactor notebook", or "jupyter best practices".

Master data visualization principles including chart selection, dashboard design, color theory, and data storytelling

Data visualization design, tools, and storytelling for impactful analytics presentations

Helps query and analyze PostgreSQL databases. Use when the user asks about database queries, schema inspection, table relationships, or data analysis tasks. Can connect to local or remote PostgreSQL instances and execute safe, parameterized queries. Supports schema exploration, query optimization suggestions, and data export.

Use when user says "build concepts", "generate stories", "create stories", "brainstorm stories", "brainstorm features", "create stories for [node]", or asks for new story ideas. Complete story lifecycle - generates evidence-based stories from git commits and gap analysis, validates quality, vets for conflicts, and retries up to 10 times if duplicates detected. Polishes stories with hold_reason='polish' FIRST before generating new ones. Supports multi-node batching. Does NOT commit - leaves that to caller.

Use when managing Shannon CLI performance and costs - check cache statistics, clear stale entries, set budgets, understand automatic model selection and cost optimization

This skill should be used when the user reports "error", "bug", "problem", needs to "fix" something, mentions "debug", "failing", "broken", "issue", "not working", "crash", or any problem-solving scenario. Enforces systematic root cause identification using five whys methodology before attempting solutions.

Create production-grade web interfaces, dashboards, and data visualizations using Plantix brand guidelines. Use this skill when the user asks to build webpages, landing pages, dashboards, charts, or any visual interface. Generates polished, on-brand designs that follow Plantix's established visual identity and style principles.

Discovers and lists Claude Code session transcripts from .claude/logs/ for analysis. Use when the user wants to find available sessions, view session timelines, identify which sessions to analyze for workflow improvements, or understand session history. Triggers when user mentions "what sessions do I have", "analyze my workflow", "show my recent sessions", "find transcripts from [date]", or similar session discovery requests.