Anthropic Skills

多次元フィールドデータの描画API実装、およびプロット軸のスケール・目盛・表示範囲の診断・修正を行う

TanStack Table で勤怠一覧/勤務表を作る。列定義、ソート/フィルタ、ページング、集計行、アクセシビリティ、CSV出力の型を固定する。キーワード: TanStack Table, table, columns, sorting, filtering, CSV

Create a new Ethereum data investigation page in the notebooks repo. Use when the user wants to add a new investigation, analysis, or research page that queries Xatu/ClickHouse data and visualizes findings with charts.

Data analysis and reporting patterns for LogiAccounting Pro. Use when generating reports, analyzing trends, or creating visualizations.

|

Provides Systematic library evaluation with emphasis on readability, actionable insights, and informed decision-making. Use when asked "should we use X", "is there a better library", during security audits, or making migration decisions. Produces concise, scannable reports that drive adoption decisions - not walls of text.

|

|

A/B testing framework for safe experimentation with statistical validation

Data visualization and inspection skill. Use for (1) creating matplotlib/seaborn plots from data files or marimo notebooks, or (2) inspecting DataFrames by showing first N rows, column names, and dtypes. For plots, provide chart type, data context, and styling. For inspection, ask to "show" or "display" the data.

This skill should be used when the user asks to "track metrics", "calculate ARR", "what metrics should I track", "benchmark my metrics", "understand churn", "calculate LTV", "what is burn multiple", "GMV calculation", "marketplace metrics", or mentions specific metrics like ARR, MRR, NRR, churn, CAC, LTV, burn rate, runway, GMV, take rate, or cohort analysis.

MongoDB database exploration for understanding game data, debugging, and investigation. Auto-applies when discussing database structure or debugging data issues.

Data analysis, scientific computing, visualization with pandas, numpy, matplotlib

Create and embed Mermaid diagrams in Markdown files for visualizing documentation, features, architecture, workflows, and processes. Use when asked to "add a diagram", "create a flowchart", "visualize the workflow", "show the architecture", or when documentation needs visual enhancement. Supports flowcharts, sequence diagrams, class diagrams, state diagrams, ER diagrams, Gantt charts, pie charts, and more.

ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.

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

Create, edit, and analyze Excel spreadsheets with formulas, formatting, data analysis, and visualization. Use when working with .xlsx files for professional documents, financial models, data analysis, or reporting.

Integrate Databuddy analytics into applications using the SDK or REST API. Use when implementing analytics tracking, feature flags, custom events, Web Vitals, error tracking, LLM observability, or querying analytics data programmatically.

Audit pilot data, models, and workflows for bias and inclusivity issues. Use when evaluating fairness across demographic groups, identifying algorithmic biases, and recommending mitigation strategies to ensure equitable outcomes.

Extract patterns, insights, and knowledge from text content. Use when asked to digest, extract, summarize, analyze patterns in code, conversations, documents, or decisions. Stores extracted knowledge for future retrieval.

Detect and alert on emerging anomalies and risk flags from pilot metrics and data streams. Use when monitoring live data, threshold breaches, or statistical outliers to trigger governance reviews and corrective actions.

Design and generate visual dashboards to present pilot insights and trends. Use when creating executive summaries, interactive or static dashboard layouts, and report visualizations for stakeholder review.

Use the Databuddy REST API for programmatic access to analytics data. Use when querying analytics data, building custom dashboards, sending events via API, or integrating analytics into backend services.

Define measurable success metrics, KPIs, and acceptance criteria aligned to pilot objectives. Use when establishing evaluation frameworks, go/no‑go thresholds, or performance benchmarks based on pilot goals and baseline data.

>

Run accuracy evaluation/tuning for RQ-SCAN and generate reports.

Perform in-depth architectural analysis of codebases through iterative dialog and visual diagrams. Use when users want to understand their software architecture, explore design patterns and anti-patterns, evaluate potential architectural changes, or gain deep insights into code structure and relationships. Particularly valuable for onboarding to unfamiliar codebases, assessing technical debt, planning refactoring efforts, or understanding how components interact across system boundaries.

Explore and analyze pilot data sets to uncover patterns, anomalies, and initial insights. Use when performing ad-hoc data investigations, validating data quality, or preparing exploratory visualizations for hypothesis generation.

Expected data format (csv, json, parquet)

Map pilot outcomes to strategic benefits, ROI estimates, and KPI alignments to demonstrate value realization. Use when quantifying business impact, calculating return on investment, and aligning pilot results with organizational goals.

Design data visualisations for B2B dashboards displaying buying signals, composite scores, trends, and alerts. Apply when building charts, sparklines, score breakdowns, heatmaps, or any interface requiring rapid comprehension of multivariate data. Covers the 2-second rule, pre-attentive processing, visualisation selection by data type, trend surge detection, score explainability, and mobile-responsive patterns.

Specialist in generating comprehensive Markdown reports of the knowledge model.

Analyze plans and improve query performance.

Create dashboards with KPIs and real-time metrics.

Document ER diagrams and table metadata.

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

Combine outputs from multiple instances into unified view, preserving diversity

Generate comprehensive network infrastructure reports including health status, performance analysis, security audits, and capacity planning recommendations.

Cross-domain integration using diffusion dynamics. Operationalizes intellectual chaos methodology - deliberately combining diverse materials to surface unexpected patterns. Use when given multiple documents from different fields, asked to find connections between disparate concepts, synthesizing across disciplines, or when user uploads varied materials expecting emergent insight.

Generates PowerPoint presentations from templates with consistent styling across tables, charts, and Mermaid diagrams. Use when creating PPTX files, working with template-based presentations, or applying unified styling from style.yaml. Supports Python, R, and native PowerPoint shapes.