Anthropic Skills

|

Transform documents, reports, and data into professional McKinsey-style HTML presentations with intelligent chart selection and interactive navigation. Use when: (1) Creating presentations from documents/reports, (2) Converting markdown/text to slides, (3) Generating HTML slides, (4) Applying McKinsey/BCG design, (5) Data visualization in presentations. Keywords: presentation, slides, HTML, McKinsey style, charts, visualization, 幻灯片, 演示文稿

Formats structured data using TOON v2.0 to minimize tokens while preserving readability. Use when outputs include tables, logs, events, or repeated records and token budgets matter. Triggers include "format table", "structured data", "TOON", "minimize tokens", or "large list".

Master SQL query optimization, indexing strategies, and EXPLAIN analysis. Use when debugging slow queries, designing database schemas, or optimizing application performance.

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

AISC Design Guide 1 expert for steel column base plate and anchor rod connection design. Use when users ask about base connections, base plates, anchor rods, column-to-foundation connections, concrete bearing strength, eccentricity, small vs large moment classification, shear transfer, or AISC Design Guide 1. Supports both LRFD and ASD design methods with 15 worked examples covering axial, moment, shear, and biaxial loading.

Research technical solutions, analyze architectures, gather requirements thoroughly. Use for technology evaluation, best practices research, solution design, scalability/security/maintainability analysis.

Build financial models for startups, business cases, revenue forecasting, unit economics, and investment analysis. Includes templates and formulas.

Data analysis with end-state first protocol. Clarify decisions before diving into data. Python/pandas focused.

Database (PostgreSQL) SQL best practices for clean, performant, and maintainable queries. Use when writing or reviewing SQL, schema changes, or database-related guidance.

Generates data-driven reports about the project. Use for initial project reports or session summaries.

A skill to search historical data for price, volume, or event patterns similar to the current context.

Patterns for analyzing Jira ticket quality and identifying improvement opportunities.

SQLite-based metrics storage for SEO time-series data

Best practices for creating comprehensive Jupyter notebook data analyses with statistical rigor, outlier handling, and publication-quality visualizations

Create professional software diagrams using Mermaid's text-based syntax.

Use when evaluating data for AI projects. Use before project commitment. Produces data quality assessment, gap analysis, and remediation recommendations.

Use when defining product analytics requirements. Use after product live. Produces KPI definitions, dashboard specifications, alert thresholds, and measurement methodology.

Use when balancing AI investments across initiatives. Use during planning cycles. Produces portfolio analysis, resource allocation, and investment recommendations.

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

Perform paired t-tests and repeated-measures ANOVA for biomechanical data analysis with formatted Excel output. Use when analyzing EMG, force, kinematics data with statistical comparisons, creating auto-updating Excel reports, or applying Excel formula automation. Always outputs publication-ready Excel files.

Write data analysis reports where all quantitative information appears in programmatically-generated plots, never in hand-written text tables. Prevents AI from fabricating numbers by ensuring all values come from computed data rendered visually. Use when creating analysis reports, generating summary statistics, or presenting correlation/comparison results.

Guidelines for managing TimescaleDB hypertables, continuous aggregates, and migrations. Use this when creating new tables or modifying time-series data schemas.

Visualize biomechanics signal data including EMG, Forceplate (Fx/Fy/Fz), and CoP/CoM trajectories. Use when creating grid plots, onset timing markers, window highlights, TKEO pipeline visualizations, or trajectory scatter plots for biomechanics research. Triggers on EMG plot, forceplate visualization, CoP trajectory, CoM trajectory, TKEO onset, signal grid, biomechanics chart.

Evaluates machine learning models for demographic bias using the fairlearn library. Use this skill immediately after training any predictive model.

Inspect Excel file structure (sheets, data types, VBA code) to help AI understand the workbook before writing code. Use when you need to understand an Excel file's schema, analyze data structure, or extract VBA code for modification.

Extract actionable insights from user research, transcripts, and feedback with strategic alignment assessment. Use when analyzing any customer conversation, interview, or feedback document.

Optimize SQL queries for Databricks analytics with automatic data profiling, partition analysis, and performance optimization. Use when users request data analysis, SQL queries, or analytics tasks that involve large tables. The skill ensures queries are optimized by checking table metadata, partition columns, data size, and applying best practices before executing queries. Essential for interactive analytics requiring good performance on large datasets.

This skill should be used when the user wants to visualize data. It intelligently selects the most suitable chart type from 26 available options, extracts parameters based on detailed specifications, and generates a chart image using a Python script.

Analyze preprocessed data for investigative journalism with full transparency. Use when a journalist has clean, preprocessed data ready for analysis and needs to identify patterns, anomalies, relationships, or statistical findings that support a story. Triggers include requests to analyze data, find patterns, identify outliers, cross-reference records, calculate statistics, or answer specific investigative questions. Complements the structured-data-preprocessing skill. Emphasizes simple, legible

Spawn data-analyst agents to answer queries about the P&L dataset.

Create and fill dynamic layout reports via API. Use when building structured reports with layouts containing grids, flex containers, and content slots. Supports charts (Chart.js), diagrams (Mermaid), infographics (AntV), markdown, tables, and code blocks. Use this skill when asked to create reports, dashboards, or documents with visual layouts.

This skill should be used when the user asks to "create dataset", "add trace to dataset", "curate regression tests", "build test set from traces", "list datasets", "show dataset items", or needs to manage Langfuse datasets for experiment validation and regression testing.

Unified math capabilities - computation, solving, and explanation. I route to the right tool.

Computational geometry with Shapely - create geometries, boolean operations, measurements, predicates

Use when the user asks to analyze score trends, regressions, distributions, or compare quality metrics across releases, environments, or trace names in Langfuse.

This skill should be used when the user asks to "set up tracking", "what should I track", "map behaviors to goals", "identify leading indicators", "which habits matter", "connect actions to outcomes", or needs to identify which daily behaviors produce their defined targets.

This skill should be used when the user asks to "review my week", "analyze my data", "what's working", "check progress", "weekly review", "monthly review", "look at my metrics", "show my trends", or wants to extract signal from tracked data and close the feedback loop.

This skill should be used when generating progress visualizations, charts, graphs, sparklines, progress bars, or dashboards in the terminal. Provides patterns for ASCII-based data visualization in Claude Code responses.

This skill should be used when the user asks to "analyze scores", "show score trends", "detect score regressions", "compare scores across releases", "get score statistics", or needs to understand score distributions and quality metrics over time.