Anthropic Skills

This skill should be used when the user asks about "data table", "tanstack table", "sortable table", "filterable table", "table pagination", "column sorting", "row selection", or mentions building data tables, grids, or TanStack Table integration with shadcn.

Work with DHIS2 health information systems - extract data, query metadata, run validations, manage users, or check system info. Use this skill for ANY DHIS2-related request. It routes to specialized sub-skills and provides centralized client setup and API patterns.

获取上证指数收盘情况及热门板块涨跌幅数据（东方财富 API）。

Run data quality checks and validation rules in DHIS2. Use for validation rules, violations, or data quality analysis. Routed via dhis2 skill for general DHIS2 requests.

全面的电子表格创建、编辑与分析工具，支持公式、格式设置、数据分析和可视化。当需要处理电子表格（如 .xlsx、.xlsm、.csv、.tsv 等）时使用，包括：(1) 创建包含公式和格式的新电子表格，(2) 读取或分析数据，(3) 在保留公式的情况下修改现有电子表格，(4) 在电子表格中进行数据分析和可视化，或 (5) 重新计算公式。

Help users synthesize and act on customer feedback. Use when someone is analyzing NPS responses, processing support tickets, reviewing user research, synthesizing feedback from multiple channels, or trying to identify patterns in customer input.

Get DHIS2 system information including version, database details, and server configuration. Use for version checks or server capabilities. Routed via dhis2 skill for general DHIS2 requests.

|

Extract data elements and data element groups from DHIS2. Use for data element metadata, groups, or category option combos. Routed via dhis2 skill for general DHIS2 requests.

Comprehensive descriptive analysis of tabular datasets with grouped statistics, entity extraction, and publication-ready summaries. Use when analyzing Excel/CSV datasets requiring: (1) Overall and grouped descriptive statistics, (2) Frequency distributions by categorical variables, (3) Entity extraction from text fields, (4) Temporal dynamics analysis, (5) CSV output tables with MD summary reports. Supports SDT scores, engagement metrics, or any continuous/categorical variables.

Extract organisation units and groups from DHIS2. Use for org unit hierarchy, metadata, levels, or groups. Routed via dhis2 skill for general DHIS2 requests.

Postgres performance optimization and best practices from Supabase. Use this skill when writing, reviewing, or optimizing Postgres queries, schema designs, or database configurations.

Build and edit Oxy data app YAML files (*.app.yml) that visualize data through tasks and displays. Use when users ask to create dashboards, data apps, reports, or interactive analytics interfaces. Helps define SQL/workflow/agent tasks and render outputs as tables, charts, and markdown.

Build self-contained interactive HTML dashboards with Chart.js, dropdown filters, and professional styling. Use when creating dashboards, building interactive reports, or generating shareable HTML files with charts and filters that work without a server.

Creates executive summaries, reports, and documentation of findings

|

>

Guide for creating OpenHEXA data pipelines. Use when users ask to create a pipeline, build a data pipeline, automate data processing, extract data from DHIS2/IASO, or schedule data workflows. Covers pipeline architecture, @pipeline and @parameter decorators, tasks, file/database I/O, connections, and the OpenHEXA toolbox.

Orchestrator for creating interactive HTML dashboards in OpenHexa. Use when users ask to create a dashboard, build a dashboard, make a visualization dashboard, display data in charts, or create visual reports. This skill coordinates the technical stack, data querying, maps, and branding skills to produce complete, professional dashboards.

Grey Relational Analysis for MCM/ICM competitions. Use for small-sample correlation analysis and factor importance ranking. Does not require large samples, normal distribution, or linear relationships. Ideal for analyzing which factors most influence outcomes when data is limited.

|

Technical implementation guide for dashboard components including GridStack (drag/resize), ECharts (charts), and Tailwind CSS (styling). Referenced by dashboard-builder skill. Do not use directly - use dashboard-builder instead.

Apply publication-quality style presets to plots. Use when the user wants to style a plot like Wilke, Tufte, Nature, The Economist, or apply minimal/publication styling.

Create decomposed, parallelizable execution plans with copy-pasta prompts for multi-agent workflows. Use when planning large migrations, refactoring tasks, or any work that can benefit from parallel execution across multiple agents.

Guide for creating map visualizations in dashboards. Covers geographic data detection, shape-based maps (polygons/GeoJSON), point-based maps (lat/lon coordinates), and world map backgrounds. Referenced by dashboard-builder skill. Do not use directly - use dashboard-builder instead.

Profile and explore datasets to understand their shape, quality, and patterns before analysis. Use when encountering a new dataset, assessing data quality, discovering column distributions, identifying nulls and outliers, or deciding which dimensions to analyze.

>

Creates charts, dashboards, and visual representations of data

A chart & report builder designed for use by AI.

Create effective data visualizations with Python (matplotlib, seaborn, plotly). Use when building charts, choosing the right chart type for a dataset, creating publication-quality figures, or applying design principles like accessibility and color theory.

Diagnose and fix data quality problems in datasets. Use when working with dirty data, finding duplicates, handling missing values, detecting outliers/anomalies, validating constraints (functional dependencies, referential integrity), profiling datasets, or cleaning data for analysis or ML. Covers the full data quality lifecycle - define, detect, clean, measure.

Queries data warehouse and answers business questions about data. Handles questions requiring database/warehouse queries including "who uses X", "how many Y", "show me Z", "find customers", "what is the count", data lookups, metrics, trends, or SQL analysis.

Designs optimal filtering UX for data tables. Use when building a table that needs filters - analyzes the data columns and determines the best filter type for each. Outputs a unified filter field with inline header filters.

>

Connect Spice to data sources like PostgreSQL, MySQL, S3, Databricks, Snowflake, and more. Use when asked to "add a dataset", "connect to a database", "load data from S3", or "configure a data source".

Creates Power BI reports and visuals in PBIR format. Use for pages, charts, tables, slicers, and visual configuration.

Applies Power BI best practices, BPA rules, and enterprise standards. Use for quality validation, naming conventions, and performance optimization.

Create and manage Plunker (plnkr.co) examples for AG Charts. Use when working with plnkr.co URLs, creating shareable code demos, forking existing plunks, or troubleshooting Plunker structure issues.

Iterative multi-agent research pipeline with gap analysis, source verification, and confidence-rated Obsidian reports. Uses parallel Gemini CLI agents + Exa with progressive deepening across multiple research waves.

Create new AI-powered features using xAI Grok. Use when user mentions "new AI feature", "add Grok", "create prompt", "AI analysis", or "generate with AI".