Data
Write SQL, explore datasets, and generate insights faster. Build visualizations and dashboards, and turn raw data into clear stories for stakeholders.
10 skills · version 1.1.0
Install
hrida-agent-sdk plugin install data@knowledge-work-skillsOr, inside a session: /plugin install data@knowledge-work-skills. See Installation for scopes and updates.
Connectors
Skills work on their own with files you share, and get more useful when these tools are connected (configured in the plugin's .mcp.json):
Snowflake, Databricks, BigQuery, Hex, Amplitude, Amplitude Eu, Atlassian, Definite.
Skills
| Skill | What it does | Use case | How to use |
|---|---|---|---|
| analyze | Answer data questions -- from quick lookups to full analyses. | When looking up a single metric, investigating what's driving a trend or drop, comparing segments over time, or preparing a formal data report for stakeholders. | /data:analyze <question> |
| build-dashboard | Build an interactive HTML dashboard with charts, filters, and tables. | When creating an executive overview with KPI cards, turning query results into a shareable self-contained report, building a team monitoring snapshot, or needing multiple charts with filters in one browser-openable file. | /data:build-dashboard <description> [data source] |
| create-viz | Create publication-quality visualizations with Python. | When turning query results or a DataFrame into a chart, selecting the right chart type for a trend or comparison, generating a plot for a report or presentation, or needing an interactive chart with hover and zoom. | /data:create-viz <data source> [chart type] |
| data-context-extractor | Generate or improve a company-specific data analysis skill by extracting tribal knowledge from analysts. BOOTSTRAP MODE - Triggers: "Create a data context skill", "Set up data analysis for our warehouse", "Help me create a skill for our database", "Generate a data skill for [company]" → Discovers schemas, asks key questions, generates initial skill with reference files ITERATION MODE - Triggers: "Add context about [domain]", "The skill needs more info about [topic]", "Update the data skill with [metrics/tables/terminology]", "Improve the [domain] reference" → Loads existing skill, asks targeted questions, appends/updates reference files. | When data analysts want Claude to understand their company's specific data warehouse, terminology, metrics definitions, and common query patterns. | /data:data-context-extractor |
| data-visualization | Create effective data visualizations with Python (matplotlib, seaborn, plotly). | When building charts, choosing the right chart type for a dataset, creating publication-quality figures, or applying design principles like accessibility and color theory. | Automatic |
| explore-data | Profile and explore a dataset to understand its shape, quality, and patterns. | When encountering a new table or file, checking null rates and column distributions, spotting data quality issues like duplicates or suspicious values, or deciding which dimensions and metrics to analyze. | /data:explore-data <table or file> |
| sql-queries | Write correct, performant SQL across all major data warehouse dialects (Snowflake, BigQuery, Databricks, PostgreSQL, etc.). | When writing queries, optimizing slow SQL, translating between dialects, or building complex analytical queries with CTEs, window functions, or aggregations. | Automatic |
| statistical-analysis | Apply statistical methods including descriptive stats, trend analysis, outlier detection, and hypothesis testing. | When analyzing distributions, testing for significance, detecting anomalies, computing correlations, or interpreting statistical results. | Automatic |
| validate-data | QA an analysis before sharing -- methodology, accuracy, and bias checks. | When reviewing an analysis before a stakeholder presentation, spot-checking calculations and aggregation logic, verifying a SQL query's results look right, or assessing whether conclusions are actually supported by the data. | /data:validate-data <analysis to review> |
| write-query | Write optimized SQL for your dialect with best practices. | When translating a natural-language data need into SQL, building a multi-CTE query with joins and aggregations, optimizing a query against a large partitioned table, or getting dialect-specific syntax for Snowflake, BigQuery, Postgres, etc. | /data:write-query <description of what data you need> |
Automatic skills
3 skills marked Automatic are background expertise: they have no slash command and load on their own when your request needs them.
Example
Ask in plain language and the right skill loads automatically, or call one directly:
/data:analyze <question>