Claude skills for data analysis
Paste query results and get the headline finding, the drivers, and the right chart for the data shape, not a paragraph restating the numbers.
- SQL to InsightsTurns SQL query results into a decision-ready business narrative - headline finding, drivers, recommendation - plus the right chart choice for the data shape. Use when someone asks "what does this data actually mean", "summarize these query results for the exec team", "what chart should I use for this", or pastes a result set and wants the so-what for a non-technical audience. Do NOT use to diagnose or speed up the query itself - use sql-query-optimizer instead; do NOT use to build a full multi-part narrative presentation around an analysis - use data-story instead; do NOT use for open-ended exploration of an unfamiliar dataset - use eda-playbook instead.Data
- EDA PlaybookRuns a structured exploratory data analysis on a new or suspect dataset - schema audit, target analysis, feature profiling, missingness patterns, and leakage checks - ending in a written decision log. Use when someone says "I just got this dataset, where do I start", "my model metrics look too good", "audit this data before we model it", or is debugging unexpected model behavior. Do NOT use for writing the transformation code itself - use pandas-expert instead; for ongoing production data monitoring use data-quality; for constructing model features after EDA use ml-feature-engineering; for answering a one-off business question from a database use sql-to-insights.Data
- Data Quality FrameworkDesigns layered data quality checks across completeness, validity, consistency, uniqueness, timeliness, and accuracy, with severity tiers, freshness SLAs, and anomaly baselines wired into dbt and CI. Use when someone asks "how do I stop bad data reaching dashboards", "set up dbt tests for this model", "our pipeline loaded duplicate rows again", "what data quality checks should this table have", or "how fresh does this source need to be". Do NOT use for detecting distribution drift in ML features and predictions - use data-drift-monitor instead; for one-off exploration and profiling of a new dataset - use eda-playbook instead; for infrastructure and application telemetry - use observability-stack instead; for removing personal data from datasets - use pii-scrubber instead.Data
- R for AnalysisWrites idiomatic tidyverse R for data analysis - dplyr wrangling pipelines, tidyr reshaping, explicit joins, layered ggplot2 visualization, and broom-tidied statistical models - with reproducibility practices baked in. Use when someone asks "write this analysis in R", "how do I pivot this data frame", "fit a regression per group in R", or wants messy base-R scripts converted to clean pipe-based tidyverse code. Do NOT use for Python-based dataframe work - use pandas-expert instead; for interpreting results for stakeholders use sql-to-insights.Data
- Sql OptimizerAnalyzes SQL queries and recommends indexing, rewrite, execution-plan, and data-model improvements.Data
- Hugging Face DatasetsExplores and extracts Hugging Face datasets through the read-only Dataset Viewer API - splits, paginated rows, search, filter, parquet links, and stats - plus zero/low-dependency upload flows.Data
You never pick the skill. Connect once and describe the task; the right one installs itself. Connect to Claude
Questions
Does Claude run the queries?
Skills shape how Claude interprets and presents results you provide (or that other tools fetch). They are instructions, not database connections.