Menu
Quick dataset profiling for compact schema, summary statistics, missingness, duplicates, distributions, and obvious quality checks. For goal-directed or domain-sensitive EDA, use structured_eda instead.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Author and publish bespoke analytical reports from validated findings, bounded aggregate evidence, methodology, caveats, and an evidence ledger. Use for final reports, report-like dashboards, interactive analytical briefings, or redesigning existing report HTML; the creative author owns all unspecified story, prose, layout, and visual decisions.
Use Dataclaw tools for governed data science and analytics work. Includes tools for interacting with data, running jupyter notebooks, proposing, updating and reviewing analytical plans, experiment tracking, training machine learning models, and generating reports.
Publish, revise, inspect, export, and troubleshoot DataClaw artifacts. Use when a report, dashboard, chart, profile, model card, or living-report note should become a secure, versioned, shareable artifact through dataclaw-artifacts.
Estimate and defend causal effects inside the Dataclaw data-science workflow by choosing an identification strategy, stating the estimand, testing design-specific assumptions, quantifying uncertainty, and refusing unsupported causal claims. Use for impact analysis, policy or treatment effects, difference-in-differences, matching or weighting, instrumental variables, regression discontinuity, synthetic controls, interrupted time series, mediation questions, and observational “does X cause Y?” requests.
Design, analyze, or audit randomized experiments inside the Dataclaw data-science workflow with a defensible randomization unit, power and duration, pre-registered outcomes, assignment and exposure checks, sequential and multiplicity control, and uncertainty at the assignment level. Use for A/B and multivariate tests, cluster or geo experiments, switchbacks, holdouts, factorial designs, non-inferiority, uplift and heterogeneous-treatment analyses, experiment readouts, and sample-size planning.
Build reproducible, leakage-safe model inputs inside the Dataclaw data-science workflow by defining prediction-time availability, excluding identifiers, fitting transforms within folds, cross-fitting target-derived features, handling temporal and grouped data correctly, and versioning feature lineage. Use for tabular, temporal, categorical, text, geospatial, nested, interaction, aggregation, embedding, selection, and dimensionality-reduction features used by predictive, forecasting, causal, uplift, or segmentation models.
| name | data_profiling |
| description | Quick dataset profiling for compact schema, summary statistics, missingness, duplicates, distributions, and obvious quality checks. For goal-directed or domain-sensitive EDA, use structured_eda instead. |
| tags | ["data","analysis","profiling"] |
Related skills: structured_eda (escalate to goal-directed EDA when the profile is not enough).
Use this skill for a quick, compact dataset profile: shape, schema, summary statistics, missingness, duplicates, basic distributions, and obvious quality flags.
If the user asks for exploratory data analysis, model readiness, dashboard/KPI preparation, survey/research analysis, time-series/event/text/geospatial/causal exploration, or any analysis where the user's goal/domain should change the path, fetch and follow structured_eda instead.
Load and inspect the dataset. Show the shape (rows x columns), column names, and data types.
Summary statistics for each column:
Missing values: Report count and percentage per column. Flag columns with >20% missing.
Duplicates: Check for duplicate rows and report count.
Distributions: For numeric columns, note skewness. For categorical columns with <20 unique values, show value counts.
Correlations: For a quick profile, compute only a small numeric correlation summary after excluding identifiers, codes, constants, and obvious non-measures. Highlight strong correlations (|r| > 0.7) as relationship candidates, not conclusions.
Data quality flags: Note any columns that appear to have constant values, high cardinality, or mixed types.
Present results in clear tables and summarize 3-5 key findings at the end.
Do not continue into follow-up loops, causal interpretation, modeling recommendations, or domain-heavy conclusions from this skill alone. If the profile reveals material quality risks, target/metric questions, surprising relationships, or domain-specific caveats, switch to structured_eda.
