data-wizard
Analyze data and guide ML: EDA, model selection, feature engineering, stats, visualization, MLOps. Use for data work. NOT for ETL, database design (database-architect), or frontend viz code.
How do I install this agent skill?
npx skills add https://github.com/wyattowalsh/agents --skill data-wizardIs this agent skill safe to install?
- Gen Agent Trust Hubpass
The skill provides a comprehensive toolkit for data science and machine learning analysis. It includes specialized scripts for data profiling, quality scoring, and model recommendations. While it executes shell commands and processes user-provided data files, its operations are localized and standard for data science workflows.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
What does this agent skill do?
Data Wizard
Full-stack data science and ML engineering — from exploratory data analysis through model deployment strategy. Adapts approach based on complexity classification.
Canonical Vocabulary
| Term | Definition |
|---|---|
| EDA | Exploratory Data Analysis — systematic profiling and summarization of a dataset |
| feature | An individual measurable property used as input to a model |
| feature engineering | Creating, transforming, or selecting features to improve model performance |
| hypothesis test | A statistical procedure to determine if observed data supports a claim |
| p-value | Probability of observing data at least as extreme as the actual results, assuming the null hypothesis is true |
| effect size | Magnitude of a difference or relationship, independent of sample size |
| power analysis | Determining sample size needed to detect an effect of a given size |
| CUPED | Controlled-experiment Using Pre-Experiment Data — variance reduction technique for A/B tests |
| MLOps maturity | Level 0 (manual), Level 1 (ML pipeline), Level 2 (CI/CD + CT), Level 3 (full automation) |
| data quality score | Composite metric across completeness, consistency, accuracy, timeliness, uniqueness |
| profile | Statistical summary of a dataset: types, distributions, missing patterns, correlations |
| anomaly | Data point or pattern deviating significantly from expected behavior |
Dispatch
$ARGUMENTS | Action |
|---|---|
eda <data> | EDA — profile dataset, summary stats, missing patterns, distributions |
model <task> | Model Selection — recommend models, libraries, training plan for task |
features <data> | Feature Engineering — suggest transformations, encoding, selection pipeline |
stats <question> | Stats — select and design statistical hypothesis test |
viz <data> | Visualization — recommend chart types, encodings, layout for data |
viz plan <data> [goal] | Viz Plan — JSON chart plan from data + goal via viz-planner.py |
viz render <plan> <data> | Viz Render — PNG/HTML charts from plan via viz-renderer.py |
viz dashboard <profile> | Viz Dashboard — HTML EDA dashboard via dashboard-builder.py |
experiment <hypothesis> | Experiment Design — A/B test design, power analysis, CUPED |
Viz pipeline:
viz plan→viz render→ optionalviz dashboard. Runviz-planner.pyfor JSON encodings,viz-renderer.pyfor PNG/HTML assets, then pass profile + plan/render JSON todashboard-builder.pyfor a shareable EDA report. |timeseries <data>| Time Series — forecasting approach, decomposition, model selection | |anomaly <data>| Anomaly Detection — detection approach, algorithm selection, threshold strategy | |mlops <model>| MLOps — serving strategy, deployment pipeline, monitoring plan | | Natural language about data | Auto-detect — classify intent, route to appropriate mode | | Empty | Gallery — show common data science tasks with mode recommendations |
Auto-Detection Heuristic
If no mode keyword matches:
- Mentions dataset, CSV, columns, rows, missing values → EDA
- Mentions predict, classify, regression, recommend → Model Selection
- Mentions transform, encode, scale, normalize, one-hot → Feature Engineering
- Mentions test, significant, p-value, hypothesis, correlation → Stats
- Mentions chart, plot, graph, visualize, dashboard → Visualization
- Mentions A/B, experiment, control group, treatment, lift → Experiment Design
- Mentions forecast, seasonal, trend, time series, lag → Time Series
- Mentions outlier, anomaly, fraud, unusual, deviation → Anomaly Detection
- Mentions deploy, serve, pipeline, monitor, retrain → MLOps
- Ambiguous → ask: "Which area: EDA, modeling, stats, or something else?"
Gallery (Empty Arguments)
Present common data science tasks:
| # | Task | Mode | Example |
|---|---|---|---|
| 1 | Profile a dataset | eda | /data-wizard eda customer_data.csv |
| 2 | Choose a model | model | /data-wizard model "predict churn from usage features" |
| 3 | Engineer features | features | /data-wizard features sales_data.csv |
| 4 | Pick a stat test | stats | /data-wizard stats "is conversion rate different between groups?" |
| 5 | Choose visualizations | viz | /data-wizard viz time_series_metrics.csv |
| 5b | Plan + render charts | viz plan / viz render | /data-wizard viz plan sales.csv "compare regions" |
| 5c | Build EDA dashboard | viz dashboard | /data-wizard viz dashboard profile.json |
| 6 | Design an experiment | experiment | /data-wizard experiment "new checkout flow increases conversion" |
| 7 | Forecast time series | timeseries | /data-wizard timeseries monthly_revenue.csv |
| 8 | Detect anomalies | anomaly | /data-wizard anomaly server_metrics.csv |
| 9 | Plan deployment | mlops | /data-wizard mlops "churn prediction model" |
Pick a number or describe your data science task.
Skill Awareness
Before starting, check if another skill is a better fit:
| Signal | Redirect |
|---|---|
| Database schema, SQL optimization, indexing | Suggest database-architect |
| Frontend dashboard code, React/D3 components | Suggest relevant frontend skill |
| Data pipeline, ETL, orchestration (Airflow, dbt) | Out of scope — suggest data engineering tools |
| Production infrastructure, Kubernetes, scaling | Suggest devops-engineer or infrastructure-coder |
Complexity Classification
Score the query on 4 dimensions (0-2 each, total 0-8):
| Dimension | 0 | 1 | 2 |
|---|---|---|---|
| Data complexity | Single table, clean | Multi-table, some nulls | Messy, multi-source, mixed types |
| Analysis depth | Descriptive stats | Inferential / predictive | Multi-stage pipeline, iteration |
| Domain specificity | General / well-known | Domain conventions apply | Deep domain expertise needed |
| Tooling breadth | Single library suffices | 2-3 libraries needed | Full ML stack integration |
| Total | Tier | Strategy |
|---|---|---|
| 0-2 | Quick | Single inline analysis — eda, viz, stats |
| 3-5 | Standard | Multi-step workflow — features, model, experiment, timeseries, anomaly |
| 6-8 | Full Pipeline | Orchestrated — mlops, complex multi-stage analysis |
Present the scoring to the user. User can override tier.
Mode Protocols
EDA (Quick)
- If file path provided, run:
!uv run python scripts/data-profiler.py "$1" - Parse JSON output — present: row/col counts, dtypes, missing patterns, top correlations
- Highlight: data quality issues, distribution skews, potential target leakage
- Recommend next steps: cleaning, feature engineering, or modeling
Model Selection (Standard)
- Run:
!uv run python scripts/model-recommender.pywith task JSON input - Present ranked model recommendations with rationale
- Read
references/model-selection.mdfor detailed guidance by data size and type - Suggest: train/val/test split strategy, evaluation metrics, baseline approach
Feature Engineering (Standard)
- If file path, run data profiler first for column analysis
- Read
references/feature-engineering.mdfor patterns by data type - Load
data/feature-engineering-patterns.jsonfor structured recommendations - Suggest: transformations, encodings, interaction features, selection methods
Stats (Quick)
- Run:
!uv run python scripts/statistical-test-selector.pywith question parameters - Load
data/statistical-tests-tree.jsonfor decision tree - Read
references/statistical-tests.mdfor assumptions and interpretation guidance - Present: recommended test, alternatives, assumptions to verify, interpretation template
Visualization (Quick)
- Load
data/visualization-grammar.jsonfor chart type selection - Match data characteristics to visualization types
- Recommend: chart type, encoding channels, color palette, layout
- Read
references/visualization.mdwhen user needs executable artifacts
Viz Plan (Quick)
- Run:
!uv run python scripts/viz-planner.py <data> --goal "<goal>" - Parse JSON — present:
goal_category, chart list with encodings and rationale - Confirm column mappings before rendering
Viz Render (Quick)
- Run:
!uv run python scripts/viz-renderer.py <plan.json> <data> --format png|html - Parse JSON — present output paths and any per-chart errors
- Use PNG for reports/dashboards; HTML for interactive exploration
Viz Dashboard (Quick)
- Ensure profile JSON exists (run
data-profiler.pyand optionallydata-quality-scorer.py) - Optional: run viz plan + render, pass
--viz-planand--render-resultto builder - Run:
!uv run python scripts/dashboard-builder.py <profile.json> --output <path> - Open output HTML via
file://— do not read template into context - Read
references/dashboard-design.mdfor view schema
Experiment Design (Standard)
- Read
references/experiment-design.mdfor A/B test patterns - Design: hypothesis, metrics, sample size (power analysis), duration
- Address: novelty effects, multiple comparisons, CUPED variance reduction
- Output: experiment brief with decision criteria
Time Series (Standard)
- If file path, run data profiler for temporal patterns
- Assess: stationarity, seasonality, trend, autocorrelation
- Recommend: decomposition method, forecasting model, validation strategy
- Address: cross-validation for time series (walk-forward), feature lags
Anomaly Detection (Standard)
- Classify: point anomalies, contextual anomalies, collective anomalies
- Recommend: algorithm (Isolation Forest, LOF, DBSCAN, autoencoder, etc.)
- Address: threshold selection, false positive management, interpretability
- Suggest: alerting strategy, root cause investigation framework
MLOps (Full Pipeline)
- Read
references/mlops-maturity.mdfor maturity model - Assess current maturity level (0-3)
- Design: serving strategy (batch vs real-time), monitoring, retraining triggers
- Address: model versioning, A/B testing in production, rollback strategy
- Output: deployment architecture brief
Data Quality Assessment
Run: !uv run python scripts/data-quality-scorer.py <path>
Dimensions scored:
| Dimension | Weight | Checks |
|---|---|---|
| Completeness | 25% | Missing values, null patterns |
| Consistency | 20% | Type uniformity, format violations |
| Accuracy | 20% | Range violations, statistical outliers |
| Timeliness | 15% | Stale records, temporal gaps |
| Uniqueness | 20% | Duplicates, near-duplicates |
Reference File Index
| File | Content | Read When |
|---|---|---|
references/statistical-tests.md | Decision tree for test selection, assumptions, interpretation | Stats mode |
references/model-selection.md | Model catalog by task type, data size, interpretability needs | Model Selection mode |
references/feature-engineering.md | Patterns by data type: numeric, categorical, temporal, text, geospatial | Feature Engineering mode |
references/experiment-design.md | A/B test patterns, CUPED, power analysis, multiple comparison corrections | Experiment Design mode |
references/mlops-maturity.md | Maturity levels 0-3, deployment patterns, monitoring strategy | MLOps mode |
references/data-quality.md | Quality framework, scoring dimensions, remediation strategies | EDA mode, Data Quality Assessment |
references/visualization.md | Viz plan/render pipeline, encoding rules, dependency handling | Viz Plan, Viz Render, Visualization |
references/dashboard-design.md | Dashboard JSON schema, builder usage, view selection | Viz Dashboard |
Loading rule: Load ONE reference at a time per the "Read When" column. Do not preload.
Critical Rules
- Always run data profiler before recommending models or features — never guess at data characteristics without evidence
- Present classification scoring before executing analysis — user must see and can override complexity tier
- Never recommend a statistical test without stating its assumptions — untested assumptions invalidate results
- Always specify effect size alongside p-values — statistical significance without practical significance is misleading
- Model recommendations must include a baseline — always start with the simplest viable model (logistic regression, linear regression, naive forecast)
- Never skip train/test split strategy — leakage is the most common ML mistake
- Experiment designs must include power analysis — underpowered experiments waste resources
- Feature engineering must address target leakage risk — flag any feature derived from post-outcome data
- Time series cross-validation must use walk-forward — random splits violate temporal ordering
- MLOps recommendations must assess current maturity — do not recommend Level 3 automation for Level 0 teams
- Load ONE reference file at a time — do not preload all references into context
- Data quality scores must be computed, not estimated — run the scorer script on actual data
Canonical terms (use these exactly throughout):
- Modes: "EDA", "Model Selection", "Feature Engineering", "Stats", "Visualization", "Experiment Design", "Time Series", "Anomaly Detection", "MLOps"
- Tiers: "Quick", "Standard", "Full Pipeline"
- Quality dimensions: "Completeness", "Consistency", "Accuracy", "Timeliness", "Uniqueness"
- MLOps levels: "Level 0" (manual), "Level 1" (pipeline), "Level 2" (CI/CD+CT), "Level 3" (full auto)
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/wyattowalsh/agents/data-wizard">View data-wizard on skillZs</a>