Wicked Garden Data

wicked-garden:data — data engineering, analysis, and ML

Every sub-action runs inline (no dispatch): parse the arguments, pre-read the data where noted, load the Tier-3 rubric from refs/, apply it, and emit structured markdown with tables and prioritized findings. For delegated or parallel worker execution, dispatch the wicked-garden-data-engineer fork skill instead.

Routing

| Sub-action | Use for | Rubric | |------------|---------|--------| | analyze [--focus stats\|quality\|warehouse\|ml] [--context ] [--refresh] [--scenarios] | one-off exploration of a CSV/Excel/data file | [refs/analyze.md](refs/analyze.md) | | profile | dataset structure + quality profile | [refs/data.md](refs/data.md) | | validate --schema --data | schema validation | [refs/data.md](refs/data.md) | | quality | quality report (completeness, uniqueness, validity) | [refs/data.md](refs/data.md) | | ml review | ML model review | [refs/ml.md](refs/ml.md) | | ml pipeline --type | training-pipeline design | [refs/ml.md](refs/ml.md) | | pipeline design --source --target [--frequency ] | ETL pipeline design | [refs/pipeline.md](refs/pipeline.md) | | pipeline review | ETL pipeline review | [refs/pipeline.md](refs/pipeline.md) | | ontology | ontology recommendation for a dataset | inline (§ Ontology) |

Detailed templates and examples: [refs/analysis-templates.md](refs/analysis-templates.md), [refs/ml-templates.md](refs/ml-templates.md), [refs/pipeline-templates.md](refs/pipeline-templates.md), [refs/data-examples.md](refs/data-examples.md).

Analyze — interactive data analysis

Interactive analysis on a CSV/Excel/data file. Use for one-off data exploration. NOT for schema-level checks (use profile / validate / quality) or pipeline review (use pipeline review).

1. Parse `, --focus` (stats|quality|warehouse|ml, default

stats), --context, --refresh, --scenarios.

1. Read first rows of the file to capture column names / types / nulls / sample.
2. Read("${CLAUDE_PLUGIN_ROOT}/skills/data/refs/analyze.md") — the EDA

rubric, quality/warehouse/ml modes, insight pattern, and output format.

1. Apply the rubric directly for the chosen --focus mode and emit the analysis.

Profile / Validate / Quality — core data engineering ops

Schema-level engineering ops on a dataset. NOT for interactive exploration (use analyze) or ML pipeline review (use ml).

1. Parse the sub-action (profile|validate|quality) and its args (``,

--schema for validate).

1. Read the data file head/tail to capture columns / types / nulls / sample.
2. Read("${CLAUDE_PLUGIN_ROOT}/skills/data/refs/data.md") — the profile,

validate, and quality rubrics with output formats and quality thresholds.

1. Apply the rubric for the requested sub-action and emit structured markdown

with tables and prioritized findings.

Optional scripted paths (deterministic profiling/validation):

sh "${CLAUDE_PLUGIN_ROOT}/scripts/_python.sh" "${CLAUDE_PLUGIN_ROOT}/scripts/data/data_profiler.py" \
  --input data.csv --output profile.json

sh "${CLAUDE_PLUGIN_ROOT}/scripts/_python.sh" "${CLAUDE_PLUGIN_ROOT}/scripts/data/schema_validator.py" \
  --schema schemas/expected.json \
  --data data/actual.csv

For files >1GB, use the analyze sub-action for efficient SQL-based profiling via DuckDB.

ML — model review and training-pipeline design

ML model review and training-pipeline design. NOT for ETL pipeline design (use pipeline) or data profiling (use profile).

1. Parse the sub-action (review|pipeline) and args (`` for review,

--type for pipeline).

1. For review, read model files at ``.
2. Read("${CLAUDE_PLUGIN_ROOT}/skills/data/refs/ml.md") — the model review

checklist, pipeline design template, deployment readiness checklist, and MLOps standards.

1. Apply the rubric for the requested sub-action and emit structured markdown.

Pipeline — data pipeline design and review

Data pipeline design and review. NOT for ML training pipelines (use ml pipeline) or one-off file analysis (use analyze).

1. Parse the sub-action (design|review) and args. For review, read pipeline

files at `. For design, capture --source, --target, --frequency`.

1. Read("${CLAUDE_PLUGIN_ROOT}/skills/data/refs/pipeline.md") — the design

checklist, review rubric with P1/P2/P3 findings, pattern selection, and engineering standards.

1. Apply the rubric for the requested sub-action and emit structured markdown.

Ontology — recommend ontologies for a dataset

Sample a dataset (CSV/Excel/Parquet/JSON) and recommend matching public ontologies (Schema.org, Dublin Core, DCAT, FOAF, GoodRelations, SKOS) or a custom shape. Use this for ontology mapping. NOT for interactive analysis (use analyze) or quality reports (use quality).

1. Arg parse — extract file-path from the arguments.
2. Run recommender:

``bash cd "${CLAUDE_PLUGIN_ROOT}" && uv run python scripts/_run.py scripts/data/ontology_recommender.py "${file_path}" ``

1. Present the script's match table, column-mapping suggestions, and any

custom-ontology fallback inline.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: mikeparcewski
• Source: mikeparcewski/wicked-garden
• License: MIT
• Homepage: https://wg.wickedagile.com/

Install and usage instructions live in the source repository linked above.