data-science-research

v0.2.2

Exploratory data science & reproducible research team — agents (exploratory-data-scientist, feature-and-modeling-engineer, research-reproducibility-engineer) for the analysis layer between raw data and a defensible result: data profiling/cleaning, EDA, hypothesis generation, communicating findings with uncertainty; feature engineering, classical modeling (regression, trees, boosting), model selection, evaluation (cross-validation, metrics) and leakage avoidance; and the reproducibility spine — notebook hygiene, pinned environments, experiment tracking, data/version control, seeds, and reproducible pipelines. best-practices, decision-tree knowledge bank, skills, commands, templates, a hook, scenarios bank, and stdlib-only ds_calc.py (classification/regression metrics, split-check). Seams: is-the-result-statistically-real -> applied-statistics; productionize/serve/monitor -> ml-engineering; data pipelines/warehouse -> data-platform. Requires ravenclaude-core@>=0.7.0.

Claude Code3 Skills

By Matt CorbettLicense: MIT7 GitHub starsUpdated last week

Directory evidence

Runtimes: Claude Code
Parsed components: 3 skill or MCP entries
Source updated: Sep 15, 2026
Manifest status: Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install data-science-research for Claude Code

Installs for the current user

claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install data-science-research@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually

$ git clone https://github.com/mcorbett51090/RavenClaude

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/data-science-research/.

Plugin files

plugins/data-science-research/

├── .claude-plugin/plugin.json
├── skills/eda-workflow/SKILL.md
├── skills/feature-engineering-and-modeling/SKILL.md
└── skills/reproducible-research/SKILL.md

Included Skills3

eda-workflowskills/eda-workflow/SKILL.md

Run a disciplined exploratory pass before anyone models: profile the data (shape, types, missingness, cardinality, distributions), make and document cleaning decisions, visualize distributions and relationships, spot leakage candidates and target-definition problems, generate hypotheses, and communicate findings with their uncertainty.

feature-engineering-and-modelingskills/feature-engineering-and-modeling/SKILL.md

Engineer features and fit, select, and honestly evaluate classical models on tabular data: build leakage-aware features, set a baseline, choose between regression / trees / gradient boosting, build a leakage-safe cross-validation harness with every transform fit inside the fold, and pick the metric from the decision and its cost structure.

reproducible-researchskills/reproducible-research/SKILL.md

Make an analysis re-runnable by anyone: enforce notebook hygiene (top-to-bottom-clean, no out-of-order state), pin environments and dependencies in a lockfile, set and thread random seeds, version data and artifacts, track experiments (params + metrics + code/data version per run), and convert a run-once notebook into a scripted, deterministic pipeline.

Plugin manifests1

plugins/data-science-research/.claude-plugin/plugin.json

{
  "name": "data-science-research",
  "version": "0.2.2",
  "description": "Exploratory data science & reproducible research team — agents (exploratory-data-scientist, feature-and-modeling-engineer, research-reproducibility-engineer) for the analysis layer between raw data and a defensible result: data profiling/cleaning, EDA, hypothesis generation, communicating findings with uncertainty; feature engineering, classical modeling (regression, trees, boosting), model selection, evaluation (cross-validation, metrics) and leakage avoidance; and the reproducibility spine — notebook hygiene, pinned environments, experiment tracking, data/version control, seeds, and reproducible pipelines. best-practices, decision-tree knowledge bank, skills, commands, templates, a hook, scenarios bank, and stdlib-only ds_calc.py (classification/regression metrics, split-check). Seams: is-the-result-statistically-real -> applied-statistics; productionize/serve/monitor -> ml-engineering; data pipelines/warehouse -> data-platform. Requires ravenclaude-core@>=0.7.0.",
  "author": {
    "name": "Matt Corbett"
  },
  "homepage": "https://github.com/mcorbett51090/RavenClaude",
  "license": "MIT",
  "keywords": [
    "data-science",
    "eda",
    "feature-engineering",
    "modeling",
    "scikit-learn",
    "cross-validation",
    "reproducibility",
    "experiment-tracking",
    "jupyter",
    "leakage",
    "evaluation",
    "pandas"
  ],
  "requires": {
    "plugins": [
      "ravenclaude-core@>=0.7.0"
    ]
  }
}