| name | small-data-power-planner |
| description | Help teams decide what can be learned responsibly from small, imbalanced, expensive, or scarce datasets. Use when an agent needs a judgment-heavy data science workflow for avoid overfitting scarce data, including evidence review, local artifact inspection, risk classification, stakeholder-ready decisions, reproducibility, governance, or agent-to-agent handoff. Trigger for Codex, Claude, Gemini, Copilot, Cursor, Windsurf, Gravity, LangGraph, CrewAI, AutoGen, or local agents when this exact workflow is needed. |
Small Data Power Planner
Mission
Help teams decide what can be learned responsibly from small, imbalanced, expensive, or scarce datasets.
Current pain point: Small datasets are forced through high-capacity methods, producing unstable conclusions and overconfident narratives.
Why this skill exists: Power, uncertainty, resampling, priors, and simpler baselines must be planned before modeling scarce data.
Operating Rules
- Start by restating the decision this skill is supporting.
- Inspect local artifacts first before asking for context.
- Treat scripts as evidence collectors, not as substitutes for judgment.
- Preserve raw data, notebooks, configs, and model artifacts unless the user explicitly asks for mutation.
- Mark missing context as
unknown, not provided, or owner decision; do not invent it.
- Classify each blocker as
stop, fix-first, monitor, accepted risk, or owner decision.
- Use the output contract exactly unless the user asks for a different format.
- Keep final recommendations auditable: every important claim needs evidence, assumption, or caveat.
What This Skill Must Do
- Transform a vague request into an explicit Small Data Power Planner decision with named owner, evidence, assumptions, and action threshold.
