zpower426

Ensures analysis code quality post statistical review by checking for efficiency, reproducibility, and clarity.

Evaluate trained models with rigorous statistical methods and one-time test set assessments.

Execute analysis plans with independent tasks using fresh subagents for focused execution and review.

Transform analytical designs into detailed, executable tasks for efficient execution.

Kick off analysis projects with structured hypothesis-driven brainstorming.

Systematically select the best model through baseline comparison and hyperparameter optimization.

datapowers provides a robust framework for data mining and machine learning workflows, ensuring statistical integrity and rigorous validation.

Decompose analysis designs into actionable tasks for execution.

Facilitate structured brainstorming for analysis projects to ensure clarity and alignment before coding.

Systematic approach to investigate and resolve issues in data pipelines and ML models.

Execute an analysis plan with subagent-driven analysis and a two-stage review process.

Verifies statistical correctness of analytical tasks to ensure data integrity.

Streamline the creation, transformation, and selection of features while ensuring reproducibility and avoiding data leakage.

Ensure analytical outputs are correct and statistically significant with rigorous auditing.

Maintain a persistent record of analysis sessions to prevent context drift.

Introduction to a disciplined analytical workflow for data mining and statistical rigor.

Defines the structure and testing protocols for creating new datapowers skills.

Generate a high-density, PII-free data profile for datasets to provide structured context for subagents.

Streamline the finalization of analysis work by guiding delivery options and artifact verification.

Execute specific analysis tasks as a subagent with complete task specifications.

Systematic exploration of datasets to ensure thorough understanding before modeling.

Enforce three-layer data validation before training to prevent model failures.

Ensures all analyses, models, and reports are verified before delivery.

Execute written analysis plans with structured task management and mandatory reviews.

Create reproducible analysis reports that communicate findings clearly and lead to actionable insights.

Ensure strict temporal integrity in time-series feature engineering to prevent data leakage.

Validate data quality and schema before model training or feature engineering.