Audit datasets, joins, labels, and ground truth before analysis or modeling. Use when data meaning, row grain, time semantics, source-of-truth reliability, or label construction may invalidate conclusions; not for general model evaluation after the evidence base is already trusted.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Determine what the data actually represents and whether its labels can support the intended claim. The outcome is an evidence-backed readiness judgment, not a generic profile report.
State the intended decision, entity, row grain, target, prediction moment, outcome window, and population. If these are not known, surface that uncertainty before interpreting columns or labels.
Preserve source data unchanged. Work from read-only inputs or documented snapshots, and keep every correction, exclusion, or derived label traceable to its source.
Read references/audit-playbook.md when selecting concrete tests or grading the severity of a finding.
target, truth, gold, or final.Within already authorized data, systems, and compute, run read-only or reversible tests and document the evidence. Obtain approval before choosing a new source of truth, changing label policy, excluding a material population, applying irreversible corrections, accessing a new or sensitive source, incurring material cost, involving an external reviewer, or sharing records outside the approved boundary.
Use assets/data-and-ground-truth-audit.md for the deliverable. For every material finding, record evidence, affected scope, consequence, and recommended treatment. End with one status:
Never upgrade unknown to ready because no defect was observed.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Design leakage-safe machine learning experiments that mirror real deployment and support fair model comparisons. Use when defining prediction timing, feature eligibility, train-validation-test splits, baselines, metrics, or controlled model iterations; not for auditing whether raw labels are trustworthy.
The English summary is being prepared. Showing the original description.
Isolate the root cause of ML performance drops, inconsistent evaluations, prediction errors, and training-serving mismatches across data, labels, splits, pipelines, models, metrics, and runtime behavior. Use when investigating a reproducible failure or regression, not routine model selection or general performance validation.
The English summary is being prepared. Showing the original description.
Orchestrate an end-to-end data analysis or machine learning project from decision framing through reproducible handoff. Use when a request spans multiple lifecycle stages or an ambiguous modeling request must become a decision-ready result; use narrower audit or experiment-design skills for isolated reviews.
The English summary is being prepared. Showing the original description.
Package completed data analysis and ML work so an independent recipient can reproduce the claimed results, verify artifact lineage, and operate the handoff within its stated scope. Use when finalizing a project, study, model package, or review bundle; not for deploying to a live system.
The English summary is being prepared. Showing the original description.
Route data analysis and machine learning work to the right skill in this suite. Use when starting any analysis, modeling, validation, or reproducibility task and the matching specialized skill is not yet clear; not needed when one specific skill already clearly applies.
The English summary is being prepared. Showing the original description.
Validate trained models and analytical claims against their intended decision, independent evidence, and human-reviewed ground truth. Use when reviewing model performance, analysis conclusions, launch claims, or evaluation reports; use failure diagnosis instead when the main task is locating a known defect.
The English summary is being prepared. Showing the original description.