aiopshwang
- 8 skills
- 0 followers
- 17 hours ago last updated
- ▌ Evidence First Problem Solving · aiopshwang bundleResolve complex or high-impact problems when the cause, solution path, requirements, or proof boundary is genuinely uncertain. Use when work needs evidence-led diagnosis, consequential design or implementation, or a completion audit; do not trigger merely because work has multiple steps, or for simple facts, fully specified routine changes, or pure creative generation.
- ▌ Using Data Analysis · aiopshwang bundleRoute 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.
- ▌ Diagnosing Ml Failures · aiopshwang bundleIsolate 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.
- ▌ Validating Models And Claims · aiopshwang bundleValidate 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.
- ▌ Shipping Reproducible Results · aiopshwang bundlePackage 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.
- ▌ Auditing Data And Ground Truth · aiopshwang bundleAudit 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.
- ▌ Designing Leakage Safe Experiments · aiopshwang bundleDesign 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.
- ▌ Running Decision Grade Data Science · aiopshwang bundleOrchestrate 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.