Results for “model-checking”

Manage machine learning models in the Agent Platform Model Registry: list, describe, upload, update, and delete models and their versions.

Guides implementation of new model architectures in NeMo AutoModel through five phases: discovery, implementation, registration, validation, and testing.

The layers trade timeliness against definitiveness.

Monitor a live model for data quality, input and prediction drift, performance decay, and fire retraining triggers.

Cross-model benchmark for gstack skills. (gstack)

Models threats for a service, feature, endpoint, integration, or architecture: assets, attackers, boundaries, flows, and abuse cases.

Detect poisoned training data and backdoored models across the ML pipeline using statistical analysis, activation clustering, and spectral signatures.

Turn model work into a production ML system with data contracts, reproducible training, quality gates, deployable artifacts, and monitoring.

Plan which model tier handles which work BEFORE execution begins — a high-cognition model deeply understands the problem, lays the foundations, then emits a modular plan assigning each module the cheapest tier that can safely execute it, with escalation tripwires and one-way-door protection. Advisory only: it announces "next module → tier X / model Y" at each boundary and the HUMAN switches models — harnesses like Cursor cannot switch mid-run. Load when the user asks which model to use, wants a model plan, model tiers, model-tier routing, assign models to tasks or modules, says "cheap model got stuck", "which model for this task", "cost-efficient model choice", or when implementation-plan / problem-to-plan need a model: tier column. NOT dynamic-routing (plan-path selection after failure) — this skill assigns cognition tiers to work.

Every metric encodes an opinion about which mistake hurts.

Research latest Claude models and update selection guide — run when new models drop or periodically to stay current

Entrena modelos de machine learning con Scikit-learn, LightGBM y XGBoost, desde un baseline hasta un modelo productivo con validación robusta y explicabilidad.

Turns model work into a production ML system with data contracts, reproducible training, quality gates, deployable artifacts, and monitoring.

Deploy a trained model to serving with versioning, shadow or canary rollout, and a tested rollback path.

Prevents AI-introduced regressions with sandbox-mode API testing, automated bug-check workflows, and patterns that catch blind spots where the same model writes and reviews code.

Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.

Evaluate model quality with task-appropriate metrics and systematic error analysis. Use when: (1) comparing models, (2) analyzing failures, (3) setting go/no-go thresholds. NOT for: production monitoring implementation.

Audit an existing financial model workbook for correctness (formula tracing, hardcode and error detection, sign and consistency checks, tie-outs, and sensitivity stress) before you rely on its outputs.

Reduces AI API costs by 30-75% by classifying task complexity, checking prompt quality, and routing tasks to the most cost-efficient model tier before execution.

Comprehensive process for discovering and validating data model requirements before design

Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.

Model-trader version compatibility protocol: Embed version metadata in checkpoints, validate at load time. Trigger when: (1) training and live trading versions diverge, (2) models fail to load, (3) action interpretation issues.

Train machine learning models end-to-end, covering data loading, preprocessing, architecture selection, training loops, validation, and checkpointing. Use when the user requests model training or provides relevant inputs for this workflow.

Oracle CLI second-model review/debug/refactor/design with selected files, dry-run token checks, API or browser engine.

Train or fine-tune sentence-transformers models for retrieval, similarity, clustering, classification, and reranking, with support for bi-encoders, cross-encoders, and sparse encoders.

Performs STRIDE-A threat model analysis of repositories and systems, producing architecture overviews, DFD diagrams, prioritized findings, and executive assessments. Supports both single analysis and incremental updates with change tracking.

Fine-tune open models or Gemini models using Agent Platform infrastructure, from environment setup through data preparation, job configuration, monitoring, and deployment.

Recommend model families and validation strategy based on data, constraints, and objective. Use when: (1) choosing algorithms, (2) balancing bias/variance, (3) planning benchmark baselines. NOT for: final legal/compliance sign-off.

Verify tasks marked [X] in tasks.md are implemented, not phantom completions (marked done but backed by missing or dead code).

Enforces rigorous ML modeling, feature engineering, training, and evaluation standards at principal-engineer level.

database-model-standards

Runs bottom-up type-chain validation across database, hooks, and UI layers, then fixes errors at the failing layer for project health checks before large changes.

Mandatory training archive with model gating (APPROVED/REVIEW/DROP). Trigger when: (1) training run completes, (2) need to decide which models to deploy, (3) want historical training reference, (4) need checkpoint recommendations for overfitting.