DOMAIN PACK / 10 WORKFLOWS

AI and Machine Learning.

Machine learning, model training, evaluation, LLM, retrieval, and responsible release workflows. Discover 10 documented skills, read their use cases, and copy a verified installation command.

Open interactive explorer ↗Install the GNCore CLI →

01 / COLLECTION WORKFLOWS10 REAL SKILL IDS

01 / ml-problem-framing

ML Problem Framing

Decide whether a machine learning approach fits the task, data, constraints, and failure costs.

View skill and install command ↗02 / ml-dataset-audit

ML Dataset Audit

Audit dataset provenance, schema, representativeness, label quality, leakage, and split strategy.

View skill and install command ↗03 / ml-preprocessing-pipeline

ML Preprocessing Pipeline

Build deterministic preprocessing that prevents leakage and preserves training-to-serving parity.

View skill and install command ↗04 / ml-model-train

ML Model Training Run

Implement a reproducible model training run with configuration, baseline, checkpoints, and evaluation.

View skill and install command ↗05 / ml-model-evaluation

ML Model Evaluation

Evaluate model quality, uncertainty, subgroup behavior, and representative errors against a baseline.

View skill and install command ↗06 / ml-model-improvement

ML Improvement Loop

Improve a model through controlled experiments with a fixed evaluation protocol and root-cause analysis.

View skill and install command ↗07 / ml-llm-evaluation

LLM Evaluation Suite

Evaluate an LLM feature with representative tasks, rubrics, adversarial cases, latency, and cost.

View skill and install command ↗08 / ml-rag

RAG Grounding Workflow

Build and evaluate retrieval-augmented answers with source access controls and abstention.

View skill and install command ↗09 / ml-finetuning

Model Fine-Tuning Plan

Assess fine-tuning suitability and prepare a controlled, leakage-safe fine-tuning workflow.

View skill and install command ↗10 / ml-release-monitor

Model Release and Monitoring

Prepare a model release with provenance, compatibility, rollback, and drift monitoring gates.

View skill and install command ↗

02 / INSTALL A SKILLUSE REAL CATALOG IDS

Choose first.
Then install.

Install only the skills relevant to your task and target. GNCore skills guide an AI assistant—they cannot perform work independently.

Read installation details ↗

TERMINAL / COPY COMMANDS

gncore install ml-problem-framing --apps vscode-codex --scope workspace