Rai Build Starter Ontology
Walks through building a first RAI ontology from Snowflake tables or local data samples. Use when creating a new RAI model, starting a proof of concept, or onboarding a new dataset.
Dev Skills Review
Reviews RAI agent skills for structure, content quality, prompt engineering,
Rai Prescriptive Problem Formulation
Formulates optimization and constraint satisfaction problems from ontology models — decision variables, constraints, objectives, and common patterns. Use for optimization and constraint-satisfaction tasks — building, reviewing, debugging, or relaxing an over-constrained formulation to resolve a reported conflict / IIS; then solve it with rai-prescriptive-solver-management. Not for interpreting or…
Rai Discovery
Translation, ideation, and routing layer between an ontology and the RAI reasoners. Surfaces questions the data can answer, classifies them by reasoner family (prescriptive, graph, predictive, rules), and translates user-facing problem framings into the technical implementation hints the downstream reasoner skills need. Use before choosing a reasoner workflow or when scoping what to build next.
Rai Prescriptive Solver Management
Covers solver lifecycle including problem type classification, solver selection and creation, global constraints, pre-solve validation, solve execution (including requesting sensitivity and conflict / IIS diagnostics), and solver-level diagnostics. Use when configuring or running optimization solvers, not for interpreting post-solve results (see rai-prescriptive-results-interpretation).
Rai Health
Guides diagnosis of RAI engine performance, failed transactions, CDC/data-stream health, and CDC engine management. Use when a reasoner is slow or queuing, a transaction or batch has failed, a CDC stream is suspended or quarantined, or CDC engine sizing/recovery is needed.
Dev Release
Bumps the plugin version across manifest files, commits, and
Rai Deployment
Take a built RelationalAI model to production — deploy it into a Snowflake schema and version it through the op log (branch, collaborate, merge, and tear down with the `rai models` CLI), or deploy it as a Snowflake Intelligence (Cortex) agent. The one path-to-prod skill across deployment targets. Use when deploying a model, managing its deployed lifecycle, or operationalizing it as a Cortex agent…
Rai Setup
Setup and configuration for RelationalAI — first-time install walkthrough and all raiconfig.yaml tuning. Use when installing RAI, connecting to Snowflake, running RAI locally on DuckDB for development, or editing raiconfig.yaml. Not for writing PyRel model code (see rai-pyrel-coding) or solver usage and diagnostics (see rai-prescriptive-solver-management).
Rai Prescriptive Results Interpretation
Interprets optimization solver output including solution extraction, status codes, quality assessment, result explanation, sensitivity analysis (shadow prices, reduced costs, basis status), and infeasibility diagnosis (conflict / IIS). Use when analyzing solve results, reading dual or marginal values, diagnosing why a model is infeasible, or communicating optimization outcomes — not solver config…
Rai Predictive Training
Configure and train graph neural network (GNN) models, generate predictions, evaluate results, and manage trained models. Use when ready to train, generate predictions, evaluate, or manage models; for concepts, data loading, edges, and feature configuration, see `rai-predictive-modeling`.
Rai Querying
PyRel v1 query construction against `relationalai.semantics.Model` — selects, filters, joins, aggregates, grouping, export. Load this BEFORE writing any PyRel query, even your first one — your prior knowledge of the syntax is likely stale. Use whenever the user asks to query, count, list, rank, aggregate, join, or export data from a RAI model, even if they don't say "PyRel". Does not cover derivi…
Rai Pyrel Coding
Covers PyRel v1 language syntax — imports, type system, concepts, properties, relationships, data loading, references, and code structure. Use when writing or reviewing general PyRel code — not query construction (see rai-querying), business-rule authoring via derived properties (see rai-rules-authoring), or optimization formulation with decision variables, constraints, and objectives (see rai-pr…
Rai Graph Analysis
Graph algorithm selection and execution on PyRel v1 models — construction from ontology patterns, parameter tuning, and result extraction. Use for questions about a network's structure — centrality and importance, community detection, connectivity and components, reachability and dependencies, shortest paths and distance, node similarity, and variable-length path enumeration (where the route itse…
Rai Ontology Design
Covers RAI domain modeling decisions — concepts, relationships, data mapping, model composition, enrichment, and advanced modeling patterns. Use when reviewing, enriching, or evolving an existing ontology — not for greenfield starter builds (see rai-build-starter-ontology).
Rai Predictive Modeling
Build graph neural network (GNN) models — concepts, Snowflake data loading, task relationships, graph edges, and PropertyTransformer features. Use for node classification, regression, and link prediction tasks; for training, predictions, and evaluation, see `rai-predictive-training`.
Rai Rules Authoring
Converts natural language business rules into PyRel derived properties — validation, classification, derivation, alerting, and reconciliation. Use whenever a task assigns each entity a new tier, segment, score, or flag, or derives a new property; author it here as a derived property, then query it with rai-querying.