randoneering/randoneering-agent-guide - Page 3

experiment-tracking

This skill contains some example code snippets for running experiment tracking

ml-development

**[REQUIRED]** for ALL data science, machine learning, data analysis, and statistical tasks. MUST be invoked when: analyzing data, building ML models, creating visualizations, statistical analysis, exploring datasets, training models, feature engineering,…

ml-jobs

Transform local Python scripts into Snowflake ML Jobs. Use when: running ML workloads on Snowflake compute pools, GPU training, submitting Python scripts to run remotely, converting local scripts to ML jobs, distributed training. Triggers: ml job, submit job,…

model-monitor

Set up and manage ML Observability for Snowflake Model Registry models. Use when: creating model monitors, tracking drift, viewing performance metrics, managing monitor lifecycle. Triggers: model monitor, ML observability, monitor model, drift detection,…

model-registry

Deploy models to Snowflake Model Registry and route to inference deployment. Use when: registering serialized models, deploying trained models, logging models. Triggers: model registry, deploy model, register model, log model, model to snowflake.

machine-learning

**[REQUIRED]** For **ALL** data science and machine learning tasks. Use when: analyzing data, training models, deploying models to Snowflake, registering models, working with ML workflows, running ML jobs on Snowflake compute, model registry, log model,…

spcs-inference

Deploy models from Snowflake Model Registry to Snowpark Container Services for real-time inference. Use when: creating inference services, SPCS deployment, REST endpoints for models, GPU inference. Triggers: create inference service, SPCS inference, inference…

openflow

Openflow data integration operations. Openflow is a Snowflake NiFi-based product for data replication and transformation. Use for connector deployment, configuration, diagnostics, and custom flows.

best-practices-audit

Verify semantic view compliance with established best practices including naming conventions, descriptions, metadata completeness, data quality standards, inconsistencies detection, and duplicates detection.

custom-criteria-audit

Evaluate semantic view against user-defined validation rules and custom criteria specified in natural language.

semantic-view-optimization-audit

Comprehensive audit system for semantic views with multiple audit types including VQR testing, best practices verification (with inconsistencies and duplicates detection), and custom criteria evaluation.

vqr-testing-audit

Systematically test semantic views by evaluating all verified queries without VQR hints. Identifies which queries fail to measure semantic view completeness.

semantic-view-creation

Create new semantic views using FastGen API for automated generation from SQL queries and table metadata. Falls back to manual approach if FastGen fails.

semantic-view-optimization-debug

Debug and fix specific SQL generation issues in semantic views. Diagnoses root causes, applies targeted optimizations, and validates fixes. Use after semantic-view-optimization-onboarding skill when you have a failing question or VQR.

semantic-view-optimization-patterns

Library of optimization patterns for dimensions, metrics, filters, relationships, and custom instructions. Use when root cause analysis identifies gaps needing targeted fixes.

semantic-view-optimization-setup

Initial setup for optimization sessions. Downloads semantic view YAML, extracts verified queries, and prepares optimization directory. Required first step before audit or debug workflows.

semantic-view-optimization

Use for **ALL** requests that mention: create, build, debug, fix, troubleshoot, optimize, improve, or analyze a semantic view. This is the **REQUIRED** entry point - even if the request seems simple. DO NOT attempt to create or debug semantic views manually -…

semantic-view-optimization-time-tracking

Track and report execution time for workflow steps including setup, audit, debug, and validation. Only use when explicitly requested for performance analysis.

semantic-view-upload

Upload a semantic view YAML file to Snowflake database.schema

semantic-view-optimization-validation

Validate semantic model changes by comparing SQL execution results with exact match requirements. Used by audit and debug to verify optimizations produce correct results.

snowflake-postgres-connect

Network policy setup and connectivity checks. Triggers: 'my IP', 'network policy', 'can't connect', 'add IP', 'import connection'.

snowflake-postgres-manage

Manage Snowflake Postgres instances: list, describe, create, suspend, resume.

snowflake-postgres

**[REQUIRED]** Use for **ALL** requests involving Snowflake Postgres: create instance, list instances, suspend, resume, reset credentials, describe instance, import connection. Triggers: 'postgres', 'pg', 'create instance', 'show instances', 'suspend',…

writing-style

Justin's personal blog writing style for Hugo site content. Triggers: blog posts, weekly updates, technical tutorials. Covers conversational tone, honest reflection, technical accessibility, Strunk's clarity principles, and AI pattern avoidance.

flox-builds

Building and packaging applications with Flox. Use for manifest builds, Nix expression builds, sandbox modes, multi-stage builds, and packaging assets.

flox-containers

Containerizing Flox environments with Docker/Podman. Use for creating container images, OCI exports, multi-stage builds, and deployment workflows.

flox-cuda

CUDA and GPU development with Flox. Use for NVIDIA CUDA setup, GPU computing, deep learning frameworks, cuDNN, and cross-platform GPU/CPU development.

flox-publish

Use for publishing user packages to flox for use in Flox environments. Use for package distribution and sharing of builds defined in a flox environment.

flox-services

Running services and background processes in Flox environments. Use for service configuration, network services, logging, database setup, and service debugging.

flox-sharing

Sharing and composing Flox environments. Use for environment composition, remote environments, FloxHub, and team collaboration patterns.

documentation-writing

Documentation writing guidelines. Triggers: README, CHANGELOG, API docs, technical writing, user guides, code comments. Covers natural writing style, AI phrase avoidance, structure, clarity, and audience-appropriate tone.