skills.rest
randoneering
randoneeringCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

dataset-curation

Create and curate evaluation datasets in Snowflake Agent Evaluations format.

Updated Mar 7, 2026
Search Tags:#benchmarking#dataset#snowflake#annotation#dataset-curation#agent-evaluation#cortex
One-click install
npx skills add https://github.com/randoneering/nix-flake-mirror --skill dataset-curation
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: dataset-curation
Source: https://github.com/randoneering/nix-flake-mirror/tree/main/home/programs/opencode/skills/snowflake/agent_optimization/dataset-curation
Command: npx skills add https://github.com/randoneering/nix-flake-mirror --skill dataset-curation

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Create and manage evaluation datasets for Cortex Agents to enable robust testing and benchmarking of agent behavior.

Core Features & Use Cases

  • Workflow design: Define dataset schemas, source questions, and expected answers to ensure consistent evaluation formats.
  • Format standardization: Produce datasets in the Snowflake Agent Evaluations format, including ground_truth structures and tool invocations.
  • Versioned delivery: Maintain dataset versions (v1, v2, ...) and re-register with clear change logs for reproducibility.

Quick Start

Create a new evaluation dataset by outlining the source questions, expected answers, and the steps to register it for evaluation.

Frequently Asked Questions about dataset-curation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create an evaluation dataset for Cortex Agents in Snowflake?▼

To create an evaluation dataset for Cortex Agents, you outline source questions, expected answers, and tool invocations to conform to the Snowflake Agent Evaluations format for robust benchmarking.

What is the required format for Snowflake Agent Evaluations datasets?▼

Snowflake Agent Evaluations datasets require a standardized format that includes ground_truth structures and specific tool invocations to ensure consistent testing and benchmarking of agent behavior.

Can I expand an existing dataset for agent evaluation benchmarking?▼

Yes, you can apply dataset curation to expand existing datasets, build from scratch, or use production-derived datasets while maintaining coverage across agent tools for Snowflake Agent Evaluations.

How do I manage versions for annotated agent evaluation datasets?▼

You manage versions by maintaining dataset iterations like v1 and v2, then re-registering them with clear change logs to support reproducible evaluation pipelines and annotated data.

Does dataset curation work with production-derived data for Cortex agent benchmarking?▼

Yes, dataset curation supports production-derived datasets by applying schema definitions and format standardization to conform to Snowflake Agent Evaluations requirements for accurate benchmarking.

Related Skills

Explore More Data & Analytics Skills→
ContextJet-aiContextJet-ai
29

build-eval-dataset

Create and verify layered evaluation datasets for LLM applications.

Official
Intermediate
randoneeringrandoneering

adhoc-testing-for-cortex-agent

Interactively test Cortex Agent responses and debug issues via scripts/test_agent.py.

Community
Advanced
davekim917davekim917
1

cortex-code

Orchestrate Snowflake-native commands and agent workflows via the Cortex Code CLI.

Community
Advanced
EurecaMomentEurecaMoment

benchclaw-stage3-real-image-evidence-compilation

Clean and annotate real-image datasets for BenchClaw stage 3.

Official
Advanced