复制这段 Prompt，发给你正在使用的 AI 助手。
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/NVIDIA/kumo-engine.正在加载仓库 README…
已展示 17 / 17 个已收集 Skill。
Reference for translating a validated ML request into KumoAI graph configuration, PQL (predictive query language), and Kumo Predict SDK code. Normally loaded by the kumo-data-science skill after its intake checks pass, rather than invoked directly. Triggers:…
原文语言：英语
Use for any work with KumoAI predictive models on Snowflake data: train a model, score data with a trained one, or answer questions about an existing model or run — explain its predictions, diagnose its training, publish, reload or retain it, train or score…
原文语言：英语
Inspect and interpret gradient attribution (including requests called radiant attribution), column analysis and sampled explanation subgraphs from a Kumo model trained in a Snowflake Python notebook. Locate the correct run's explanation artifacts, explain…
原文语言：英语
Publish and reload Kumo models through the Snowflake registry, reconstruct compatible scoring inputs, and retain or retrieve run diagnostics and output files through a Snowflake stage. Use for saved-model scoring and artifact retention without retraining by…
原文语言：英语
Train with caller-supplied labels, weights and splits or score exact entity/anchor rows through Snowflake source tables using the local Kumo API. Use when generated populations do not represent the requested rows.
原文语言：英语
Configure a Kumo model plan for a user-defined Snowflake task, including encoders, run mode, bounded experiments, sampling, optimization, architecture, metrics and refits. Preserve target and evaluation constraints and use existing diagnostics for comparisons.
原文语言：英语
Evaluate an existing Kumo training run in a Snowflake Python notebook using aggregate metrics, trial results, learning curves, refit evidence, and training progress. Use for model-quality questions or training diagnostics; inspect existing results without…
原文语言：英语
Orchestrate Kumo UI ticket work from GitHub issue analysis through implementation, validation, and optional PR creation.
原文语言：英语
Use when the user asks to check, view, or search Kumo application logs from a supplied file or a selected Kubernetes deployment.
原文语言：英语
Scaffold and implement UI features following Kumo conventions. Use when creating new components, pages, hooks, stores, or tests in ui/src/.
原文语言：英语
Use when the user asks to debug, investigate, or fix a GitHub issue or supplies a repository bug report.
原文语言：英语
Use when a training or prediction job is stuck or slow at a particular stage, or its Temporal workflow status needs investigation.
原文语言：英语
Use before a debugging workflow, when asked to check the environment, or when the local CLI tools needed for the requested task are not working.
原文语言：英语
Review PR code changes against ML standards. Use when reviewing PRs that touch ML pipeline code (packages/kumo-core, kumo/pquery, kumo/train, kumo/task, kumo/automl, kumo/explain). Applies lessons learned from past ML reviews.
原文语言：英语
Review PR code changes against UI conventions. Use when reviewing PRs that touch frontend code (ui/src/). Applies lessons learned from past UI reviews and enforces coding guidelines.
原文语言：英语
Scaffold and implement UI catalog components following conventions. Use when creating new primitives, block components, stories, or tests in kumo-ui-catalog.
原文语言：英语
Review PR code changes against UI catalog conventions. Use when reviewing PRs that touch components, stories, or tests in kumo-ui-catalog.
原文语言：英语
暂时无法加载仓库 README。你仍可浏览下方的 Skill 目录。