Навыки: Данные

Expert-level Databricks platform, Apache Spark, Delta Lake, MLflow, notebooks, and cluster management

Create and query Databricks Genie Spaces for natural language SQL exploration. Use when building Genie Spaces or asking...

Use this skill to classify an incoming Databricks task and route it to the narrowest owning specialist on the Databricks...

Create and manage Databricks notebooks programmatically. Use when generating ingestion code, creating ETL notebooks, exe...

Execute SQL queries against Databricks using the DBSQL MCP server. Use when querying Unity Catalog tables, running SQL a...

Unity Catalog system tables and volumes. Use when querying system tables (audit, lineage, billing) or working with volum...

Unity Catalog system tables for lineage, audit logs, billing, compute, jobs, and query history. Use when querying system...

Python dataclass best practices: slots, frozen, validation. Trigger when optimizing dataclasses or creating config class...

Dataclass patterns including frozen dataclasses, slots, immutability, and value objects. Activated when designing data c...

Work with Data Commons, a platform providing programmatic access to public statistical data from global sources. Use thi...

Expert skill for Datadog Observability & Security Platform

Query logs, metrics, monitors, and dashboards from Datadog. Search logs, check alert status, and investigate incidents.

Troubleshoot Datadog API authentication issues (401/403 errors), understand API keys vs app keys, and configure correct...

Automatically detects Datadog resource mentions (URLs, service queries, natural language) and intelligently fetches cond...

Work with Datadog Incidents API - fetch incidents with enrichment, update incident fields, understand incident data stru...

Search Datadog logs via API - query syntax, storage tiers (indexes, flex, online-archives), pagination. Use when searchi...

Reviews SQL queries and DataFrame operations for optimization opportunities including predicate pushdown, partition prun...

Save, publish, create, attach to, or share a Datagrok project, including turning data sync on. The save and share flows...

Convert documents (PDF, EPUB, PPTX, DOCX, XLSX, HTML, images) to Markdown using Datalab cloud API. Use when user wants t...

Datalog bottom-up fixpoint iteration for recursive queries

Credit risk data cleaning and variable screening pipeline for pre-loan modeling. Use when working with raw credit data t...

Use this skill when the user asks about DataQ — FMCSA's data review system at dataqs.fmcsa.dot.gov — for disputing inspe...

Query, explore, and update databases through existing DataRobot data connections (datastores) with the connection's stor...

Guidance for feature engineering, feature discovery, feature importance analysis, and understanding DataRobot's automate...

Tools and guidance for model explainability, prediction explanations, feature impact analysis, SHAP values, SHAP distrib...

Comprehensive guidance for training models in DataRobot, including project creation, AutoML configuration, feature engin...

Compare two datasets to find differences, added/removed rows, changed values. Use for data validation, ETL verification,...

Curate and clean training datasets for high-quality machine learning

Use this skill when designing, cleaning, deduplicating, or documenting datasets for model training and evaluation includ...

按唯一主键确定性比较两版行式数据，识别新增、删除、修改、未变化记录和字段级差异，适用于数据发布验收、回归核对和迁移结果检查。

Create, clean, and optimize datasets for LLM fine-tuning. Covers formats (Alpaca, ShareGPT, ChatML), synthetic data gene...

Use this when the user wants to generate, normalize, verify, deduplicate, or export training datasets for Codex, Antigra...

Generate evaluation datasets with adjustable difficulty levels from PDF documents for RAG system testing and benchmarkin...

Dataset Loader Creator - Auto-activating skill for ML Training. Triggers on: dataset loader creator, dataset loader crea...

Dataset versioning with DVC, HF Datasets processing patterns, data curation workflows, quality checks, and annotation pi...

> "Datasette is the fastest way to publish data online as an interactive,

Extracts key specifications from component datasheet PDFs for maker projects. Use when user shares a datasheet PDF URL,...

Create a DataSource note documenting a specific database, table, API endpoint, dataset, or data entity with schema, qual...

Tier 1 Component Skill - Creates or updates Dataverse schema components programmatically using the Dataverse Web API and...

Comprehensive data visualization toolkit for creating beautiful, mathematically elegant visualizations with D3.js, Chart...

Verify current date from system. Use when outputting dates, scheduling, or time-sensitive operations. Prevents knowledge...

Format dates and times in various formats, calculate date differences, and provide date-related information. Use this wh...

Analyze date range analyzer operations. Auto-activating skill for Data Analytics. Triggers on: date range analyzer, date...

Handle date and timezone conversions correctly in forms and displays. Use when working with: Date inputs, new Date(), fo...

Use when editing Planning Hubs, timelines, calendars, or any file with day-name + date combinations (Wed Nov 12), relati...

DAW-specific quirks, known issues, and workarounds for Logic Pro, Ableton Live, Pro Tools, Cubase, Reaper, FL Studio, Bi...

Parse models, migrations, or schema and generate an ERD diagram + DB documentation Arguments: (no arguments — auto-detec...

Query the STG Supabase database with natural language