Data & Analytics

Optimizes Snowflake SQL query performance from provided query text. Use when optimizing Snowflake SQL for: (1) User provides or pastes a SQL query and asks to optimize, tune, or improve it (2) Task mentions "slow query", "make faster", "improve performance", "optimize SQL", or "query tuning" (3) Reviewing SQL for performance anti-patterns (function on filter column, implicit joins, etc.) (4) User asks why a query is slow or how to speed it up

Optimizes Snowflake query performance using query ID from history. Use when optimizing Snowflake queries for: (1) User provides a Snowflake query_id (UUID format) to analyze or optimize (2) Task mentions "slow query", "optimize", "query history", or "query profile" with a query ID (3) Analyzing query performance metrics - bytes scanned, spillage, partition pruning (4) User references a previously run query that needs optimization Fetches query profile, identifies bottlenecks, returns optimize...

Develops and troubleshoots dbt incremental models. Use when working with incremental materialization for: (1) Creating new incremental models (choosing strategy, unique_key, partition) (2) Task mentions "incremental", "append", "merge", "upsert", or "late arriving data" (3) Troubleshooting incremental failures (merge errors, partition pruning, schema drift) (4) Optimizing incremental performance or deciding table vs incremental Guides through strategy selection, handles common incremental got...

Data: data engineering, analytics, ETL, QA, testing. Triggers: data pipeline, etl, data warehouse, analytics, dashboard, metrics, kpi, testing, test automation, qa, quality assurance, ci/cd testing, data science.

Building and training neural networks with PyTorch. Use when implementing deep learning models, training loops, data pipelines, model optimization with torch.compile, distributed training, or deploying PyTorch models.

This skill should be used when the user asks to "get Census data", "query American Community Survey", "find ACS data", "get population by state", "query Decennial Census", "find Census variables", "get median income data", "download demographic data", "Census API query", "get housing data from Census", or mentions US Census Bureau data (demographics, income, poverty, education, housing, population estimates, etc.).

def plot_hist(da_observations, da_forecast, station_name, rp=None, leadtimes=None): if leadtimes is None: leadtime = da_forecast.leadtime.values fig, ax = plt.subplots() for leadtime in leadtimes: observations, forecast = utils.get_same_obs_and_forecast(da_observations, da_forecast, leadtime) rank = utils.get_rank(observations.values, forecast.values) ax.hist(rank, histtype='step', label=int(leadtime), bins=np.arange(0.5, max(rank)+1.5, 1), alpha=0.8) ax.legend(loc=9, title="Lead time (days)"...

def plot_hist(da_observations, da_forecast, station_name, rp=None, leadtimes=None): if leadtimes is None: leadtime = da_forecast.leadtime.values fig, ax = plt.subplots() for leadtime in leadtimes: observations, forecast = utils.get_same_obs_and_forecast(da_observations, da_forecast, leadtime) rank = utils.get_rank(observations.values, forecast.values) ax.hist(rank, histtype='step', label=int(leadtime), bins=np.arange(0.5, max(rank)+1.5, 1), alpha=0.8) ax.legend(loc=9, title="Lead time (days)"...

start = '2001-01-01' end = '2001-10-31' version = 2 rf_list_slice = da_glofas_reforecast_interp[version].sel(time=slice(start,end)) ra_slice = da_glofas_reanalysis[version].sel(time=slice(start, end)) rf_list_slice.mean(axis=1).plot.line( x='time', add_legend=True) ra_slice.plot.line(label='Historical', c='k') plt.show() ``` We'll compute forecast skill using the ```xskillscore``` library and focus on the CRPS (continuous ranked probability score) value, which is similar to the mean absolute ...

This notebook explores the Ranked Probability Skill Score (RPSS) for IRI's seasonal forecast. In the end results were not really used. Interactive tool several skill measurements: https://iri.columbia.edu/our-expertise/climate/forecasts/verification/ Data description RPSS: http://iridl.ldeo.columbia.edu/maproom/Global/Forecasts/skill_precip_seasonal.html Data files RPSS: http://iridl.ldeo.columbia.edu/home/.jingyuan/.NMME_seasonal_hindcast_verification/.monthly_RPSS_seasonal_hindcast_precip_E...

Track and analyze US government shutdown liquidity impacts by monitoring TGA (Treasury General Account), bank reserves, EFFR, and SOFR data from FRED API. Use when user wants to (1) analyze current or past government shutdown effects on financial markets, (2) track liquidity conditions during fiscal policy disruptions, (3) assess "stealth tightening" effects, (4) compare shutdown episodes across different monetary policy regimes (QE vs QT), or (5) generate liquidity stress reports with histor...

Instructions for fetching current weather temperature data for Karachi, Pakistan from wttr.in API

追踪 GitHub 话题下的热门项目趋势，AI 智能分析，每日趋势报告。

Analyzes stock data and generates technical signals using Yahoo Finance. Use when the user asks for analysis of a specific stock ticker using this specific tool, or asks for "yahoo stock analysis" or mentions "get_info" or "signal" scripts. Provides RSI, MACD, MA, and simple trend signals.

Fetches AI news from smol.ai RSS and generates structured markdown with intelligent summarization and categorization. Optionally creates beautiful HTML webpages with Apple-style themes and shareable card images. Use when user asks about AI news, daily tech updates, or wants news organized by date or category.

Design ETL/ELT pipelines with proper orchestration, error handling, and monitoring. Use when building data pipelines, designing data workflows, or implementing data transformations.

Implement data quality checks, validation rules, and monitoring. Use when ensuring data quality, validating data pipelines, or implementing data governance.

Generate comprehensive SDLC reports including iteration status, metrics dashboards, and executive summaries.

Facilitate data-driven technical decisions using embedded decision matrices and trade-off analysis.

Generate executive-ready performance summaries with insights and recommendations.

Orchestrate marketing data collection, transformation, and reporting workflows.

Synthesize audience insights from multiple data sources into unified personas and segments.

Reverse-engineer voice profiles from sample content by analyzing writing patterns.

Copilot agent that assists with machine learning model development, training, evaluation, deployment, and MLOps Trigger terms: machine learning, ML, AI, model training, MLOps, model deployment, feature engineering, model evaluation, neural network, deep learning Use when: User requests involve ai ml engineer tasks.