Total 53,748 skills, Data Processing has 2766 skills
Showing 12 of 2766 skills
Use this skill when building budgets, conducting variance analysis, implementing rolling forecasts, or allocating costs. Triggers on FP&A, budgeting, variance analysis, rolling forecasts, cost allocation, headcount planning, department budgets, and any task requiring financial planning or budget management.
World-class data science skill for statistical modeling, experimentation, causal inference, and advanced analytics. Expertise in Python (NumPy, Pandas, Scikit-learn), R, SQL, statistical methods, A/B testing, time series, and business intelligence. Includes experiment design, feature engineering, model evaluation, and stakeholder communication. Use when designing experiments, building predictive models, performing causal analysis, or driving data-driven decisions.
A-share financial data toolkit. Provides scripts to obtain real-time A-share market quotes, financial indicators, share increases/reductions by directors, supervisors and senior executives, northbound capital flows, and macroeconomic data (LPR, CPI/PPI, PMI, social financing, M2). Used when real-time A-share market data is required to support investment analysis. All data sources are free and no API key is required.
Explain AQL queries and their results, and provide data insights. Use this whenever the user asks what a query does, wants to understand results, or needs to dig deeper into why a metric changed.
Identify and prioritize causal variants at GWAS loci using statistical fine-mapping and locus-to-gene predictions. Computes posterior probabilities for causal variants, links variants to genes via L2G predictions, annotates functional consequences, and suggests validation strategies. Use when asked to fine-map GWAS loci, prioritize causal variants, identify credible sets, or link GWAS signals to causal genes.
Optimizes ClickHouse queries for speed and efficiency. Helps with primary key design, sparse indexes, data skipping indexes (minmax, set, bloom filter, ngrambf_v1), partitioning strategies, projections, PREWHERE optimization, approximate functions, and query profiling with EXPLAIN. Use when writing ClickHouse queries, designing table schemas, analyzing slow queries, or implementing analytical aggregations. Works with columnar OLAP workloads.
亚马逊细分市场评论分析与消费者情感洞察。当用户提到细分市场评论分析、消费者情感、用户痛点、客户反馈洞察、评论主题分析、好评差评拆解、细分市场舆情挖掘、产品评论情感分析、niche market reviews, consumer sentiment, customer pain points, review topic analysis, positive/negative reviews, opinion mining, Jiimore data时触发此技能。即使用户未明确提及"细分市场评论"，只要其需求涉及分析亚马逊细分市场中的消费者评论或理解细分市场层面的客户情感，也应触发此技能。
Multi-signal pressure analysis on HTX USDT-M perpetuals — combines funding rate, OI, elite long/short ratio, recent liquidations, and basis into a unified pressure score with squeeze-risk verdict. Public, no API key required.
Import transactions from CSV, OFX, or QIF bank exports and deduplicate.
Build quick IRR/MOIC sensitivity tables for PE deal evaluation. Models returns across entry multiple, leverage, exit multiple, growth, and hold period scenarios. Use when sizing up a deal, stress-testing assumptions, or preparing IC returns exhibits. Triggers on "returns analysis", "IRR sensitivity", "MOIC table", "what's the return at", "model the returns", or "back of the envelope".
Build end-to-end ETL pipelines and analytics dashboards using Harvard Art Museums API data with Python, SQL, and Streamlit
>