agent

当用户询问金融数据（"BTC 价格"、"NVDA 市盈率"）、市场分析、股票或加密货币研究、量化策略、回测（"回测一个动量策略"）、资产或投资组合追踪，或帮助将投资想法转化为 Alva 上的实时策略、仪表板和分析时使用。依托 250+ 金融数据源，涵盖加密货币、股票、宏观、链上和社交数据，以及云端分析和回测能力。当用户询问 Alva 平台功能时也使用此技能。

Expert data analysis covering SQL querying, data visualization, statistical analysis, business reporting, and data storytelling. Use when writing SQL queries, building dashboards, performing cohort or funnel analysis, running hypothesis tests, or presenting data-driven recommendations to stakeholders.

Guided statistical analysis with test selection and reporting. Use when you need help choosing appropriate tests for your data, assumption checking, power…

Automated LLM-driven hypothesis generation and testing on tabular datasets. Use when you want to systematically explore hypotheses about patterns in empirical…

Expert marketing analytics covering campaign analysis, attribution modeling, marketing mix modeling, ROI measurement, and performance reporting. Use when analyzing campaign ROI, comparing attribution models, optimizing marketing budget allocation, building executive dashboards, or running A/B test statistical analysis.

Therapeutics Data Commons. AI-ready drug discovery datasets (ADME, toxicity, DTI), benchmarks, scaffold splits, molecular oracles, for therapeutic ML and…

Diagnose and fix bugs with root-cause analysis and verification. Use when you have a concrete issue report, failing behavior, runtime error, or test regression…

Unified Kaggle skill. Use when the user mentions kaggle, kaggle.com, Kaggle competitions, datasets, models, notebooks, GPUs, TPUs, hackathons, writeups,…

Expert people analytics covering workforce analytics, HR metrics, predictive modeling, employee insights, and data-driven HR decisions. Use when building turnover prediction models, analyzing engagement surveys, running pay equity regressions, designing people dashboards, scoring flight risk, or advising HR leaders with workforce data.

Expert analytics engineering covering data modeling, dbt development, data transformation, and semantic layer management. Use when building dbt models, designing star schemas, writing staging or mart SQL, configuring data tests, defining semantic-layer metrics, or optimizing warehouse query performance.

Triage Antithesis test reports to understand what happened in a run: look up runs, check status, investigate failed properties (assertions), view metadata, download logs, inspect findings, and examine environmental details. Load after a run completes or when investigating a failure.