Total 50,401 skills, Data Processing has 2557 skills
Showing 12 of 2557 skills
Fit Bayesian regression models with PyMC using the Hogg approach — start simple, diagnose problems, upgrade the likelihood. Use when the user needs regression with proper uncertainty quantification, heteroscedastic errors, outlier robustness, or model comparison. Covers Normal, Student-t, and GLM likelihoods with ArviZ diagnostics and LOO-CV.
Build end-to-end ETL pipelines and analytics dashboards using Harvard Art Museums API data with Python, SQL, and Streamlit
A股数据：行情、财务、股东、资金流、K线、概念板块、龙虎榜、市场异动。 当用户查询沪深北 A 股时使用（例如：603186 华正新材、300476 胜宏科技、000001 平安银行、龙虎榜、北向资金）。
End-to-end data engineering pipeline for Harvard Art Museums API with ETL, SQL analytics, and Streamlit visualization
Build end-to-end ETL pipelines and analytics dashboards using the Harvard Art Museums API with Python, SQL, and Streamlit
Reconciliation Report Analysis Expert - Parses ONLY local Settlement Detail report files (SETTLEMENT_DETAIL_*.csv / .xlsx) for settlement amount validation, fee analysis, and reconciliation knowledge Q&A. Does NOT support Transaction Detail or Settlement Summary reports. Triggers: settlement detail parsing, settlement amount validation, fee analysis, fee model, reconciliation knowledge, interchangeFee, schemeFee, fee rules, settlement, attribution.
Understands the Metabase Database Metadata Format — a YAML-based on-disk representation of databases, tables, and fields synced from a Metabase instance. Use when the user needs to read, edit, or understand metadata files produced by `@metabase/database-metadata`, or when reasoning about a project's schema (columns, types, FK relationships) through the `.metadata/databases` folder.
Review closed trades, partial exits, and monthly trade aggregates for process adherence, risk discipline, execution quality, and evidence-based trading behavior patterns. Use after trader-memory-core and signal-postmortem have produced records, or when the user asks for a post-trade coach, risk-manager style review, rule-adherence review, next-session operating rules, or psychology-aware trading behavior feedback. This skill does not provide buy/sell advice, therapy, or broker execution.
Find incomplete records, normalize field values in bulk, dedupe with `hubspot objects merge`, and audit custom properties. Builds on `bulk-operations` for JSONL piping and dry-run/digest/confirm.
Vendor-neutral skill to check a KPI dictionary for conflicting definitions, grain mismatches, and missing ownership.
Complete Guide to QMT (Xuntou High-Speed Strategy Trading System) Python Strategy Development. Covers strategy writing, backtesting, live trading, API references, and code examples. Use this skill when developing QMT quantitative strategies or querying QMT APIs.
AKShare is an open-source financial data interface library that provides full-category financial data including stocks, futures, options, funds, foreign exchange, bonds, indices, and cryptocurrencies; it is used when users need to obtain various financial market data