Total 53,974 skills, Data Processing has 2767 skills
Showing 12 of 2767 skills
Analyze digital assets including cryptocurrency fundamentals, blockchain mechanics, DeFi protocols, and on-chain metrics. Use when the user asks about crypto investing, Bitcoin, Ethereum, staking yields, DeFi lending, impermanent loss, or on-chain valuation metrics. Also trigger when users mention 'blockchain', 'proof of stake', 'proof of work', 'smart contracts', 'NFTs', 'stablecoins', 'NVT ratio', 'TVL', 'crypto portfolio allocation', 'halving', or ask about risks and returns of cryptocurrency.
Compute and compare investment return metrics including TWR, MWR/IRR, CAGR, and annualized returns. Use when the user asks about portfolio performance calculation, comparing manager returns, linking sub-period returns, understanding why different return methods give different numbers, or converting returns across time periods. Also trigger when users mention 'how much did I make', 'annual return', 'compound growth', 'dollar-weighted vs time-weighted', 'what was my rate of return', 'geometric vs arithmetic mean', 'log returns', or ask about the effect of cash flows on reported returns.
Builds Geographically Weighted Regression (GWR) workflows in CARTO. Triggers when the user mentions GWR, geographically weighted regression, spatially varying relationships, local regression, local coefficients, spatial regression, "what drives X in different areas", "why do prices vary spatially", "local factors affecting Y", varying coefficients, coefficient maps, spatial non-stationarity, or wants to model how the relationship between a dependent variable and predictors changes across geography. Produces per-cell regression coefficients that reveal how predictor importance shifts from place to place.
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.
Act as a Renaissance Tech-level quantitative systems engineer. Build unified feature engines instead of isolated strategies, rigorously test predictive variables, and assemble scoring models.
Obtain securities and financial information such as JoinQuant A-share market quotes, historical K-lines, financial data, and indicator data; Use this when users mention JoinQuant, jqdata, jqdatasdk and need to obtain A-share data
Find insurance payments, total annual premiums, and compare to benchmarks.
通过 EHunt Temu 店铺查询（网关路由 `ehunt/temu/storeQuery`）按多维度筛选 Temu 店铺（店名/ID、国家站点、后台类目、全托管/半托管、总/周/月销量与销售额、评分、评论、粉丝、商品数、开店时间等）。当用户提到 EHunt Temu 店铺、Temu 店铺分析、Temu seller、Temu 店铺排行、Temu 半托管店铺、Temu 销售额、temu stores、Temu store query 时触发。即使用户未写 EHunt，只要在 Temu 上找店铺、筛店铺数据或分析店铺表现，也应触发此技能。
通过专利ID或公开号查询智慧芽专利数据库中的专利著录（书目）信息。当用户提到专利著录信息查询、专利书目信息、专利申请人查询、专利发明人查询、专利分类号、专利摘要获取、专利引用分析、专利优先权主张、专利申请引用、专利审查员信息、patent bibliographic data, inventor lookup, applicant lookup, patent classification, patent metadata, PatSnap, patent citations时触发此技能。即使用户未明确提及"著录信息"，只要其需求涉及通过专利ID或公开号查询特定专利的详细元数据，也应触发此技能。
MPSTATS Ozon 俄罗斯站 SKU 全量详情批量查询。一次最多传 100 个 Ozon 商品 ID，返回每个 SKU 的价格、折扣、Ozon Card 价、评分、评论数、库存、销量、销售额、潜在销售额/损失销售额、上架日期、图片等完整商品卡。当用户提到 Ozon 商品详情、Ozon SKU 详情、Ozon 价格/评分/销量/库存核对、批量 Ozon SKU 查询、竞品 Ozon 基础数据拉取、Ozon 竞品卡片、MPSTATS Ozon detail, Ozon SKU detail, Ozon product card, Ozon batch lookup, Russian marketplace product detail 时触发此技能。即使用户未明确说"MPSTATS"，只要意图是按 Ozon SKU 拉取全量商品卡数据，也应触发此技能。
Valuation methodology framework covering absolute (DCF / DDM / SOTP) and relative (PE-Band / PB-ROE / EV-EBITDA / PS) approaches — when to use each, pros/cons, common pitfalls, and practical application with Longbridge data. Triggers: "估值方法", "估值方法论", "DCF", "DDM", "SOTP", "PE估值", "EV/EBITDA", "绝对估值", "相对估值", "估值框架", "估值方法論", "絕對估值", "相對估值", "valuation methodology", "DCF model", "DDM", "SOTP", "PE band", "EV EBITDA", "absolute valuation", "relative valuation", "valuation framework".
Vehicle routing (VRP, TSP, PDP) with cuOpt — Python API only. Use when the user is building or solving routing in Python.