Найдите подходящую возможность для вашего агента.
Use PROACTIVELY when users need guaranteed schema compliance or validated tool inputs from Anthropic's structured outputs feature. Expert advisor for choosing between JSON outputs (data extraction/formatting) and strict tool use (agentic workflows). Analyzes requirements, explains trade-offs, and delegates to specialized implementation skills. Not for simple text responses or unstructured outputs.
Create, manipulate, and analyze geometries using geometry classes and geometry operators. Use for spatial calculations, geometry creation, buffering, intersections, unions, and mesh operations.
Create advanced cartographic symbols using CIM (Cartographic Information Model). Use for complex multi-layer symbols, animated markers, custom line patterns, and data-driven symbology.
Parse and analyze personal financial transaction CSV exports to calculate account totals and generate detailed breakdowns. Use when the user asks to analyze transaction data, generate financial summaries, calculate account balances, or review spending from CSV exports. Supports account grouping (Galicia, Mercado Pago, Quiena, LLC/Relay, HSBC, Crypto), automatic internal transfer detection, and detailed transaction listings.
Configure and manage data quality tests, profiling, alerts, and incidents in OpenMetadata. Use when setting up quality tests, configuring profiler workflows, creating observability alerts, or triaging data quality incidents.
Data warehouse (大数据/数仓) ops skill for designing and operating analytical data platforms. Use for tasks like defining source-of-truth, building ETL/ELT pipelines, dimensional modeling (star schema), data quality checks, partitioning strategies, cost/performance tuning, governance, lineage, and SLA monitoring.
Shipping Data Analysis - Brock's Reusable Prompt v4.0 Analyzes any shipping dataset with FirstMile-branded deliverables, normalized address grouping, and conditional advanced analytics based on available data fields. Use when: (1) Prospect provides shipping data (PLD, exports, etc.) (2) "analyze shipping data" or "shipping analysis" (3) "run Brock's prompt" or "data analysis v4.0" (4) Need DIM exposure, zone distribution, or cost intelligence reports (5) Creating prospect-facing shipping profile analysis Triggers on: "shipping analysis", "analyze shipping", "PLD analysis", "Brock's prompt", "data analysis v4.0", "shipping profile", "DIM exposure", "zone distribution"
Work with temporal data using TimeSlider, TimeExtent, and time-aware layers. Use for animating data over time, filtering by date ranges, and visualizing temporal patterns.
Unified markdown and OpenCode component specialist providing document quality enforcement (structure, style), content optimization for AI assistants, complete component creation workflows (skills, agents, commands with scaffolding, validation, packaging), ASCII flowchart creation for visualizing complex workflows, and install guide creation for MCP servers, plugins, and tools.
Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets. Apply when users need to work with large CSV/HDF5/Arrow/Parquet files, perform fast statistics on massive datasets, create visualizations of big data, or build ML pipelines that do not fit in memory.
Generate and execute SQL queries against the civitai_records PostgreSQL database to analyze video performance on Civitai. Use when users ask about: video engagement metrics (likes, hearts, comments), content performance analysis, tag/theme analysis, quality scores, weekly reports, comparing videos, content recommendations, trend analysis, or any Civitai data queries. Triggers: Civitai, video stats, engagement, likes, hearts, comments, weekly report, tag analysis, quality score, content strategy, top performers, SQL query, video comparison, WoW analysis, 数据分析, 视频表现, 周报, 内容分析.
Create custom layer types with WebGL rendering, custom tile layers, and blend layers. Use for advanced visualizations and custom data sources.
Perform comprehensive data analysis, statistical modeling, and data visualization by writing and executing self-contained Python scripts. Use when you need to analyze datasets, perform statistical tests, create visualizations, or build predictive models with reproducible, code-based workflows.
Automated LLM-driven hypothesis generation and testing on tabular datasets. Use when you want to systematically explore hypotheses about patterns in empirical data (e.g., deception detection, content analysis). Combines literature insights with data-driven hypothesis testing. For manual hypothesis formulation use hypothesis-generation; for creative ideation use scientific-brainstorming.
Fast Python framework for building interactive web apps, dashboards, and data visualizations without HTML/CSS/JavaScript. Use when user wants to create data apps, ML demos, dashboards, data exploration tools, or interactive visualizations. Transforms Python scripts into web apps in minutes with automatic UI updates.
Comprehensive toolkit for creating, analyzing, and visualizing complex networks and graphs in Python. Use when working with network/graph data structures, analyzing relationships between entities, computing graph algorithms (shortest paths, centrality, clustering), detecting communities, generating synthetic networks, or visualizing network topologies. Applicable to social networks, biological networks, transportation systems, citation networks, and any domain involving pairwise relationships.
Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing models, or implementing explainable AI. Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box model.
Perform comprehensive data analysis, statistical modeling, and data visualization by writing and executing self-contained Python scripts. Use when you need to analyze datasets, perform statistical tests, create visualizations, or build predictive models with reproducible, code-based workflows.
Implement WrenAI-inspired three-tab architecture (Answer/View SQL/Chart) for text-to-SQL applications. Use when building query response interfaces with data tables, SQL display, and chart visualizations. Includes patterns for multi-response threads, chart pinning to dashboard, context drift detection and handling, Elasticsearch-powered search and discovery, performance optimization with virtualization, and data caching strategies. Designed for React with Salt DS components, Apache ECharts, Elasticsearch, and localStorage state management.
Style and render geographic data with renderers, symbols, and visual variables. Use for creating thematic maps, heatmaps, class breaks, unique values, labels, and 3D visualization.
