Discover and use skill skills to extend Claude's capabilities
869 Skill Skills Available
根据用户描述智能选择最合适的图表类型并生成 Mermaid 代码。支持流程图、时序图、类图、ER图、甘特图、状态图等全部类型，配色鲜艳美观。
Time-boxed technical investigation with structured output. Use for feasibility studies, architecture exploration, integration assessment, performance analysis, or risk evaluation. Creates spike tasks in ohno, enforces time-boxing, generates spike reports, and creates actionable follow-up tasks. Triggers on "spike on X", "investigate whether we can", "how hard would it be to", "what's the best approach for", or any exploratory technical question needing bounded research.
Comprehensive multi-dimensional skill reviews across structure, content, quality, usability, and integration. Task-based operations with automated validation, manual assessment, scoring rubrics, and improvement recommendations. Use when reviewing skills, ensuring quality, validating production readiness, identifying improvements, or conducting quality assurance.
Use this skill when you want to learn about generating high-quality insights that will be automatically captured. Insights using the "★ Insight" format are automatically extracted by hooks - no manual saving required.
レポートコンパイルエージェント - 分析結果のMarkdownファイルを統合HTMLレポートに変換。/compile-report [出力パス] で呼び出し。
Master color management and visual styling with Colorcet. Use this skill when selecting appropriate colormaps, creating accessible and colorblind-friendly visualizations, applying consistent themes, or customizing plot aesthetics with perceptually uniform color palettes.
Compact Plotly visualization patterns. Express for quick plots, Graph Objects for control.
对CSV/Excel数据进行描述性统计分析。当用户需要"统计分析"、"数据分布"、"描述统计"、"查看数据特征"、"异常值检测"、"数据探索"或请求分析数值数据时使用此skill。
Systematic comparison of segments, cohorts, or time periods - ensure fair apples-to-apples comparisons, identify meaningful differences, explain WHY differences exist
AI agent creates structured implementation plans with task breakdown, dependency mapping, risk assessment, and file-level detail. Use when planning features, projects, or complex implementations.
GraphDB可視化エージェント - RyuGraphデータベースの内容をMermaid/DOT/HTML形式で可視化。/visualize-graph [出力パス] で呼び出し。
全面的电子表格创建、编辑和分析，支持公式、格式设置、数据分析和可视化。当需要处理电子表格（.xlsx, .xlsm, .csv, .tsv 等）以进行以下操作时使用：(1) 创建带有公式和格式的新电子表格，(2) 读取或分析数据，(3) 在保留公式的同时修改现有电子表格，(4) 电子表格中的数据分析和可视化，或 (5) 重新计算公式
Generate production-ready forecasting experiments with StatsForecast and TimeGPT. Use when setting up model benchmarking or cross-validation. Trigger with 'scaffold experiment' or 'compare models'.
Generate comprehensive markdown benchmark reports from forecast accuracy metrics with model comparisons, statistical analysis, and regression detection. Use when analyzing baseline performance, comparing forecast models, or validating model quality. Trigger with 'generate benchmark report', 'analyze forecast metrics', or 'create performance summary'.
Research and summarize Nixtla ecosystem updates and time-series forecasting content from the web and GitHub. Use when gathering release notes, recent changes, or best-practice references. Trigger with \"Nixtla updates\", \"what's new with TimeGPT\", or \"find time-series papers\".
Analyze Nixtla baseline forecasting results (sMAPE/MASE on M4 or other
[UI/UX] Visualizes user flows and screen transitions as ASCII diagrams. Represents navigation flows, user journeys, and screen-to-screen paths. Use when requesting 'flow diagram', 'user journey visualization', or 'navigation flow'.
Analyze Nixtla baseline forecasting results (sMAPE/MASE on M4 or other
Analyze and explain TimeGPT forecast results in plain English. Generates
Statistical tests for time series stationarity (ADF, KPSS, PP tests)
Comprehensive Generalized Linear Model analytics for regression and classification
全方位的試算表建立、編輯和分析功能，支援公式、格式化、資料分析和視覺化。當 Claude 需要處理試算表（.xlsx、.xlsm、.csv、.tsv 等）時使用，包括：(1) 建立包含公式和格式的新試算表、(2) 讀取或分析資料、(3) 修改現有試算表同時保留公式、(4) 試算表中的資料分析和視覺化，或 (5) 重新計算公式
Draft the results section from figures and their captions. Builds a coherent narrative from visual evidence. Use when the user types /write_results, when figures exist with captions, or after methods section is complete.
Create publication-quality scientific figures with matplotlib, seaborn, and plotly. Includes multi-panel layouts, error bars, significance markers, colorblind-safe palettes, and journal-specific export (PDF/EPS/TIFF). Use when creating figures for manuscripts, presentations, or any research visualization.
Test at extremes (1000x bigger/smaller, instant/year-long) to expose fundamental truths hidden at normal scales
Information gathering utilities (analytics, research, content analysis) (general)
Search and list Danmarks Statistik tables by subject or keyword. Use when user needs to find specific tables or browse tables within a subject area.
Training monitoring dashboard setup with TensorBoard and Weights & Biases (WandB) including real-time metrics tracking, experiment comparison, hyperparameter visualization, and integration patterns. Use when setting up training monitoring, tracking experiments, visualizing metrics, comparing model runs, or when user mentions TensorBoard, WandB, training metrics, experiment tracking, or monitoring dashboard.
Synthesize multiple sentiment analyses to identify market trends, gaps, opportunities, and predict likely hits. Cross-analyzes patterns to find underserved markets and highlight unique innovations.
Execute numerical calculations and mathematical computations using Julia. Use this skill for matrix operations, linear algebra, numerical integration, optimization, statistics, and scientific computing tasks.
