All categories
Data & Analytics
Data analysis, BI, visualization, datasets, statistics, and ML workflows
- 12,625
- 527
Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.
Open in full browserBrowse data & analytics skills
Showing 1,441–1,464 of 12,625 skills
- AlgorithmsUse when researching algorithms, data structures, optimization, performance, or need modern alternatives to classic algorithmsVotes: 0GitHub stars: 2
- Aice Gpa CalculationCalculate GPA and total credits for Foreign Credential Evaluation (FCE) reports. Use when calculating course statistics, processing grade data, or validating GPA calculations in credential evaluation contexts.Votes: 0GitHub stars: 2
- Ai Ml Data ScienceEnd-to-end data science patterns (modern best practices): problem framing -> data -> EDA -> feature engineering (with feature stores) -> modelling -> evaluation -> reporting, plus SQL transformation (SQLMesh). Emphasizes MLOps integration, drift monitoring, and production-ready workflows.Votes: 0GitHub stars: 2
- XlsxComprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulasVotes: 0GitHub stars: 2
- Calculation SkillA skill for mathematical calculationsVotes: 0GitHub stars: 2
- Aeon 3This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.Votes: 0GitHub stars: 2
- Academic PerformanceAnalyze student GPA and academic performance, grade distributions, honor roll and dean's list students, at-risk students, course difficulty and pass/fail rates, instructor effectiveness and ratings, academic achievement by major or department, and grade comparisons. Use when user asks about grades, GPA, academic standing, course performance, or instructor evaluations.Votes: 0GitHub stars: 2
- A2a ProtocolLiteLLM-RS A2A Protocol Architecture. Covers Agent-to-Agent communication, JSON-RPC 2.0 messaging, multi-provider orchestration, agent registry, and task state management.Votes: 0GitHub stars: 2
- 06 Mofa Studio SettingsProvider settings and user preferences in MoFA Studio. Use when editing provider UI, saving preferences, or wiring API keys and defaults.Votes: 0GitHub stars: 2
- 学术文本英译中将英文学术文本（涵盖生物信息学、医学及人文社科）翻译为正式的中文论文语言，保持术语准确性和逻辑结构。Votes: 0GitHub stars: 2
- 使用Tensorflow Java 0 4 0进行Savedmodel预测针对TensorFlow Java 0.4.0版本，实现加载SavedModel模型，将三维double数组转换为Tensor并执行预测返回double数组的逻辑。Votes: 0GitHub stars: 2
- Tensorflow Java Gpu环境配置与故障排查提供在Windows环境下使用TensorFlow for Java进行GPU计算的完整配置指南，包括Maven依赖、代码示例、CUDA/cuDNN版本兼容性检查，以及针对JDK 17的DLL加载路径设置方案。Votes: 0GitHub stars: 2
- Pytorch文本分类键盘输入推理脚本生成生成用于PyTorch LSTM文本分类模型的推理代码，支持键盘输入、jieba分词、词汇表映射及情感标签输出。Votes: 0GitHub stars: 2
- 计算数据的平均数 标准差及P值用于计算给定数据集的平均数、标准差以及两组数据间的P值。当用户要求“无需过程”或“只需结果”时，仅输出最终数值。Votes: 0GitHub stars: 2
- Tensorflow 训练代码内存优化与修复针对TensorFlow训练代码进行内存泄漏修复，包括优化数据管道、添加每轮结束后的垃圾回收回调以及修正ModelCheckpoint配置。Votes: 0GitHub stars: 2
- Pytorch中文文本分类预测脚本编写编写用于加载词汇表、使用Jieba分词、构建TextDataset类以及执行LSTM模型预测的Python代码。Votes: 0GitHub stars: 2
- TransformersWork with state-of-the-art machine learning models for NLP, computer vision, audio, and multimodal tasks using HuggingFace Transformers. This skill should be used when fine-tuning pre-trained models, performing inference with pipelines, generating text, training sequence models, or working with BERT, GPT, T5, ViT, and other transformer architectures. Covers model loading, tokenization, training with Trainer API, text generation strategies, and task-specific patterns for classification, NER, Q...Votes: 0GitHub stars: 2
- Performance OptimizationApply systematic performance optimization techniques when writing or reviewing code. Use when optimizing hot paths, reducing latency, improving throughput, fixing performance regressions, or when the user mentions performance, optimization, speed, latency, throughput, profiling, or benchmarking.Votes: 0GitHub stars: 2
- Data VisualizationCreates effective data visualizations using various libraries and tools, with focus on clarity and insight communication. Trigger keywords: chart, graph, plot, visualization, dashboard, matplotlib, d3, plotly, visualization.Votes: 0GitHub stars: 2
- Mapping High Involvement Purchase JourneysResearch-intensive purchase mapping: build a customer decision journey map for a high-involvement purchase from buyer interviews and behavioral data.Votes: 0GitHub stars: 2
- Interpreting Bayesian And Frequentist Experiment ResultsRead PostHog experiment results under Bayesian or frequentist stats: win probability, credible intervals, p-values and what counts as significant.Votes: 0GitHub stars: 2
- Building Planned Journey Funnel VisualizationsBuild a planned journey funnel diagram that shows stakeholders how buyers flow through each stage, where drop-off happens and why.Votes: 0GitHub stars: 2
- Posthog Measurements For Goal BindingsStandardizes creating and debugging PostHog insights for Hamster goal measure bindings. Covers TrendsQuery vs HogQL, the measure binding contract (aggregated_value), math types, formulas, HogQL pitfalls, and the Composio API actions needed. Use when binding a PostHog metric to a goal, debugging a measure showing 0/null, or converting HogQL to TrendsQuery.Votes: 0GitHub stars: 2
- Goal Health ReviewGuides the weekly goal review meeting: compare goals vs initiatives, prioritize newly unblocked work, assign owners. Enforces the 'one weekly meeting' principle — 30 minutes of decisions, not 45 minutes of status. Use when running a weekly goal review, planning meeting, or direction review.Votes: 0GitHub stars: 2