Marketplace
Find the right skill for the job.
Browse the full catalog through outcome-first channels, technical facets, rating filters, and server-side pagination built for a large public marketplace.
polars
This skill provides comprehensive guidance for using Polars, a high-performance DataFrame library. It covers core concepts like lazy evaluation and expressions, common operations, I/O best practices, and performance optimization. The documentation includes practical examples for data filtering, grouping, and file handling with specific code snippets.
plotly
This skill provides comprehensive guidance for using Plotly, a Python library for creating interactive data visualizations. It covers both high-level Plotly Express for quick charts and low-level graph objects for custom plots. The documentation includes 40+ chart types, export options, and integration with Dash for web apps.
xlsx
This skill provides tools for creating, editing, and analyzing Excel files with a strong emphasis on formula usage over hardcoding. It includes specific workflows for financial modeling with color coding standards, number formatting rules, and mandatory formula recalculation via LibreOffice. The documentation clearly distinguishes between pandas for data analysis and openpyxl for Excel-specific features.
xlsx
This skill enables Claude to create, edit, and analyze Excel files with proper formulas and formatting. It provides clear workflows for financial modeling with color coding standards, prevents hardcoding by enforcing formula usage, and includes a recalculation script to verify formula correctness. The documentation covers common pitfalls and verification steps.
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
advanced-evaluation
This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.
data-viz-plots
This skill provides ready-to-use Python code templates for creating publication-quality scientific plots using matplotlib and seaborn. It covers common visualization types like scatter plots, heatmaps, violin plots, and volcano plots with specific styling recommendations for academic papers.
scanpy
This skill provides a complete workflow for single-cell RNA-seq analysis using Scanpy, covering data loading, QC, normalization, dimensionality reduction, clustering, and visualization. It includes practical code examples for common tasks and publication-quality figure customization.
github-workflow-automation
This skill provides GitHub Actions automation with AI swarm coordination. It generates and optimizes CI/CD pipelines, manages pull requests and releases, and coordinates multi-repo workflows. The tool integrates with GitHub CLI and offers eight specialized modes for different GitHub automation tasks.
senior-data-engineer
World-class data engineering skill for building scalable data pipelines, ETL/ELT systems, and data infrastructure. Expertise in Python, SQL, Spark, Airflow, dbt, Kafka, and modern data stack. Includes data modeling, pipeline orchestration, data quality, and DataOps. Use when designing data architectures, building data pipelines, optimizing data workflows, or implementing data governance.
reasoningbank-intelligence
This skill implements an adaptive learning system for AI agents using ReasoningBank. It enables agents to record experiences, recognize patterns, optimize strategies, and continuously improve through meta-learning. The tool integrates with AgentDB for persistence and supports vector search for pattern matching.
matplotlib
This skill provides detailed guidance for using Matplotlib, covering both pyplot and object-oriented interfaces. It includes practical examples for common plot types, subplot layouts, customization, and troubleshooting. The documentation addresses specific issues like date formatting, legend placement, and 3D visualization problems with concrete solutions.
ai-email-pipeline
This skill implements an AI-driven email processing pipeline where LLMs handle all intent parsing and tool invocation, avoiding regex or state machines. It emphasizes conversation persistence, raw attachment passing to models, and learning from real bugs like 'no I mean...' misinterpretations.
agentdb-learning
A comprehensive reinforcement learning toolkit for AI agents offering 9 algorithms with WASM acceleration, practical CLI/API interfaces, and clear training workflows for building self-improving autonomous systems.
This skill provides Python code examples for common PDF operations including text extraction, table parsing, merging/splitting documents, and creating new PDFs. It covers multiple libraries like pypdf, pdfplumber, and reportlab with clear code snippets for each task.
backend-migration-standards
Provides concrete guidelines for creating database migrations with reversible changes, proper naming conventions, and zero-downtime deployment strategies. Includes specific patterns for adding/removing columns, index management, and separating schema from data migrations. Offers framework-specific examples for Alembic, Rails, and Sequelize.
agentdb-vector-search
Provides vector search capabilities for AgentDB with HNSW indexing and quantization. Supports CLI operations, API integration, and MCP server for Claude. Includes benchmarks showing 150x-12,500x speed improvements over traditional methods.
github-multi-repo
This skill orchestrates changes across multiple GitHub repositories using AI swarm agents. It synchronizes package versions, runs cross-repo tests, and creates coordinated pull requests. The tool helps teams manage dependencies and deployments across distributed codebases with automation.
zarr-python
Provides comprehensive guidance for using Zarr to store large N-dimensional arrays with chunking and compression. Covers array creation, cloud storage integration, performance optimization, and common patterns for scientific workflows. Includes practical examples for S3/GCS, Dask integration, and troubleshooting slow performance.
z-card-image
生成配图、封面图、卡片图、文字海报、公众号文章封面图、微信公众号头图、X 风格帖子分享图、帖子长图、社媒帖子长图。适用于帖子类型数据、post data、social posts、tweet/thread、转发推文、转发帖子、小绿书配图、图片封面、card image。
bdi-mental-states
A sophisticated skill for implementing BDI cognitive architectures, enabling RDF-to-mental-state transformations with strong ontological foundations and neuro-symbolic integration patterns.
swarm-orchestration
This skill enables coordination of multiple AI agents for parallel task execution using agentic-flow. It supports mesh, hierarchical, and adaptive topologies with features like load balancing, fault tolerance, and shared memory. Useful for complex projects requiring distributed AI workforces.
scikit-learn
This skill provides detailed guidance for using scikit-learn, covering classification, regression, clustering, and preprocessing. It includes practical code examples, algorithm selection tables, and warnings about common mistakes like data leakage. The documentation helps users build ML pipelines and evaluate models effectively.
pytorch-lightning
Provides structured templates and best practices for PyTorch Lightning development. Covers LightningModule organization, Trainer configuration, distributed training strategies, and common debugging patterns. Includes ready-to-use code snippets for data pipelines, logging, and multi-GPU setups.