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.
flow-nexus-neural
This skill enables training and deploying neural networks in distributed E2B sandboxes. It supports multiple architectures (feedforward, LSTM, GAN, transformer) and offers a template marketplace. Includes federated learning for privacy-sensitive data and distributed training for large models.
fda-database
Provides a Python wrapper for the openFDA API, enabling structured queries for drug adverse events, device recalls, product labeling, and substance data. Includes built-in rate limiting, caching, and examples for common regulatory analysis workflows.
nl-router
A sophisticated natural language router that intelligently maps user requests to appropriate skills and workflows with clear confidence scoring and structured routing patterns.
parse-git-status
Parses raw git status output into structured JSON data, extracting branch info, tracking status, and categorizing files by change type (staged, modified, untracked). Useful for automating git workflow checks and pre-commit validation.
bigquery
A Rust-based CLI tool for Google BigQuery operations that replaces the Python bq CLI. Provides query execution with cost estimation, data ingestion via streaming or bulk load, table management, and template system. Includes MCP server for AI-assisted querying and LSP for editor integration.
lancer
A CLI tool for LanceDB that handles document ingestion, semantic search, and table management with multi-modal support for text and images. Provides MCP server integration for Claude Desktop, multiple embedding model options, and metadata filtering capabilities.
AgentDB Vector Search
Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases.
ml-pipeline-workflow
Build end-to-end MLOps pipelines from data preparation through model training, validation, and production deployment. Use when creating ML pipelines, implementing MLOps practices, or automating model training and deployment workflows.
Pair Programming
AI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with truth-score verification.
single-cell-multi-omics-integration
This skill provides a structured cheat sheet for integrating single-cell multi-omics data using five different computational methods. It outlines specific steps for MOFA, GLUE, SIMBA, TOSICA, and StaVIA workflows with clear data preparation, training, and inspection phases. The instructions reference actual notebook files and include dependency notes for each method.
ai-llm-engineering
Operational skill hub for LLM system architecture, evaluation, deployment, and optimization (modern production standards). Links to specialized skills for prompts, RAG, agents, and safety. Integrates recent advances: PEFT/LoRA fine-tuning, hybrid RAG handoff (see dedicated skill), vLLM 24x throughput, multi-layered security (90%+ bypass for single-layer), automated drift detection (18-second response), and CI/CD-aligned evaluation.
moai-formats-data
A Python library focused on data format optimization, featuring a custom TOON encoding for 40-60% token reduction in LLM contexts, fast JSON/YAML processing via orjson, and schema-based data validation. Includes practical examples for common data handling tasks and warnings for anti-patterns.
moai-ai-nano-banana
Integrates Google's Gemini 3 Pro image generation API with CLI tools for batch image creation. Supports multiple resolutions (1K-4K), aspect ratios, style prefixes, and concurrent processing. Includes smart retry logic and config file support for automated workflows.
nlp-engineer
A comprehensive NLP engineering skill with excellent coverage of modern NLP tasks, clear workflows, and production-focused checklists for building robust multilingual systems.
dbt-artifacts
Monitor dbt execution using the dbt Artifacts package. Use this skill when you need to track test and model execution history, analyze run patterns over time, monitor data quality metrics, or enable programmatic access to dbt execution metadata across any dbt version or platform.
dbt-architecture
This skill transforms Claude into a dbt architecture consultant focused on implementing medallion architecture patterns. It provides concrete folder structures, naming conventions, configuration strategies, and decision trees for organizing dbt projects. The guidance includes specific SQL templates, layer-specific rules, and practical examples for bronze/silver/gold layers.
web-frameworks
This skill provides a guide for building web apps using Next.js, Turborepo, and RemixIcon. It covers setup, configuration, and integration patterns for single apps and monorepos. The documentation includes code examples for common tasks like routing, data fetching, and icon usage.
regulatory-templates-gate1
A specialized skill for mapping template placeholders to backend data sources in financial regulatory reporting. It enforces strict naming conventions (snake_case) and data source prefixes to ensure audit trail compliance. The skill focuses on interactive validation of field mappings with confidence thresholds.
reading-dss-boundary-data
Specializes in reading HEC-DSS files (V6/V7) to extract boundary condition data for hydraulic modeling. Automates catalog reading and time series extraction, converting DSS data to pandas DataFrames with metadata. Requires Java JVM and pyjnius, uses lazy loading to minimize overhead until first DSS operation.
hera
A Python-based tool for querying Hera log details with filters for space ID, store ID, tail name, and time range. Provides structured API access to log data with parameter validation and error handling. Useful for programmatic log analysis in specific infrastructure environments.
Claudeisms Operational Guidelines
This skill enforces a strict set of operational protocols for AI task execution, including sequential processing, minimal responses, and safety confirmations for destructive operations. It prevents common AI pitfalls like making assumptions about dates, providing inaccurate time estimates, or performing unsafe operations without user confirmation.
defense-in-depth
This skill teaches a four-layer validation pattern for catching invalid data at multiple system boundaries. It provides concrete TypeScript examples for entry validation, business logic checks, environment guards, and debug instrumentation. The approach makes certain bugs structurally impossible by validating at every data flow layer.
pymc-bayesian-modeling
This skill provides a detailed guide for Bayesian modeling using PyMC, covering the full workflow from data preparation to model validation. It includes practical code examples for building hierarchical models, MCMC sampling, variational inference, and model comparison techniques like LOO/WAIC. The documentation addresses common pitfalls like divergences and offers reparameterization solutions.
github-release-management
Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management