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.
cloudflare-workers-ai
Run LLMs and AI models on Cloudflare's GPU network with Workers AI. Includes Llama 4, Gemma 3, Mistral 3.1, Flux images, BGE embeddings, streaming, and AI Gateway. Handles 2025 breaking changes. Prevents 7 documented errors. Use when: implementing LLM inference, images, RAG, or troubleshooting AI_ERROR, rate limits, max_tokens, BGE pooling, context window, neuron billing, Miniflare AI binding, NSFW filter, num_steps.
frontend-dev-guidelines
Provides concrete implementation patterns for modern React/TypeScript apps using Suspense, lazy loading, TanStack Query, and MUI v7. Includes checklists, import aliases, file organization rules, and working code examples for components, data fetching, forms, and routing.
BrightData
A progressive web scraping skill that attempts four methods in sequence: built-in WebFetch, curl with headers, browser automation, and finally a paid Bright Data service. It handles bot detection and JavaScript-heavy sites by escalating through increasingly capable tiers.
data-modeling
A comprehensive and well-structured data modeling guide covering essential concepts from ER modeling and normalization to NoSQL patterns and schema evolution strategies.
torch-geometric
This skill provides comprehensive access to PyTorch Geometric for graph neural network development. It covers installation, graph creation, dataset loading, model building, training loops, and benchmarking utilities. The documentation includes practical code examples for common GNN tasks like node classification and molecular property prediction.
geopandas
This Skill provides comprehensive documentation for using GeoPandas, a Python library for geospatial data analysis. It covers installation, core concepts, common operations, and visualization with practical code examples. The documentation includes detailed sections on data structures, I/O operations, CRS management, spatial joins, and map creation.
pysam
Genomic file toolkit. Read/write SAM/BAM/CRAM alignments, VCF/BCF variants, FASTA/FASTQ sequences, extract regions, calculate coverage, for NGS data processing pipelines.
Recon
This skill performs infrastructure reconnaissance including domain, IP, and network analysis. It combines passive data gathering with authorized active scanning to map attack surfaces. The skill clearly distinguishes between passive and active techniques with strict authorization requirements. It integrates with other security skills like OSINT and web assessment for complete security workflows.
tanstack-query
Provides detailed implementation patterns for TanStack Query v5 including breaking changes, client setup with error handling, SSR configuration for Next.js, and integration with React Server Components. Covers practical migration guidance and production defaults.
prompt-lookup
Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.
TanStack Table
Build headless data tables with TanStack Table v8. Server-side pagination, filtering, sorting, and virtualization for Cloudflare Workers + D1. Prevents 12 documented errors. Use when building tables with large datasets, coordinating with TanStack Query, or fixing state management, performance, or React 19+ compatibility issues.
model-registry-maintainer
A comprehensive and well-structured guide for maintaining AI model registries with clear workflows, practical examples, and integration with existing systems like LiteLLM.
tanstack-query
Manage server state in React with TanStack Query v5. Covers useMutationState, simplified optimistic updates, throwOnError, network mode (offline/PWA), and infiniteQueryOptions. Use when setting up data fetching, fixing v4→v5 migration errors (object syntax, gcTime, isPending, keepPreviousData), or debugging SSR/hydration issues with streaming server components.
flow-nexus-neural
A comprehensive Skill for distributed neural network training and deployment in E2B sandboxes, offering advanced architectures, template marketplace, and cluster management with innovative features like divergent patterns and decentralized consensus.
transformers
This skill provides access to Hugging Face Transformers library for loading pre-trained models, performing inference, and fine-tuning across NLP, vision, and audio tasks. It includes practical code examples for pipelines, model loading, text generation, and training workflows with clear installation and authentication guidance.
fastapi
Build Python APIs with FastAPI, Pydantic v2, and SQLAlchemy 2.0 async. Covers project structure, JWT auth, validation, and database integration with uv package manager. Prevents 7 documented errors. Use when: creating Python APIs, implementing JWT auth, or troubleshooting 422 validation, CORS, async blocking, form data, background tasks, or OpenAPI schema errors.
router-query-integration
Provides concrete patterns for integrating TanStack Router with TanStack Query to eliminate request waterfalls during navigation. Shows how to use route loaders to prefetch data before components render, with examples for parallel queries, dependent queries, and error handling.
self-improve
A sophisticated meta-skill that enables AI agents to autonomously improve their own capabilities through documentation updates and system extensions based on real-world usage patterns.
cto-advisor
Technical leadership guidance for engineering teams, architecture decisions, and technology strategy. Includes tech debt analyzer, team scaling calculator, engineering metrics frameworks, technology evaluation tools, and ADR templates. Use when assessing technical debt, scaling engineering teams, evaluating technologies, making architecture decisions, establishing engineering metrics, or when user mentions CTO, tech debt, technical debt, team scaling, architecture decisions, technology evaluation, engineering metrics, DORA metrics, or technology strategy.
error-handling-patterns
Provides concrete error handling patterns for Python and TypeScript/JavaScript, covering custom exceptions, retry logic, graceful degradation, and error collectors. Includes practical code examples for common scenarios like API calls and data validation.
langchain-architecture
Provides practical guidance for building LLM applications with LangChain, covering agents, chains, memory, and document processing. Includes working code examples for common patterns like RAG and multi-step workflows, plus testing and optimization tips.
pci-compliance
Provides detailed guidance for implementing PCI DSS compliance, including code examples for secure payment handling, tokenization, audit logging, and validation. Covers all 12 core requirements with practical Python snippets and checklists.
agentdb-advanced
A comprehensive skill covering advanced AgentDB features for distributed AI systems, including QUIC synchronization, custom distance metrics, hybrid search, and multi-database management with practical code examples.
xlsx
A spreadsheet toolkit for creating, editing, and analyzing Excel files with formulas and formatting. Includes financial modeling standards, formula verification, and LibreOffice integration for recalculation. Focuses on error-free outputs with specific color coding and documentation requirements.