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.
prpm-development
This skill provides detailed internal documentation for PRPM, a package manager for AI prompts and agents. It covers architecture, format conversion between Cursor, Claude, and Continue, package types, and development workflows. It includes concrete code examples, testing patterns, and deployment procedures for contributors.
snowflake-connections
This skill provides detailed guidance for configuring Snowflake connections across CLI tools, Streamlit apps, and Snowpark applications. It covers multiple authentication methods (SSO, key pair, username/password, OAuth), environment management, and CI/CD integration with specific file examples and security best practices.
ai-collaborate-teaching
Provides a structured framework for designing AI-integrated learning experiences using the Three Roles model. Offers concrete templates, balance guidelines, and verification mechanisms to ensure students learn foundational skills while effectively collaborating with AI tools.
verification-before-completion
Enforces a discipline where AI agents must run verification commands and show evidence before claiming task completion. Provides concrete examples for different contexts like testing, building, and linting, with specific command templates and success criteria.
matchms
Provides Python code for mass spectrometry data workflows using matchms library. Handles file import/export, spectrum filtering, similarity calculations, and compound identification. Includes 10 practical workflows for metabolomics analysis with clear examples.
risk-manager
This skill provides structured frameworks for enterprise risk identification, quantification, and mitigation across financial, operational, and cybersecurity domains. It integrates multiple analytical tools including Python, R, and SQL for modeling, with checklists for compliance verification and risk reporting automation.
ai-rag
Provides concrete patterns for building RAG and search systems, covering chunking, hybrid retrieval, reranking, and evaluation. Includes decision trees, implementation checklists, and links to templates for production deployment. Focuses on separating retrieval quality from answer quality and treating staleness as a correctness issue.
bsl-model-builder
This skill helps build semantic data models using the Boring Semantic Layer (BSL). It defines dimensions and measures on Ibis tables, supports joins, and allows configuration via YAML. It's designed for creating reusable data models for analytics.
ai-multimodal
Provides unified access to Google Gemini's multimodal API for processing audio, images, videos, and documents, plus image generation. Includes practical scripts for batch processing, media optimization, and document conversion. Clear guidance on model selection, token costs, and rate limits.
torch-geometric
Provides a comprehensive guide for using PyTorch Geometric for graph neural network tasks. Covers installation, data structures, model building, training workflows, and includes benchmark scripts for comparing GNN architectures on standard datasets.
Backend Models Standards
Define database models with clear naming, appropriate data types, constraints, relationships, and validation at multiple layers. Use this skill when creating or modifying database model files, ORM classes, schema definitions, or data model relationships. Apply when working with model files (e.g., models.py, models/, ActiveRecord classes, Prisma schema, Sequelize models), defining table structures, setting up foreign keys and relationships, configuring cascade behaviors, implementing model validations, adding timestamps, or working with database constraints (NOT NULL, UNIQUE, foreign keys). Use for any task involving data integrity enforcement, relationship definitions, or model-level data validation.
compliance-architecture
Enterprise-grade compliance architecture for SOC 2, HIPAA, GDPR, PCI-DSS. Provides compliance checklists, security controls, audit guidance, and regulatory requirements for serverless and cloud architectures. Activates for compliance, HIPAA, SOC2, SOC 2, GDPR, PCI-DSS, PCI DSS, regulatory, healthcare data, payment card, data protection, audit, security standards, regulated industry, BAA, business associate agreement, DPIA, data protection impact assessment.
project-astrology-vedic
This skill provides detailed Vedic astrology analysis with sidereal zodiac calculations, Dasha systems, and Nakshatra interpretations. It includes comprehensive reference tables for planets, signs, and lunar mansions, plus clear guidelines for when to use it versus other astrology skills. The documentation differentiates Vedic from Western astrology and explains key concepts like Ayanamsa systems.
openai-assistants
Build stateful chatbots with OpenAI Assistants API v2 - Code Interpreter, File Search (10k files), Function Calling. Prevents 10 documented errors including vector store upload bugs, temperature parameter conflicts, memory leaks. Deprecated (sunset August 2026); use openai-responses for new projects. Use when: maintaining legacy chatbots, implementing RAG with vector stores, or troubleshooting thread errors, vector store delays, uploadAndPoll issues.
prompt-optimizer
A prompt optimization tool that analyzes and rewrites user prompts for better AI responses. It categorizes prompts (system, task-specific, creative, technical, agentic) and applies a structured framework with progressive disclosure and token efficiency. The tool offers three optimization levels (quick polish, balanced enhancement, deep transformation) based on input quality.
bulk-wgcna-analysis-with-omicverse
This skill provides step-by-step guidance for running WGCNA co-expression network analysis using the omicverse Python package. It covers data preprocessing, network construction, module detection, and hub gene identification with specific code examples and troubleshooting tips for common issues.
cloudflare-agents
Build AI agents with Cloudflare Agents SDK on Workers + Durable Objects. Provides WebSockets, state persistence, scheduling, and multi-agent coordination. Prevents 23 documented errors. Use when: building WebSocket agents, RAG with Vectorize, MCP servers, or troubleshooting "Agent class must extend", "new_sqlite_classes", binding errors, WebSocket payload limits.
qdrant
Provides Java patterns for integrating Qdrant vector database with Spring Boot and LangChain4j. Covers client setup, collection management, vector operations, and RAG implementations. Includes Docker deployment, dependency configuration, and practical code examples for semantic search and retrieval systems.
query-expert
This skill helps developers write and optimize database queries across SQL and NoSQL systems. It provides examples for PostgreSQL, MySQL, MongoDB, and others, covering query patterns, performance analysis, and common anti-patterns. It's useful for debugging slow queries and learning best practices.
model-usage
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
skill-lookup
Activates when the user asks about Agent Skills, wants to find reusable AI capabilities, needs to install skills, or mentions skills for Claude. Use for discovering, retrieving, and installing skills.
Line Execution Checker
Check if specific lines were executed using gcov data
debug-protocol
Provides a structured 5-step debugging protocol (Reproduce, Isolate, Identify, Fix, Verify) with mandatory logging to prevent guess-and-retry loops. Enforces a 3-5-rewrite rule and includes specific checklists for CSS/JS issues and multi-AI handoff procedures.
agent-evals
Provides a systematic approach to evaluating AI agents using binary criteria instead of subjective scales. Focuses on error analysis, trace examination, and creating component-level tests. Includes practical templates for graders and workflows to identify failure patterns in agent reasoning.