AI & Machine Learning Bundle

Prompt engineering, LLM integration, agent design, model fine-tuning, and AI workflow skills for ML practitioners.

Browse all skill bundles

Included Skills (90)

Langchain — LangChain equips developers to build sophisticated LLM‑powered applications, from RAG pipelines and conversational agents to complex language model workflows. It provides Python and TypeScript tools for creating agents, structured output, prompt templates, memory‑augmented chatbots, and efficient vector store integration. Data‑centric teams and AI engineers use it to deploy and scale production‑ready language model solutions.
PydanticAI Agent Framework — This skill enables developers to build robust, type-safe AI agents in Python using PydanticAI for structured outputs, tool integration, and reliable model testing.
MCP Server Architect — Develop and deploy robust Model Context Protocol servers using TypeScript or Python to extend AI agent capabilities with custom tools and resources.
Huggingface Llm Trainer — The Huggingface Llm Trainer enables professionals to train or fine‑tune language and vision models on cloud GPU infrastructure using TRL or Unsloth, supporting SFT, DPO, GRPO, reward modeling, and GGUF conversion for local deployment. It guides users through dataset preparation, hardware selection, cost estimation, and monitoring with Trackio, while handling Hub authentication, model selection, and persistence. This skill is ideal for data scientists and ML engineers who need efficient, cloud‑based training workflows without local GPU resources.
RouterBase Model Gateway — This skill provides an OpenAI-compatible gateway for developers to route diverse AI model requests, including text, media, and embeddings, through RouterBase.
Gke Inference — The Gke Inference skill deploys and optimizes AI and ML inference workloads on Google Kubernetes Engine, using GPUs, TPUs, and model servers to deliver high‑performance inference. It allows teams to configure GKE GPU resources and deploy large language models, ensuring efficient scaling and resource utilization for real‑time inference scenarios. The skill is not intended for migration, GKE RAG with Cloud SQL or AlloyDB, or batch/HPC use cases.
AI Development Workflow — This comprehensive workflow assists developers in building, integrating, and scaling LLM applications, RAG systems, and intelligent agent architectures for production environments.
Claude Integration Assistant — This skill assists developers in building LLM-powered applications by providing expert guidance on implementing Anthropic SDKs, Claude API features, and model configurations.
Cerebras — Cerebras Inference delivers a hosted LLM API that runs open models on Cerebras wafer‑scale chips, producing thousands of tokens per second via an OpenAI‑compatible endpoint. It offers the lowest‑latency chat, code completion, and agent loops for developers requiring streaming, tool calling, strict JSON schema output, or reasoning control. The service also eliminates “model not found” errors from retired Cerebras model IDs, ensuring reliable access for production workloads.
RAG System Architect — This workflow guides developers through building and optimizing RAG systems by streamlining embedding selection, vector database configuration, and retrieval performance evaluation.
Tactical Voice Assistant — This skill enables developers to build a low-latency, Iron Man-inspired conversational voice agent using the Pipecat framework, Gemini, and OpenAI services.
RAG Security Auditor — Probes Retrieval-Augmented Generation pipelines for indirect prompt injection vulnerabilities to help security engineers validate guardrails and secure document-based AI systems.
AI Tool Discovery — This tool enables AI agents to dynamically discover, verify, and connect to external APIs and MCP endpoints for enhanced workflow automation.
Agent Platform Prompt Management — Manages and orchestrates prompts in Agent Platform. Use when you need to create, list, retrieve, version, or delete managed prompts in Agent Platform. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform prompts.
LLM Evaluation Specialist — This skill assists developers in designing robust automated evaluation pipelines, implementing LLM-as-a-judge frameworks, and mitigating bias to ensure high-quality model output assessments.
Structured Output — Structured Output directs large language models to generate validated JSON, ensuring machine‑readable data integrity. Developers and data engineers use it to extract and validate structured information from OpenAI, Anthropic, or Claude APIs, integrating seamlessly with Zod schemas, Pydantic models, and the Instructor library. Its retry strategies for malformed responses guarantee robust data extraction.
MCP Governance Controller — This skill enables developers to secure AI agent tool calls using Cedar policies, shadow-mode testing, and cryptographic Ed25519 audit receipt verification.
Haystack — Haystack is an open‑source Python framework that enables developers to construct and debug retrieval‑augmented generation pipelines, search systems, and LLM agents from modular components such as document stores, retrievers, prompt builders, chat generators, and agents. It supports custom component development, document indexing for retrieval, agent creation with tool integration, and migration from Haystack 2.x to 3.x. The framework benefits data scientists, AI engineers, and software developers who need a flexible, component‑based approach to building advanced search and conversational AI solutions.
Agent Platform Model Registry — The Agent Platform Model Registry centralizes machine learning model management, enabling users to upload, list, describe, update, or delete models with strict version control and detailed metadata. By streamlining inventory organization, it frees data scientists and ML engineers to focus on training and deployment, accelerating development cycles and improving deployment reliability.
Unified LLM Gateway — This tool simplifies AI integration by providing a single API credential to access multiple LLM providers directly within your Neon database branches.
Agent Platform Tuning — The Agent Platform Tuning skill fine‑tunes open and Gemini models within the Agent Platform infrastructure. It streamlines the adjustment of model parameters for developers who need precise control over performance. The skill is not intended for external training, endpoint deployment, or serving endpoint management.
Agent Platform Rag Engine Management — The Agent Platform Rag Engine Management skill enables professionals to list, inspect, and query RAG corpora and files within the Agent Platform, retrieving grounded contexts through the Google GenAI SDK. It supports content generation that is anchored in a specific RAG corpus, providing precise, contextually relevant information for data scientists and AI developers. This skill is not intended for general database queries or other RAG products such as Google Workspace RAG or gRAG.
LLM Prompt Engineer — This skill helps AI developers design effective prompts for LLMs, improving output quality and reliability across various applications.
Context Engineering — The Context Engineering skill audits and reorganises an AI coding agent’s context window, managing instruction files, path‑scoped rules, skills, subagents, hooks, and the current conversation. It ensures the agent follows the correct CLAUDE.md, AGENTS.md, and repository‑specific guidelines, preventing quality degradation in long sessions and avoiding unnecessary API invention. Developers and teams using Claude Code, Codex, Gemini CLI, or Cursor benefit from optimal context management and clear separation of responsibilities between skills and rules.
Fireworks AI Assistant — Provides expert guidance for Fireworks AI, helping developers integrate the inference API, fine-tune models, and deploy custom endpoints.
RAG Systems Architect — This expert assists developers in building high-quality Retrieval-Augmented Generation systems by optimizing embedding models, vector database architecture, and advanced retrieval strategies for LLMs.
Embedding Model Trainer — This skill provides specialized templates and guidance for developers to fine-tune SentenceTransformer and CrossEncoder models for advanced retrieval and semantic similarity tasks.
Together AI Platform — Together AI provides a cloud platform for developers to run and fine-tune open-source AI models via inference APIs.
Azure AI — The Azure AI skill integrates search, speech, OpenAI, and document intelligence services to provide robust search capabilities, including vector, hybrid, and semantic search. It also offers speech-to-text, text-to-speech, transcription, and OCR functions for converting audio and scanned documents into searchable text. This skill benefits developers and data professionals who need efficient, end-to-end AI-powered content retrieval and processing.
AI Tool Architect — This skill guides developers in designing robust, efficient AI agent tools through optimized schemas and descriptions to ensure reliable model performance.
Prompt Refinement Specialist — This tool refines AI prompt files by applying proven structural patterns and linguistic improvements to ensure optimal performance for end users.
Huggingface Spaces — The skill builds, deploys, and maintains applications on Hugging Face Spaces using Gradio, Docker, or static SDKs, and manages model loading, debugging, and inference providers. It supports ZeroGPU and dedicated hardware, bucket management, and community grants, ensuring smooth operation of Spaces. Clients benefit from reliable app hosting, rapid issue resolution, and efficient porting of code to Hugging Face environments.
Agent Platform Deploy — The Agent Platform Deploy skill provisions open or custom models from Model Garden to Agent Platform endpoints, monitors deployment progress, and cleans up resources by undeploying models and deleting endpoints. It is used by developers and data scientists who need to actively deploy a model, verify deployability, assess costs, or troubleshoot quota and error issues. The skill is not intended for simple listing or evaluation tasks, which are handled by other dedicated skills.
Gemini Enterprise Integrator — This skill assists developers in integrating Gemini models into enterprise applications using the Google Gen AI SDK on the Agent Platform.
LLM Prompt Optimizer — This tool refines LLM prompts using production trace data and performance metrics to help developers improve AI output quality through data-driven optimization.
Transformer Model Trainer — This skill enables developers to fine-tune and align transformer language models using advanced TRL techniques like SFT, DPO, GRPO, and reward model training.
Agent Tool Security — Implements defense-in-depth controls for AI agents to prevent unauthorized tool execution and mitigate risks from prompt injection or malicious tool usage.
Agent Memory — The Agent Memory skill endows AI coding agents with persistent, file‑based and vector‑based memory that survives across sessions. It enables developers and teams to instruct agents to remember information, build a knowledge base, or maintain context using SQLite embeddings, vector databases such as ChromaDB or Pinecone, and semantic search for efficient retrieval. This capability improves continuity and productivity for projects that require reliable, long‑term memory.
LLM Evaluation Pipeline — This tool helps AI developers improve application quality by establishing automated evaluation pipelines, creating golden datasets, and generating actionable insights for performance optimization.
TAO AutoML Optimizer — Automates hyperparameter optimization and experiment tracking for NVIDIA TAO networks, assisting developers in efficiently tuning model training, evaluation, and inference workflows.
Ruby MCP Generator — This tool generates a production-ready Model Context Protocol server project in Ruby, helping developers quickly scaffold robust AI-integrated server applications.
Copilot Agent SDK — This SDK empowers developers to embed production-tested AI agent workflows into applications, streamlining custom tool creation, session management, and seamless MCP server integration.
Multi-Agent System Architect — This skill empowers developers to design, build, and scale production-grade multi-agent workflows using LangGraph, LangChain, and advanced autonomous agent orchestration frameworks.
Azure Openai — Azure OpenAI provides Microsoft’s hosted OpenAI models—GPT, GPT‑image, Whisper, and embeddings—on Azure infrastructure. It enables secure, compliant access through Managed Identity or Entra ID, supports content filtering, and offers enterprise features such as regional data residency and private networking. This service benefits organizations that require robust, regulated deployment of advanced AI models within the Azure ecosystem.
AI Eval CI — Automate AI agent and LLM evaluations in CI/CD pipelines, ensuring quality and preventing regressions before deployment, benefiting developers and AI engineers.
Mistral AI Interface — Provides access to Mistral AI's language models for code generation, multilingual tasks, and GDPR-compliant AI inference.
Hugging Face Toolkit — Enables users to leverage Hugging Face's libraries for tasks like model inference, fine-tuning, and publishing, benefiting ML practitioners.
LLM Security Guardrails — This skill implements robust input and output validation guardrails for LLM applications to ensure safety, compliance, and protection against malicious prompt injections.
Agentic Evaluation Framework — This framework provides developers with systematic patterns for implementing self-critique and iterative refinement loops to significantly enhance the quality of AI agent outputs.
Gemini Media Generator — This tool enables developers to generate and edit high-quality images and videos using Google Gemini models with integrated cost-approval and audit logging.
mastra — Mastra is a TypeScript framework that lets developers build production‑ready AI agents, retrieval‑augmented generation pipelines, and complex workflows with type‑safe definitions and reliable tool integration. It provides vector‑based knowledge retrieval, multi‑step branching, and robust error handling while connecting to over fifty third‑party services. By eliminating the need for Python libraries, Mastra enables TypeScript teams to create sophisticated agent capabilities efficiently.
Yann LeCun Persona — This agent simulates Yann LeCun to provide expert insights on deep learning, neural networks, and AI research for developers and researchers.
System Prompt Optimizer — This tool converts verbose human-written instructions into efficient, AI-native structured formats to improve model compliance and reduce token consumption for developers.
Arize Evaluation Manager — This skill automates LLM-as-judge evaluation workflows on the Arize platform, helping developers manage evaluators, execute scoring tasks, and monitor model performance metrics.
Agent Swarm Orchestration — The skill orchestrates multiple AI agents to collaborate on complex tasks, managing routing, handoffs, consensus, memory sharing, and quality gates. It enables teams building multi‑agent systems, specialist pipelines, or autonomous agent swarms to implement hierarchical, mesh, or pipeline topologies with supervision and quality control, ensuring seamless agent-to-agent communication and robust orchestration.
Vertex AI Gemini — This skill helps enterprises deploy and fine-tune Gemini models on Google Cloud Vertex AI with enterprise-grade features.
Ragas — Ragas is an open‑source Python framework that evaluates retrieval‑augmented generation pipelines and LLM applications using metrics such as faithfulness, response relevancy, context precision, and context recall. It allows developers to score RAG systems, generate synthetic test sets from documents, embed quality checks into CI pipelines, and create custom LLM‑judged metrics. Data scientists, ML engineers, and product teams benefit from its rigorous, automated assessment of retrieval‑augmented generation performance.
Embedding Optimization Guide — This guide assists developers in selecting, fine-tuning, and optimizing embedding models to improve the performance and accuracy of vector search applications.
Sentence Transformer Trainer — This skill facilitates training and fine-tuning diverse embedding models, helping developers implement efficient retrieval, reranking, and classification pipelines using standardized production templates.
AI Model Recommender — This tool identifies optimal AI models based on specific task requirements and hardware constraints, helping developers and data scientists select the best-performing solutions.
Retrieving Developer Knowledge — The skill searches, retrieves, and synthesizes official Google developer documentation across Cloud, AI/Gemini, Android, Chrome, Web, Flutter, Go, Firebase, and related platforms. It integrates with the Developer Knowledge MCP server or REST API to provide accurate gcloud CLI commands, API syntax, IAM permissions, and architectural comparisons. Developers and architects use it to quickly locate authoritative documentation and make informed product choices.
Serverless AI Inference — Deploy and run AI models instantly with fal.ai, enabling developers to generate media and run ML inference at scale.
Prompt Safety Auditor — This tool analyzes AI prompts for security vulnerabilities, bias, and safety risks while providing actionable improvements for developers building responsible and effective AI applications.
Groq API Assistant — Provides expert guidance for integrating Groq's ultra-fast LLM inference API into real-time AI applications, assisting developers.
Autonomous Agent Architect — This workflow assists developers in designing, implementing, and orchestrating autonomous AI agents, multi-agent systems, and complex tool integrations for scalable applications.
Prompt Engineering Expert — This guide provides advanced prompt engineering patterns and optimization techniques to help developers improve LLM performance, reliability, and output quality for complex tasks.
E2B — Sandboxed Code Execution for AI — E2B provides AI agents with secure, isolated sandboxes—ephemeral Linux VMs equipped with a filesystem, package managers, and internet access—to execute code safely. It enables users to run Python or JavaScript, install packages, read and write files, or perform long processes without compromising the host system. The skill is ideal for developers integrating code execution into LangChain, CrewAI, or custom agent workflows.
AG2 (AutoGen) — Multi-Agent Conversation Framework — AG2 is an open‑source Python framework that lets developers build AI agents and multi‑agent systems capable of calling functions, executing code, and engaging in structured group chats. It supports collaboration through tool use, human approval, and coordinated conversations, making it ideal for projects that require sophisticated agent interactions or migration from earlier AutoGen or pyautogen versions. The framework serves data scientists, software engineers, and AI architects who need reliable, extensible agent orchestration in production environments.
Crawl4AI Web Crawler — Assists developers in extracting clean, structured website data for AI applications like LLM training and RAG pipelines using Crawl4AI.
Production ML Engineer — This skill assists machine learning engineers in designing, deploying, and maintaining scalable, production-ready AI systems using modern frameworks and robust infrastructure practices.
Pinecone Vector Database — This skill helps AI developers use Pinecone, a managed vector database, to build semantic search and RAG applications.
AI Product Architect — This skill assists developers in building robust, scalable, and cost-effective AI-powered products by implementing reliable LLM integration patterns and trusted user experiences.
Local Model Evaluator — This tool enables developers to perform local model evaluations using inspect-ai and lighteval to optimize backend selection and hardware performance testing.
BEVFusion Perception Trainer — This skill enables autonomous driving developers to train, evaluate, and run inference for multi-sensor 3D object detection models using LiDAR and camera fusion.
Google Cloud Solution Agentic AI Data Science Workflow — The Google Cloud Solution Agentic AI Data Science Workflow designs a customized, multi-product agentic data science architecture that follows opinionated best practices. It is used by architects building agent-based data analytics or machine learning solutions on Google Cloud. The skill is not intended for simple queries, non-agentic pipelines, general cloud reviews, or writing agent code.
Agent Fault Simulator — This tool provides deterministic failure testing for agent workflows to verify recovery, state preservation, and safety boundaries before production deployment.
MCP Server Architect — This tool assists developers in designing and building high-quality Model Context Protocol servers that enable LLMs to effectively interact with external services.
FAF Context Architect — This tool enables developers to standardize project context using the IANA-registered FAF format, ensuring seamless AI-readiness across multiple development platforms and workflows.
Famulor Workspace Manager — This tool enables seamless management of Famulor assistants, communication campaigns, and workspace automations for users through a secure, authenticated MCP server integration.
SageMaker Deployment Orchestrator — This tool streamlines model deployment to Amazon SageMaker by selecting optimal serving stacks and inference modes to assist developers with cloud infrastructure.
LLM Observability Expert — Assists developers in tracing and monitoring LLM applications using Langtrace, an open-source observability platform built on OpenTelemetry.
Agent Workflow Designer — The Agent Workflow Designer constructs production‑grade multi‑agent pipelines, enabling architects to choose sequential, parallel, or hierarchical patterns while configuring handoff contracts, failure handling, and cost controls. It refactors LLM pipelines that suffer from context bloat or unreliable handoffs, producing robust, efficient, and scalable AI workflows that meet production demands. System architects and AI engineers benefit from reliable, cost‑effective, and maintainable multi‑agent solutions.
Hugging Face Trainer — Fine-tune language and vision models using TRL or Unsloth on Hugging Face infrastructure to enable efficient cloud training and local GGUF deployment.
AI Product Architect — This skill helps developers build profitable, problem-solving AI applications by optimizing prompt engineering, cost management, and user experience for sustainable product growth.
Vector Database Specialist — This expert assists developers in architecting, optimizing, and implementing high-performance vector search and retrieval systems for RAG and semantic applications.
Vision Model Trainer — This tool enables developers to fine-tune state-of-the-art vision models for object detection, classification, and segmentation tasks directly on Hugging Face cloud infrastructure.
AI Agent Alerting — This skill generates Terraform configurations for OpenTelemetry-based alerting policies, helping developers monitor AI agent reliability, cost, safety, and performance metrics effectively.
Gemini Interactions API — The Gemini Interactions API enables developers to build stateful, multi‑turn conversations on the Gemini Enterprise Agent Platform, supporting background execution, streaming, structured output, and function calling. It allows agents to maintain context and deliver consistent, dynamic responses. Enterprises seeking robust, server‑managed dialogue systems for customer support, automation, and data‑driven interactions benefit from this capability.
Gemini Agent Manager — This tool enables developers to programmatically provision, configure, and manage stateful agent resources on the Gemini Enterprise Agent Platform via REST APIs.
SageMaker Container Selector — This tool identifies the optimal HuggingFace-curated SageMaker serving container and retrieves the correct image URI to ensure reliable, region-specific model deployments for developers.