620 skills · sorted by relevance
Plan AI application development by selecting relevant phases and companion skills. The workflow covers language model integration, retrieval from documents, agents, machine learning pipelines, monitoring, and security, with prompts and quality checklists.
Plan AI application work across six areas: prompt evaluation, context allocation, retrieval-based answer generation, agent security, evaluation pipelines, and product strategy. This overview explains the approaches; the individual workflow packages, test cases, and CI templates are not included.
Investigate prompt injection in sandboxed security challenges by tracing how untrusted text changes an agent’s decisions or tool calls. Build a minimal reproduction and preserve evidence showing where external content crosses into trusted instructions or actions.
Decide whether an LLM needs additional training or whether retrieval and better prompts will suffice. Match available examples, preferences, or verifiable results to a training method, then assess model size and memory requirements before starting.
Build searches with Qdrant that find similar content and filter results by attributes. The skill covers document retrieval for AI answers, vector storage, memory optimization, and distributed deployment for larger collections.
Generate embeddings, numerical representations of text or images, for meaning-based search, similarity comparisons, and document grouping. The skill guides model selection, multilingual processing, local execution, and integration with retrieval workflows.
Build LlamaIndex applications that retrieve relevant material before generating answers, a method called RAG. Connect documents, websites, and databases to support document questions, conversational search, structured summaries, and checks of answer relevance and source consistency.
Improve prompts through test cases and baseline comparisons, measure how well AI answers use retrieved sources, and check agent configurations. Includes Python tools for prompt analysis, retrieval quality reports, and token estimates, with costs calculated from supplied rates.
Design an enterprise search system that answers questions using retrieved company content, an approach called RAG. Gather requirements and produce architecture diagrams, deployment guidance, and validation plans using GKE, AlloyDB, and open models.
Helps design semantic search and RAG, where an AI answers using retrieved documents. Covers embeddings, numerical representations of content, plus document splitting, search indexes, keyword search combinations, and evaluation of retrieval quality.
Generate embeddings, numerical representations of text or images, for meaning-based search, similarity comparisons, and document grouping. The skill guides model selection, multilingual processing, local execution, and integration with retrieval workflows.
Guides building AI applications that search documents before answering questions, an approach called RAG. Covers importing files and web data, creating searchable indexes, adding conversational interfaces, and evaluating whether answers match the retrieved material.
Build searches with Qdrant that find similar content and filter results by attributes. The skill covers document retrieval for AI answers, vector storage, memory optimization, and distributed deployment for larger collections.
Guides image classification and search with OpenAI's CLIP by comparing images with text descriptions, without additional training. Includes batch processing, image-text matching, and category-based checks for potentially inappropriate images.
Retrieve Chinese medical guidelines, drug information, and regulatory documents when original sources are inaccessible. It checks document identity and version before using alternative copies, while keeping summaries and reposts separate from independent clinical evidence.
Keep report writing focused on the original request when information retrieval fails. This skill guides agents to use existing knowledge, disclose missing information, create a structured document with write_file, and verify that the file exists.
Create a structured Markdown report when multiple retrieval tools fail. Using available domain knowledge, the workflow separates verified facts from general guidance, marks missing data, and saves a document with limitations and practical next steps.
Continue Python tasks after repeated sandbox failures by saving code as a script and running it through the shell, a command interface. The workflow covers execution checks, result retrieval, and optional cleanup.
Routes AI development questions to focused references on agents, language model security, retrieval-augmented generation, which uses retrieved information in answers, and prompt design and evaluation. It also outlines principles for validation, safety boundaries, version control, and ongoing assessment.
Select technologies for AI and machine learning features in .NET 8+ applications. Get task-specific plans or implementation guidance for structured predictions, text generation, document retrieval, tool-using agents, and running pretrained models locally or in production.
Create low-pressure review questions that help learners recall and apply what they studied. Use supplied materials to produce questions, grounded answer notes, and a short plan for checking answers, correcting mistakes, and revisiting weak areas.
Search UniProt for proteins by name, gene, or organism and retrieve sequences and functional annotations. Supports FASTA, a text format for sequences, identifier conversion between databases, batch retrieval, and downloads of large result sets through its REST API.
Build searches that find documents by meaning and support recommendation features using vector databases. Includes implementation patterns for storing and retrieving vectors, combining meaning with keyword matches, and tuning search speed and result quality.
Choose embedding models, which turn text into numerical representations of meaning, for semantic search and AI answers grounded in retrieved documents. Includes examples for document splitting, preprocessing, multilingual content, and measuring retrieval quality.