2K skills ・ Works with: OpenAI · sorted by popularity
Create and run evaluations in Arize using an LLM as the judge. Define scoring criteria, connect them to actual data fields, evaluate recorded operations or experiment results, and set up continuous scoring for new data.
Design Azure infrastructure from plain language or visualize existing resources as interactive diagrams. Refine the architecture through conversation, then generate Bicep infrastructure code, review it, and validate changes before deployment.
Manage the credentials Arize uses to call LLM providers such as OpenAI and Anthropic. Create, inspect, update, or delete connections, configure allowed models and authentication methods, and retrieve connection IDs for use in evaluations.
Add controls to AI agents that use APIs, databases, and files. Use Python patterns for tool permissions, approval requirements, call limits, suspicious input checks, audit logs, and trust scores that guide delegation between agents.
Create and analyze AI model evaluation experiments in Arize using the ax CLI, a command-line tool. Collect real model outputs, export results, compare evaluation scores, and identify examples where a new model performs worse.
Improve LLM prompts using Arize production traces, evaluation results, and human feedback. Extract current instructions, identify recurring failures, revise the prompt, and compare experiments to measure changes in output quality and catch regressions.
Guides development of ChatGPT apps with interactive widgets using mcp-use and OpenAI Apps SDK, covering server tools, React interfaces, and shared state. This skill is deprecated and directs users to mcp-app-builder.
Add or verify model support in SGLang's Rust processor so chat requests produce the same prompt text and token IDs as Python. Use reference-generated test cases to find differences in tools, reasoning settings, conversation history, and errors.
Analyze LLM serving traces to identify GPU time usage, opportunities to run operations concurrently, and known patterns for combining operations. Produce three consistent tables from saved traces or live captures on supported servers.
Research stock and cryptocurrency strategies through historical testing, factor analysis, and options pricing. Analyze trading journals, extract rules from profitable trades, and generate reports comparing simulated results with actual trading outcomes.
Extract text from PDFs, Office documents, images, spreadsheets, and text files through one tool. Results share a common JSON structure, supporting document summaries, contract checks, and spreadsheet previews, with optical character recognition for scanned content.
Examine AI research directions and safety strategies through thinking models drawn from Ilya Sutskever’s public statements. The skill checks current facts when needed and presents a concise judgment with an everyday analogy.
Examine AI product reliability, learning methods, and model limitations through frameworks drawn from Andrej Karpathy’s public statements. Assess the gap between demonstrations and real use, uneven capabilities, and where people should retain control.
Add checks to LLM prompts and responses using Llama Guard 3, NeMo Guardrails, and LLM Guard. Configure content screening, conversation boundaries, and sensitive-data filtering, then measure blocking and false-positive rates with labeled test prompts.
Set up repeatable security tests for LLM apps with Promptfoo and DeepTeam. Connect them to automated build pipelines, detect renewed vulnerabilities to malicious instructions or data leakage, and compare results across model or prompt changes.
Apply consistent coding practices across TypeScript, JavaScript, React, and Node.js projects. Get guidance on naming, types, error handling, API design, file organization, and tests to make code easier to read and maintain.
Design visually distinctive websites, landing pages, and portfolios as React components, reusable pieces of a web page. Use industry references to guide typography, color, layout, motion, and relevant 3D visuals that fit the brand.
Generate and edit images through the OpenAI Image API using a bundled command-line tool. Create product shots, illustrations, and interface mockups, replace backgrounds, modify selected areas, or produce batches while specifying details to preserve.
Convert LLMs to GGUF and reduce model size through quantization, which stores weights at lower numerical precision. Prepare models for CPU or Apple Silicon inference, compare compression levels, and integrate them with local AI tools.
Build document search and AI retrieval workflows with Chroma, a database for numerical representations of text. Cover document storage, meaning-based search, metadata filters, persistence, and connections to LangChain and LlamaIndex.
Use Outlines to make language models produce data in a defined format. The skill covers extracting information into JSON, restricting classification labels, and applying Pydantic models, which define fields and data types, with local model backends.
Build search and recommendation features with Pinecone, a managed database for numerical representations of content. Covers data loading, combined meaning and keyword search, filtering by attributes, and separating data by user.
Build workflows that extract structured data from LLM responses, check field types and values with Pydantic, and retry failed extractions. Includes examples for nested data, classification, and receiving results as they are generated.
Build safety checks for LLM prompts and responses using Meta's LlamaGuard moderation model. Classify potentially harmful content, block flagged messages, serve checks through an API, and integrate them with NeMo Guardrails.