3.9K skills · sorted by relevance
Design and implement LLM applications, AI agents, and RAG systems that retrieve documents to support answers. Cover model selection, search quality, testing, monitoring, safety measures, and cost controls for applications intended for production use.
Integrate cryptocurrency exchanges into PHP applications with CCXT. Follow examples for market data, orders, authentication, and errors, with synchronous requests, ReactPHP asynchronous processing that avoids waiting on each request, and WebSocket connections for live updates.
Integrate cryptocurrency exchanges into Go applications with CCXT. Follow examples for market data, order management, authentication, and error handling, using REST for individual requests and WebSocket streams to monitor prices, order books, balances, and orders.
Automate Electron desktop apps with agent-browser through CDP, a browser debugging connection. Click controls, enter text, extract content, and capture screenshots while switching between app windows or embedded pages for routine work and testing.
Explore a web application as a user to find reproducible bugs and usability problems. Produce a structured report with reproduction steps, screenshots, and videos for interactive issues, giving responsible teams concrete evidence to investigate.
Analyze authorized macOS applications and Mach-O binaries, the executable format used on macOS. Examine signatures, dependencies, Objective-C and Swift symbols, and runtime behavior to produce findings tied to specific addresses or symbols.
Set up automated security checks that inspect source code without running the application. Configure Semgrep, SonarQube, or CodeQL, add project-specific rules, reduce false alarms, and define criteria for blocking problematic changes.
Build Python applications that handle other work while waiting for network or database operations. Use asyncio and async/await to run tasks concurrently, manage errors and timeouts, and handle cancellation with appropriate cleanup.
Configure Prometheus to collect and store operational metrics from infrastructure and applications. Covers collection schedules, alert rules, automatic discovery of monitored services, and troubleshooting checks to help establish and maintain monitoring.
Build and review C#/.NET APIs and business backends using concrete implementation patterns. Cover asynchronous operations, service dependencies, database access, configuration, caching, and tests to structure application code and examine quality and performance issues.
Evaluate LLM applications using automated scores, human reviews, and model-based judging. Build repeatable checks to compare models or prompts, assess answer quality, and detect declines in performance before deployment.
Design AI applications with LangChain 1.x and LangGraph, libraries for coordinating language models and workflows. Build agents that use external tools, manage conversation history and saved state, process documents, and support tracing and testing.
Investigate active macOS connection failures without changing network settings. Uses built-in tools to distinguish local network, DNS name lookup, upstream path, and application problems, then reports evidence, confidence, and the next useful diagnostic check.
Design application and API behavior when operations fail. Choose between exceptions and Result types, which explicitly represent success or failure, and improve retries, error messages, logging, and resource cleanup so failures are easier to handle and investigate.
Investigate LLM application failures with Phoenix CLI by reviewing execution records, recording observations, and grouping mistakes into counted categories. Inspect datasets and experiments to identify which failure types deserve evaluation tests first.
Prepare and publish Windows apps to the Microsoft Store using msstore. Covers account credentials, application packaging, submission tracking, beta testing groups, gradual releases, and automated publishing through CI/CD pipelines.
Turn application requirements into an Azure Cosmos DB NoSQL data model. Gather read and write patterns, workload volumes, and relationships, then document container structures, partition keys for distributing data, indexes, and design trade-offs in two Markdown files.
Build applications with GitHub Copilot SDK using Python, TypeScript, Go, or .NET. Add custom tools, display responses as they arrive, preserve conversations across restarts, and connect external tools through MCP, a protocol for connecting agents to tools.
Prepare an ASP.NET .NET Framework application for Windows Docker containers. Create project-specific build and runtime files, configure environment-based settings and Windows dependencies, and verify that the Docker image builds successfully.
Develop and troubleshoot distributed applications with Aspire. Coordinate services written in different languages through AppHost, configure connections and startup dependencies, inspect logs and metrics, and prepare deployment settings.
Set up telemetry, data about application operation, for web apps hosted in Azure. Choose automatic or manual instrumentation, create an Azure App Insights resource, and configure application code to send monitoring data.
Investigate high CPU usage in Java applications with Arthas. Identify busy threads, inspect method call paths, and produce an evidence-based diagnosis with specific methods to examine next.
Investigate Spring configuration and Beans, the objects Spring manages, using Arthas. Check configuration sources, find registered objects by name or type, and inspect registration details while prioritizing read-only queries.
Deploy a Software-Defined Perimeter that connects verified users to authorized applications. Configure single-packet authorization, mutual certificate authentication, access policies, and monitoring, then test whether unauthorized connections and access between applications are blocked.