181 skills · sorted by relevance
Turn a decision that needs someone else’s knowledge into a Markdown questionnaire. Clarify who will answer and what information is needed, then create prioritized questions with answer spaces for asynchronous replies or a meeting.
Write, review, and refactor Rust code using established conventions for ownership, error handling, type design, and concurrency. It guides safer implementations, avoids unnecessary copying, and organizes modules with a limited public interface.
Write or repair React tests around user actions and visible results. Cover components and hooks, simulate network responses, check accessibility, and decide when real browser component tests or end-to-end tests across pages are needed.
Write Kotlin tests with Kotest and MockK using test-driven development, where tests come before implementation. Cover asynchronous code, check behavior across generated inputs, and use Kover reports to measure how much code the tests exercise.
Build or review FastAPI applications using examples for project structure, input validation, authentication, permission checks, and asynchronous processing. Organize database updates in a separate business logic layer and test API behavior with httpx and pytest.
Review Flutter and Dart code using a checklist that adapts to the project's state management library. Check interface structure, asynchronous operations, performance, tests, accessibility, and security to identify issues across the application.
Implement asynchronous work and changing data streams in Android and Kotlin Multiplatform apps using Kotlin Coroutines and Flow. Apply patterns for parallel loading, UI state updates, cancellation, error handling, and tests that check emitted values.
Write or review Dart and Flutter apps with practical patterns for state management, navigation, networking, error handling, and tests. Use code examples to handle missing values, organize widgets, and connect login status to routing.
Trace button clicks and form actions through each state change to uncover conflicting updates, unintended resets, and asynchronous timing problems. Report where the final screen behavior differs from what the user expects, with specific fixes.
Set up reinforcement learning, training guided by response rewards, for large language models. Use Megatron-LM and SGLang to prepare data, configure training and response generation, and build asynchronous or multi-turn experiments.
Debug Node.js from the terminal by pausing execution, inspecting variables, and tracing function calls. Use interactive commands or scripts to investigate failing tests, collect runtime state, and capture CPU profiles or memory snapshots.
Prepare media assets required by an existing OD Next plan. Reuse verified capabilities and suitable assets, acquire files, measure dimensions, and retrieve background job results while preserving required content, licensing constraints, and quality conditions.
Run and manage an agent in Anthropic's cloud for long or asynchronous tasks. Create a session with packages and tools, send work, inspect status and activity, continue with saved files and conversation, then terminate the session.
Find and fix JavaScript memory leaks that accumulate as people use a web app. Review event listeners, timers, retained page elements, and outdated asynchronous tasks, then explain how to verify cleanup in the browser.
Investigate crashes, hangs, incorrect responses, and other failures by testing hypotheses against observed runtime behavior. Confirm the cause, verify the fix with a reproducing test, check the real workflow, and remove temporary debugging artifacts.
Integrate FLUX image generation and editing into applications through the BFL API. The guide covers authentication, checking asynchronous results, completion notifications through webhooks, request limits, error handling, regional endpoints, and downloading generated images before their URLs expire.
Implement SMS notifications, verification code delivery, and bulk messaging in Java with Azure Communication Services. Covers authentication, asynchronous sending, per-recipient results, error handling, and delivery reports received through Azure Event Grid.
Build text translation into Python applications with Azure AI Translator. Covers translation into multiple languages, language detection, transliteration to another writing system, dictionary entries, usage examples, and asynchronous requests for handling larger workloads.
Implement .NET workflows for Azure AI Foundry projects, including agent creation, resource connections, dataset uploads, model deployment inspection, search index management, and evaluations. Examples also cover authentication, asynchronous operations, and resource cleanup.
Generate images and videos through Atlas Cloud by checking each model’s input requirements before submission. Guides the agent through sending a request, checking progress within a time limit, and downloading and validating the resulting media.
Design and build Apify integrations for workflow platforms, AI agents, AI frameworks, or applications. Follow guidance for authentication, asynchronous cloud task execution, result retrieval, spending limits, error handling, testing, and release preparation.
Automate Amplitude tasks through Rube MCP and Composio. Send tracking events, retrieve user activity, update user properties, and manage cohorts, saved groups of users, with checks for identifiers and asynchronous update status.
Build Python integrations with crypto exchanges using CCXT. Get guidance on fetching prices and order books, placing orders, checking balances, and receiving live updates, with examples for authentication, error handling, and synchronous or asynchronous code.
Trace queued jobs from submission to their eventual effects in a CTF sandbox. Compare request-time and worker-time settings, follow retries and failed-message handling, and document the smallest sequence that explains a worker-specific result.