全部能力

Guidelines for implementing Clean Architecture patterns in Flutter and Go applications, with emphasis on separation of concerns, dependency rules, and…

Implement structured logging across applications with log aggregation and centralized analysis. Use when setting up application logging, implementing ELK stack, or analyzing application behavior.

Comprehensive guidance for building scalable, maintainable, and production-ready Node.js backend applications with modern frameworks, architectural patterns,…

Materials science toolkit. Crystal structures (CIF, POSCAR), phase diagrams, band structure, DOS, Materials Project integration, format conversion, for…

Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development. Use when writing Python tests, setting up test suites,…

Debug database performance issues through query analysis, index optimization, and execution plan review. Identify and fix slow queries.

Expert data science covering machine learning, statistical modeling, experimentation, predictive analytics, and advanced analytics. Use when selecting ML algorithms, engineering features, designing A/B tests, evaluating model performance, or building predictive pipelines.

Senior Risk Management specialist for medical device companies implementing ISO 14971 risk management throughout product lifecycle. Provides risk analysis,…

Generic release assistant — analyzes repo release rules, caches them in .omc/RELEASE_RULE.md, then guides the release

Extract structured data from multiple web pages using Playwright with built-in ethical crawling practices including rate limiting, robots.txt compliance, and error monitoring. Use when asked to "scrape data from", "extract information from pages", "collect data from site", "crawl multiple pages", or when gathering structured data from websites. Supports pagination, multi-page extraction, data aggregation, and export to CSV/JSON/Markdown. Works with browser_navigate, browser_evaluate, browser_wait_for, and browser_snapshot tools.

Analyze and implement purposeful UI animations for Next.js + Tailwind + React projects. Use when user asks to add animations, enhance UI motion, animate…

Analyze Claude Code sessions via Braintrust

Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream…

Multi-agent orchestration patterns. Use when multiple independent tasks can run with different domain expertise or when comprehensive analysis requires…

Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML…

Comprehensive guidance for implementing asynchronous Python applications using asyncio, concurrent programming patterns, and async/await for building…

Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. Uses…

Turn Notion specs into implementation plans, tasks, and progress tracking; use when implementing PRDs/feature specs and creating Notion plans + tasks from them.

Implement reactive programming patterns using RxJS, streams, observables, and backpressure handling. Use when building event-driven UIs, handling async data streams, or managing complex data flows.

LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring…