productivity▌

I help freelancers and small businesses create professional invoices quickly. Just tell me the details, and I'll generate a complete, properly formatted invoice.

Surfaces migration risks and validates migration work against known Oracle/PostgreSQL behavioral differences documented in the references/ folder.

pytorch-fsdp

Build accessible, production-ready web forms with HTML, CSS, JavaScript, and server-side processing. \n \n Covers complete form lifecycle: HTML structure, CSS styling, JavaScript validation, and server-side handling with PHP or Python \n Includes accessibility best practices (ARIA roles), progressive enhancement, and security guidelines for data transmission \n Provides references for database integration (MySQL), data formats (JSON, XML), and REST API communication \n Supports both client-side

Separate read and write models with command and query buses for scalable, event-driven architectures. \n \n Provides command and query handler infrastructure with bus patterns for dispatching operations to appropriate handlers \n Includes templates for command validation, event persistence, read model projections, and FastAPI integration \n Supports eventual consistency patterns with checkpoint-based synchronization and read-your-writes consistency helpers \n Covers event sourcing fundamentals,

Cross-service productivity workflows connecting Google Workspace apps via CLI commands. \n \n Includes five pre-built helper workflows: standup reports, meeting prep, email-to-task conversion, weekly digests, and file announcements \n Requires gws binary and authentication setup from the shared gws-shared skill documentation \n Discover available resources and methods with gws workflow --help and inspect method signatures using gws schema workflow.<resource>.<method> \n Pass parameters

Analyze current repository context and suggest relevant prompt files from the GitHub awesome-copilot repository that are not already available in this repository.

Extract clean markdown or text from up to 20 URLs, with JavaScript rendering and query-focused chunking support. \n \n Handles JavaScript-rendered pages with configurable extraction depth (basic for simple pages, advanced for dynamic SPAs and tables) \n Supports query-focused extraction to return only relevant content chunks instead of full pages \n Returns LLM-optimized markdown by default, with options for plain text format and structured JSON output \n Processes up to 20 URLs in a single call

When the user wants to create a new project, first infer as many options as possible from the user's request (e.g., "new Mojo project" means type=Mojo, "called foo" means name=foo). Then use a structured multiple-choice prompt (not plain text) to gather only the remaining unspecified options in a single interaction. Do NOT ask about options the user has already provided or implied. The options to determine are:

All commands: nansen research profiler <sub> [options]