Use when building or modifying CRUD endpoints with FastCRUD (the fastcrud PyPI package) in a FastAPI project — covers FastCRUD, crudrouter, EndpointCreator, FilterConfig, JoinConfig, auto-relationship detection, the filter operator syntax (gte, in, ilike, etc.), cursor pagination, soft delete, and how to avoid N+1…
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
Replace Tokio Rust stacks with Asupersync. Use when migrating tokio/axum/hyper/tonic apps, designing native Cx/region-based services, or debugging Asupersync internals.
Production-grade FastAPI development with async patterns, Pydantic v2, dependency injection, ML/AI endpoint design, and modern Python best practices for building high-performance REST APIs.
Master functional approaches to side effects including IO types, effect isolation, idempotent operations, and quarantining impure code - essential patterns for reliable TypeScript applications.
The Shark Pattern — universal non-blocking execution for any AI coding agent. Spawn remoras for slow tools, keep the main agent swimming. Works with Claude Code, Codex, Gemini CLI, Cursor, Aider, OpenClaw.
Background shell execution pattern for any AI coding agent. Wraps slow commands in background process + poller so the main agent always replies within 30s.
Plan and build production-ready FastAPI endpoints with async SQLAlchemy, Pydantic v2 models, dependency injection for auth, and pytest tests. Uses interview-driven planning to clarify data models, authentication method, pagination strategy, and caching before writing any code.
Tighten user prompts before they reach a model — strip conversational filler, drop fragments, dedupe sentences, rank by relevance, and compose a short, declarative system prompt that doesn't waste context. CPU-only, deterministic, dependency-free. Use it whenever a request is long, rambling, or covered in pleasantries…
Shrink LLM prompts before sending them — collapse duplicate tool results, distill old turns, minify tool schemas and system prompts, prune to a token budget, and (opt-in) prune large HTML tool results. On the output side, the proxy can cap/truncate streamed completions and strip lead-in filler. Lossy by default…
Guide for contributing to the minicode-sdk project. Use this skill when the user wants to contribute code, fix bugs, add features, or improve documentation for the minicode-sdk project.
Guide for using the minicode-sdk library. Use this skill when the user wants to learn how to use minicode-sdk to build AI agents, integrate tools, use MCP servers, or configure the SDK.
A CMakeLists.txt generator for Drogon, a C++ web framework. It creates build configuration for options such as database access, Redis, WebSockets, C++20, and coroutines.
A code generator for Drogon lambda-based HTTP routes. A route maps a web address and HTTP method, such as GET or POST, to code that handles the request.
A code generator for Drogon plugins, which initialize and manage application-wide resources during the program's lifetime. Examples include connection pools and third-party software libraries.