agusmdev

Configure Alembic for async SQLAlchemy migrations with PostgreSQL

Create FastAPI application factory with lifespan, middleware, pagination, and router configuration

Implement session-based authentication in FastAPI applications. Use when building login/logout flows, protecting endpoints with auth dependencies, creating user models with password hashing, managing sessions in database, or implementing auth exceptions. Covers HTTPBearer token validation, Argon2 password hashing, session repository/service patterns, and route protection with dependency injection.

Overview and guidelines for FastAPI 3-layer architecture with async SQLAlchemy, Pydantic v2, and best practices

Create SQLAlchemy base model with UUID, timestamp, and soft delete mixins for FastAPI

Create abstract base repository interface with CRUD, pagination, filtering, bulk operations, and soft delete

Create Pydantic v2 base schemas for request validation and response serialization in FastAPI

Create base service class that wraps repository operations and provides business logic hooks

Master multi-agent orchestration using Claude Code's TeammateTool and Task system. Use when coordinating multiple agents, running parallel code reviews, creating pipeline workflows with dependencies, building self-organizing task queues, or any task benefiting from divide-and-conquer patterns.

API client setup with fetch wrapper, error handling, authentication headers, and React Query integration for TanStack Start/Router.

Token-based authentication for TanStack Client (SPA) apps including login/logout, protected routes, auth context, token storage, and route guards. SHARED skill for both TanStack Start (client-only mode) and TanStack Router.

Mutation patterns with useMutation, optimistic updates, cache invalidation, and rollback strategies. SHARED skill for both TanStack Start (SSR) and TanStack Router (SPA).

Query patterns with queryOptions factory, key conventions, prefetching strategies, and type-safe reusable query definitions. SHARED skill for both TanStack Start (SSR) and TanStack Router (SPA).

Configure TanStack Query (React Query) with QueryClient, provider, devtools, and optimal defaults. SHARED skill for both TanStack Start (SSR) and TanStack Router (SPA).

Configure Tailwind CSS v4 and shadcn/ui with theming, dark mode, and CSS variables. SHARED skill for both TanStack Start (SSR) and TanStack Router (SPA).

Configure TanStack Start in client-only mode (defaultSsr=false) for SPA-like behavior without server-side rendering.

Run an iterative, measured optimization loop — try an idea, benchmark it, keep what improves the metric, revert what doesn't, repeat — leaving an auditable trail of commits. Use this when the user wants to ITERATIVELY optimize a measurable target and expects to try many attempts: speeding up a test suite or build, shrinking a bundle/binary, cutting latency or memory, tuning hyperparameters to lower a loss, raising a Lighthouse/benchmark score. Strong fit when the metric is NOISY (needs repeated runs to trust), correctness must be preserved while optimizing, or a reviewable record of what was tried and kept matters. Trigger for "run autoresearch", "optimize X in a loop", "set up experiments to make X faster", "keep trying changes until the benchmark improves", "tune this until the loss is low", or "measure it properly, don't guess". Less suited to one-shot fixes you already know — see the "When NOT to use this" note before reaching for it on trivial changes.

Optimize smart-linter linting speed without breaking rule detection or tests