juanre

How to release a new pgdbm library version to PyPI

How to update and publish pgdbm skills for Claude Code users

Use before implementing pgdbm patterns to avoid common mistakes - provides rationalization table and red flags that prevent pool multiplication, schema errors, and template syntax violations

Use when writing tests for pgdbm-based code - provides fixture selection decision tree and complete usage patterns without needing testing docs

Use when deciding which pgdbm pattern to use (standalone, dual-mode library, or shared pool) - provides decision tree based on deployment context without requiring doc exploration

Use when implementing pgdbm database operations - provides complete AsyncDatabaseManager and DatabaseConfig API with all methods and parameters

Use when implementing shared connection pool for multiple services in same application - provides complete setup steps for FastAPI/multi-service apps without needing examples

Use when setting up pgdbm database connections, migrations, or multi-service architecture - provides mental model of one pool/many schemas/template syntax and complete API reference without needing to read docs

Use when creating llmring.lock file for new project (REQUIRED for all applications), configuring model aliases with semantic task-based names, managing environment-specific profiles (dev/staging/prod), or setting up fallback models - lockfile creation is mandatory first step, bundled lockfile is only for llmring tools

Use when starting a new project with llmring, building an application using LLMs, making basic chat completions, or sending messages to OpenAI, Anthropic, Google, or Ollama - covers lockfile creation (MANDATORY first step), semantic alias usage, unified interface for all providers with consistent message structure and response handling

Use when switching between LLM providers, accessing provider-specific features (Anthropic caching, OpenAI logprobs), or using raw SDK clients - covers multi-provider patterns and direct SDK access for OpenAI, Anthropic, Google, and Ollama

Use when building real-time chat interfaces, displaying incremental LLM responses, or streaming output from OpenAI, Anthropic, Google, or Ollama - async iteration with usage tracking works across all providers

Use when extracting structured data from LLMs, parsing JSON responses, or enforcing output schemas - unified JSON schema API works across OpenAI, Anthropic, Google, and Ollama with automatic validation and parsing

Use when implementing function calling, tool use, or agents with LLMs - unified tool API works across OpenAI, Anthropic, Google, and Ollama with consistent tool definition and execution patterns

Use when getting started with llmemory document storage and search - covers installation, initialization, adding documents, vector search, hybrid search, semantic search, BM25 full-text search, document management, and building RAG systems with multi-tenant support

Use when building search systems that need both semantic similarity and keyword matching - covers combining vector and BM25 search with Reciprocal Rank Fusion, alpha tuning for search weight control, and optimizing retrieval quality

Use when search queries need better recall through query expansion - generates multiple query variants, retrieves with each, and fuses results using RRF for improved retrieval quality especially with ambiguous or under-specified queries

Use when building SaaS applications needing data isolation between customers - implements owner-based filtering for secure multi-tenant document storage and search with workspace, organization, or tenant-level separation

Use when building Retrieval-Augmented Generation systems - covers document ingestion, hybrid search retrieval, reranking results, and prompt augmentation for accurate LLM responses grounded in your knowledge base