MANDATORY protocol for parallel agent execution when facing 3+ independent failures or tasks that can be investigated without shared state or dependencies - dispatches multiple Claude agents to investigate and fix independent problems concurrently
Azure PostgreSQL AI Integration - Vector search, RAG pipelines, and agent memory with pgvector and azure_ai extensions
Enforce honest, evidence-bound answers. Use when the user asks to be honest/truthful, expresses frustration or urgency, or when confidence is low and errors are costly.
Append conversation context to cumulative project history - never overwrites
Search and retrieve past decisions from Mother-Harness long-term memory
Retrieve relevant context from past sessions before starting implementation. Use when beginning work on a task, when the user describes what to build, when about to write significant code, or when stuck on a problem that may have been solved before.
Use this agent when the user asks questions ("Can Claude...", "Does Claude...", "How do I...") about Claude Code (the CLI tool) - features, hooks, slash commands, MCP servers, settings, IDE integrations, keyboard shortcuts, or the Claude API (formerly Anthropic API) - API usage, tool use, Anthropic SDK usage.
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
This skill should be used for quick inline brain-faithfulness validation during coding. Use when the user asks "is this brain-faithful?", "is this naming correct?", "should this be driver or modulator?", or similar quick neuroscience questions. For deep analysis or KB verification, recommend the neuro-expert agent instead.
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
A conceptual skill for guiding the Spec-Kit + Claude Code development workflow
Expert guidance for deploying Agno AGI agents and AI applications to production using Docker, FastAPI, monitoring, CI/CD, and cloud platforms
Technical implementation guide for the RLM REPL environment. Covers code patterns, llm_query usage, answer signaling, and common implementation patterns.
Gerencia memoria persistente do usuario. Use para salvar/recuperar preferencias, fatos aprendidos e contexto entre sessoes. Exemplos: 'lembre que prefiro respostas diretas', 'o que voce sabe sobre mim?', 'esqueca minhas preferencias'.
Configure and switch between LLM providers (OpenAI, Anthropic, Azure, Ollama). Use when managing AI model providers.
A test local skill for Claude. Use when testing local skills detection.
This skill should be used when the user asks about "Python best practices", "Pythonic code", "Python patterns", "Python idioms", "type hints", "dataclasses", "async Python", "Python decorators", "context managers"
