Upstash Vector DB setup, semantic search, namespaces, and embedding models (MixBread preferred). Use when building vector search features on Vercel.

Develop production-grade Django applications with models, views, ORM queries, authentication, and admin interfaces. Use when building web applications, managing databases with Django ORM, and...

Use when a user asks a business question that requires querying data (e.g., "What were total sales last quarter?"). NOT for validating, testing, or building dbt models during development.

NEAR AI agent development and integration. Use when building AI agents on NEAR, integrating AI models, creating agent workflows, or implementing AI-powered dApps on NEAR Protocol.

Product types, sum types, semigroups, monoids, Eq, Ord, and building custom type class instances for domain modeling in TypeScript

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without...

Define how state changes over time through rules, triggers, and effects. Use when modeling state machines, defining workflows, specifying event handlers, or documenting system dynamics.

Production best practices for Cohere AI APIs. Covers model selection, API configuration, error handling, cost optimization, and architectural patterns for chat, RAG, and agentic applications.

Cohere reranking reference for two-stage retrieval, semantic search improvement, and RAG pipelines. Covers Rerank v4 models, structured data reranking, and LangChain integration.

Cohere Python SDK reference for chat, streaming, tool use, structured outputs, and RAG. Use when building Python applications with Cohere's Command models, embeddings, or reranking APIs.

Convene an LLM Council for deliberative multi-model reasoning. Uses 3-stage process (Query, Peer Review, Chairman Synthesis) for deeper analysis than simple consensus polling.

Analyzes conversations to extract patterns and workflows, then generates Skill.md files matching user's style. Use to convert successful chats into reusable skills.

Use this skill FIRST for any React UI or styling work. Enforces consistent TailAdmin design tokens, Tailwind utility grammar, reusable components, and dark mode parity.

Implement Command Query Responsibility Segregation for scalable architectures. Use when separating read and write models, optimizing query performance, or building event-sourced systems.

Implement Command Query Responsibility Segregation for scalable architectures. Use when separating read and write models, optimizing query performance, or building event-sourced systems.

Implement Command Query Responsibility Segregation for scalable architectures. Use when separating read and write models, optimizing query performance, or building event-sourced systems.

Implement Command Query Responsibility Segregation for scalable architectures. Use when separating read and write models, optimizing query performance, or building event-sourced systems.

Reviews FastAPI code for routing patterns, dependency injection, validation, and async handlers. Use when reviewing FastAPI apps, checking APIRouter setup, Depends() usage, or response models.

Formats markdown files according to best practices and common style guidelines. Use when cleaning up markdown documentation, ensuring consistent formatting, or standardizing README files.

Establish cause-effect relationships between events or states. Use when analyzing root causes, mapping dependencies, tracing effects, or building causal models.