A widely-shared X guide on setting up Claude with Projects, context, and prompting habits that unlock the 90% most people never use.

Practical guardrails for building Claude Skills that answer only from a provided knowledge base.

Andrej Karpathy's observations on LLM coding failure modes, codified into four principles. Now shipped as a Claude Code plugin under the Multica org.

Anthropic's guidance for getting the most out of Opus 4.7 in Claude Code: front-load specs, default to xhigh effort, use adaptive thinking prompts, and request parallel subagents explicitly.

Anthropic Claude Prompt Engineering Overview - Optimize model behavior with strategic prompts.

a game-changing AI model for text-to-image (art) generation