Pi Prompting

Internal scaffolding for writing prompts that DeepSeek (and other models Pi might run) can execute reliably. You won't invoke this directly. It's guidance for the pi-rescue skill when it needs to delegate coding, review, or research tasks to Pi. The core idea is to prefer concrete checklists over vague instructions, always define what "done" looks like, and use stable XML-style blocks for task, output contract, grounding rules, and action safety. Ships with prebuilt review prompts and a recipe for splitting complex asks into single-purpose runs. Useful if you're building skills that orchestrate LLM subtasks and want a tested pattern for keeping those prompts tight and grounded.

Install to Claude Code

npx -y skills add agents365-ai/365-skills --skill pi-prompting --agent claude-code