prose-guide

Guide AI-native development using the PROSE methodology — Progressive Disclosure, Reduced Scope, Orchestrated Composition, Safety Boundaries, Explicit Hierarchy. Use when: setting up AI-native projects, creating agent primitives (.instructions.md, .prompt.md, .agent.md, .spec.md), designing context engineering strategies, implementing spec-driven workflows, choosing agent delegation strategies (local vs async vs hybrid), scaling AI development to teams, assessing PROSE maturity level, or optimizing context window utilization. Also use when user mentions 'AI-native', 'agent primitives', 'context engineering', 'spec-driven development', 'AGENTS.md', 'agentic workflows', or asks how to make AI coding more reliable and repeatable.