Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Compact the current conversation into a handoff document for another agent to pick up.
Build a throwaway prototype to flesh out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".
Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.
Author a new omp-native skill. Use when the user wants to capture a recurring workflow, create a skill from scratch, formalize a procedure into a SKILL.md, scaffold a new skill under ~/.omp/agent/skills/, or "turn this into a skill".