duet

Generate Architecture Decision Records that capture the reasoning behind technical decisions. Use when the user asks to "create an ADR", "document a decision", "record why we chose X", or discusses architectural trade-offs worth preserving.

Audit a workspace for recurring friction, pick the highest-leverage one, and build the automation that removes it. Use when the user asks "what should I automate", "what's wasting my time", "find the friction in my workflow", wants a self-improvement pass over their own tooling, or runs this on a recurring loop.

Ultra-compressed response mode. Cuts token usage ~75% while keeping full technical accuracy. Use when the user says "caveman", "caveman mode", "be brief", "less tokens", "compress output", or invokes /caveman.

Review what agents accomplished, surface loose ends across sessions

Systematic debugging that applies the scientific method to failures. Use when the user says "debug this", "why is this failing", "help me find the bug", or is stuck on a problem and thrashing without progress.

Intentional design thinking for interfaces, components, and systems. Use when the user asks to "build a UI", "design a page", "create a component", "make this look good", "design an API", "design a system", or any task where aesthetic or structural design decisions matter.

Create Excalidraw diagrams programmatically. Use when the user wants architecture diagrams, flowcharts, or any visual diagram with a hand-drawn aesthetic, where editable output and drag-and-drop editing add value over Mermaid's text-only approach.

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when the user wants to stress-test a plan against their project's language and documented decisions, or asks to "grill me with docs" or "interview me about this".

Evaluate and improve how information is organized for findability. Use when the user asks to "organize this", "restructure docs", "improve navigation", "where should this go", "review file structure", or when documentation grows beyond a single page.

Find deepening opportunities in a codebase. Use when the user asks to "improve architecture", "find refactoring opportunities", "consolidate modules", "make code more testable", or wants the codebase made more AI-navigable.

Enforce one term, one meaning across code, docs, UI, API, and commits. Use when the user says "we call this three different things", "align our terminology", "build a glossary", "what do we actually mean by X", or when a review surfaces the same concept under multiple names.

Create diagrams and visualizations using Mermaid.js v11 syntax. Use when generating flowcharts, sequence diagrams, class diagrams, state diagrams, ER diagrams, Gantt charts, user journeys, timelines, or any of 24+ diagram types. Supports CLI rendering to SVG/PNG/PDF, theming, and configuration.

Evaluate and improve names in code using naming as a design diagnostic. Use when the user asks to "name this", "rename", "review naming", "what should I call", struggles to name something, or when a code review surfaces vague or misleading names.

Profiling methodology and optimization strategy for performance work. Use when the user asks to "make this faster", "optimize", "profile", "reduce latency", "fix slow", "improve throughput", or when investigating performance regressions.

Reflect on recent work—capture learnings and surface what to think about next

Post-op check for artifacts, damage, and stale references after agent work