duet

Review what agents accomplished, surface loose ends across sessions

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

Survey the project and choose what to play next

Create Excalidraw diagrams programmatically. Use when the user wants architecture diagrams, system designs, flowcharts, or any visual diagram with a hand-drawn aesthetic. Outputs editable .excalidraw JSON files. Best for architecture overviews and presentations where the hand-drawn style and drag-and-drop editing add value over Mermaid's text-only approach.

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. Essential for inline documentation diagrams that render natively on GitHub.

Judgment linter for vibe-coded output — reads the energy of the code, not just correctness. Use when the user says "vibe check", "check this vibe code", "does this hold up", "sanity check this AI code", or after a fast generation session before committing.

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", "this doesn't work", "track down the issue", or is stuck on a problem and thrashing without progress.

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.

Apply Strunk's writing rules to prose—documentation, commits, error messages, UI text. Clearer, stronger, more professional. Also handles sharpening and tightening drafts by subtraction.

Design test strategy using Beck's Test Desiderata — which properties matter, which tradeoffs to make. Use when the user asks "how should I test this", "what tests do I need", "review my test strategy", "is this well-tested", or when planning tests for a new feature or refactor.

Framework for code review that captures context future maintainers need—concerns raised, alternatives rejected, risks accepted. Use for PRs, local changes, or architecture review when the decision matters more than the diff. Produces structured feedback with must-address issues, suggestions, and observations "for the record."

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.

Systematic technical investigation—evidence gathering, option comparison, and actionable recommendations. Use when the user asks to "research X", "investigate Y", "look into Z", "compare X vs Y", "how does X work", or needs analysis of libraries, APIs, frameworks, or architectural approaches.

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", struggles to place content, or when documentation grows beyond a single page.

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.

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.