Design visible and interruptible AI agent presence in apps, browsers, collaborative canvases, voice experiences, and spatial interfaces. Use when building an agent cursor, opt-in viewport follow, a take-over control, an avatar or voice, a capture indicator,…
Design the desktop and mobile experience for delegating a complete deliverable to an expert AI agent. Use for task mandates, bounded autonomy, checkpoints, progress and interrupt/resume, asynchronous notifications, reviewable previews and diffs, versioned…
Design assistants that learn a user's role, habits and preferences over repeated interactions with inspectable, correctable memory. Use for preference capture, inferred-versus-confirmed context, "why this suggestion," changing roles, periodic consolidation,…
Design and evaluate shared conversations where multiple AI agents address a person, delegate work, and surface asynchronous progress. Use for addressee routing, turn-taking, handoffs, activity receipts, cross-device inboxes, and notification policy. NOT for…
Design long-lived AI specialists that feel continuous when a person switches projects, workspaces, and devices. Use for agent identity, project-only versus portable memory, private-to-shared handoffs, scope indicators, and resuming after absence. NOT for…
Builds, rehabilitates, audits, and hardens premium production web apps from a durable design-system contract. Use for React, Next.js, or Vite apps, including dirty existing website repos and shared header/footer or navigation-system rehabilitation, where…
Maintain consistency across all winDAGs documentation surfaces — corpus documents, marketing copy, README files, site content, skill files, API docs, and derivative documents. Enforces the canonical terminology table, voice guidelines, architectural accuracy,…
Detects and fixes color contrast violations using WCAG 2.1 guidelines and perceptual analysis. Expert in contrast ratio calculation, color blindness simulation, and providing accessible alternatives. Activate on "check contrast", "color accessibility", "WCAG…
Expert in color theory, palette harmony, and perceptual color science for computational photo composition. Specializes in earth-mover distance optimization, warm/cool alternation, diversity-aware palette selection, and hue-based photo sequencing. Activate on…
Create bespoke OKLCH product palettes with harmonious shade ramps, semantic light/dark tokens, and clear uses across Tailwind CSS, shadcn/ui, native apps, marketing, logos, favicons, app icons, and Open Graph images. Use when choosing, completing, or…
Format, repair, and audit APA Style seventh-edition papers, author-date citations, and reference lists. Use for APA student or professional manuscripts, quotations, missing reference metadata, DOI handling, and APA generative-AI attribution. NOT for MLA or…
Format and audit MLA 9 papers, author-page citations, quotations, and Works Cited entries. Use for explicit MLA requests, MLA citation repairs, container decisions, or conversion to MLA. NOT for APA, Chicago, general proofreading, source discovery, or…
Decide when and how to build UI in Apple's Liquid Glass design system (WWDC25; iOS/macOS 26+, refreshed in 27) on SwiftUI, UIKit, AppKit and the web. Covers the layer model (glass is for the floating navigation/control layer, never the content layer), regular…
Strategic patterns for solving intractable problems through cascading approximation, self-improvement, and heterogeneous evaluation from DeepMind's AlphaGo system
Apply Conway's homomorphism principle to multi-agent system design, recognizing that agent coordination structure predetermines system architecture and capability.
Master dark mode UI design with atmospheric theming, WCAG accessibility, and cross-platform best practices. Specializes in weather/sky/ocean-inspired color systems that adapt to time of day and environmental conditions. Use when the user explicitly needs dark…
Use for sensemaking, frame revision, anomaly handling, questioning strategy, and ambiguity diagnosis with the Data/Frame model before action is chosen. NOT for deterministic classification, settled execution planning, or situations where the frame is already…
Builds a candidate-controlled preparation plan for a software-engineering interview target, timeline, and practice evidence. Use for planning round coverage, story coherence, mock cadence, and debrief-driven adjustments. NOT for hiring predictions, candidate…
Designs candidate-controlled mock interview practice across voice, text, code, and whiteboards. Use for session configuration, observable-evidence feedback, and adaptive practice plans. NOT for hiring decisions, emotion inference, gaze or integrity…
You are an expert at evaluating software projects for production readiness. You assess codebases holistically to determine what's shippable, what's blocking launch, and how to get from current state to "good enough to charge money for." Use when the user…
Use when designing, building, or debugging a Model Context Protocol (MCP) server in Node/TypeScript. Triggers: stdio JSON-RPC handshake, tool descriptions as discovery surface, lazy startup vs eager catalog loading, telemetry placement, schema design for tool…
Expert in Next.js 14/15 App Router architecture, React Server Components (RSC), Server Actions, and modern full-stack React development. Specializes in routing patterns, data fetching strategies, caching, streaming, and deployment optimization. Use when the…
Expert in implementing OAuth 2.0 and OpenID Connect (OIDC) authentication flows. Specializes in secure token handling, social login integration, API authorization, and identity provider configuration. Use when the user explicitly needs oauth oidc implementer…
Expert in writing OpenAPI 3.0/3.1 specifications. Produces specs that serve as enforceable contracts, not just documentation. Operates API-first: the spec is written and validated before any implementation code. Use when the user explicitly needs openapi spec…
Expert in end-to-end testing with Playwright, the modern cross-browser testing framework. Specializes in test generation, page object patterns, visual regression testing, and CI/CD integration. Handles complex testing scenarios including authentication flows,…
LLM-powered visual testing expert for automated screenshot capture, analysis, and UI verification using Playwright with multimodal inspection. Use when semantic screenshot review is needed across themes, flows, or regressions. NOT for one-off screenshots, raw…
Expert in PostgreSQL performance tuning, query optimization, and database administration. Specializes in EXPLAIN analysis, indexing strategies, connection pooling, partitioning, and production-grade PostgreSQL operations. Use when the user explicitly needs…