Agent skills for Cursor

Flutter 3.27+ patterns — Riverpod 2 state with codegen, GoRouter 14+ navigation, Impeller rendering (default on all platforms), WASM web…

V1 instinct-based pattern capture for mobile development.

Memory persistence for mobile development context across sessions.

Eliminate mobile security misconfiguration against OWASP Mobile Top 10 M8.

Mobile offline-first architecture with local databases, CRDT conflict resolution, and background sync.

Build responsive, mobile-first web applications.

Automatically discover mobile development skills when working with iOS, Android, Swift, SwiftUI, React Native, mobile development…

Audits mobile app interfaces across Flutter and React Native builds for platform conventions, responsive layouts, touch targets, and…

Demonstrate Insufficient Cryptography (OWASP Mobile Top 10 M10) during an authorized mobile assessment — showing that an app's use of…

Use when positioning a MobiSys submission against the mobile-systems literature — offload, on-device ML, mobile OS and runtimes, sensing…

Use when deciding whether a project belongs at MobiSys — testing whether the core contribution is a mobile or embedded system…

Conducts rigorous pre-filing legal reviews and simulated hearings for Korean litigation through structured legal reasoning and statutory…

Simulate a study section / peer review of a draft grant — score it against the funder's actual criteria and write critiques as a skeptical…

MockDeviceKit for testing without physical glasses hardware

Automate Moco tasks via Rube MCP (Composio).

Run GPU workloads on Modal — training, fine-tuning, inference, batch processing.

Deploy GPU-enabled applications to Modal with pre-check workflow, optimization patterns, GPU pricing, WebSocket PTY best practices, and…

Comprehensive Modal.com platform knowledge covering all features, pricing, and best practices

Serverless GPU cloud platform for running ML workloads.

Automatically discover Modal platform skills when working with Modal.

Choose an ML model or provider when a user asks which checkpoint, router, local model, adapter, tokenizer, or inference backend fits a…