Comprehensive Modal.com serverless cloud platform expertise. GPU-accelerated Python functions, web endpoints, scheduled tasks, and AI/ML deployments with automatic scaling and per-second billing. PROACTIVELY activate for: (1) ANY Modal.com task, (2) GPU configuration (T4, L4, A10G, L40S, A100, H100, H200, B200), (3) Container images and dependencies, (4) Web endpoints (FastAPI, ASGI, WSGI), (5) Scheduling (cron, periodic), (6) Volumes and secrets management, (7) Parallel processing (map, starmap, spawn), (8) Container lifecycle (@modal.enter, @modal.exit), (9) Deployment and CI/CD, (10) Cost optimization and pricing. Provides: Complete GPU selection guide with pricing, image building best practices, web endpoint patterns, scheduling syntax, storage primitives (Volume, Dict, Queue), parallel processing patterns, lifecycle hooks, CLI commands, GitHub Actions deployment, pricing tiers and optimization strategies.
/plugin marketplace add JosiahSiegel/claude-plugin-marketplace/plugin install modal-master@claude-plugin-marketplaceGuide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Automated code review for pull requests using multiple specialized agents with confidence-based scoring