miketromba

Review a proposed code change using Codex's standard review rubric. Use when asked to review a diff, PR, branch, local change set, staged changes, or any code modification for actionable correctness, security, performance, maintainability, or regression findings.

Orchestrate an iterative code review and fix loop with Codex subagents. Use when asked to repeatedly review a local change set, staged changes, branch, or PR, delegate review to xhigh subagents using the code-review skill, have the same reviewer fix discovered issues, and repeat with fresh reviewers until no actionable findings remain.

Autumn billing and monetization platform documentation and guidance. Use when working with Autumn - an open-source billing control layer for AI and SaaS monetization. Triggers on questions about Autumn pricing, usage-based billing, feature gating, plan management, credit systems, metered billing, subscription lifecycle, Stripe integration via Autumn, check/track API, customer balances, entities, React billing hooks, CLI config, or ANY Autumn-related development tasks.

isolated-vm documentation and guidance for secure JavaScript isolation using v8 Isolates in Node.js. Use when working with isolated-vm - a native Node.js module providing access to v8's Isolate interface for running JavaScript in completely isolated environments with memory limits. Triggers on questions about isolated-vm, ivm.Isolate, v8 isolates, sandboxed JS execution in Node.js, cross-isolate references, ExternalCopy, Reference, Context, evalClosure, compileModule, or ANY isolated-vm-related development tasks.

QuickJS WebAssembly sandbox documentation and guidance for executing JavaScript/TypeScript securely. Use when working with @sebastianwessel/quickjs - a TypeScript package for running untrusted JS/TS code in an isolated QuickJS WebAssembly runtime. Triggers on questions about QuickJS sandbox, @sebastianwessel/quickjs, loadQuickJs, runSandboxed, evalCode, sandbox options, virtual file system, sandboxed fetch, custom modules in QuickJS, AI code execution in WASM, or ANY QuickJS sandbox-related development tasks.

Vercel Sandbox documentation and guidance for running untrusted code in isolated environments. Use when working with Vercel Sandbox - a compute primitive for safely executing AI-generated code, user-submitted scripts, or developer experiments in Firecracker microVMs. Triggers on questions about Vercel Sandbox SDK, sandbox CLI, @vercel/sandbox, Sandbox.create, snapshots, persistent sandboxes, sandbox authentication, sandbox pricing, sandbox system specs, microVMs, code execution isolation, or ANY Vercel Sandbox-related development tasks.

Astro web framework documentation and guidance. Use when working with Astro - an all-in-one web framework for building content-driven websites using island architecture and server-first design. Triggers on questions about Astro setup, .astro components, content collections, Markdown/MDX, islands, SSR, SSG, routing, integrations (React, Vue, Svelte, Preact, Solid), Astro config, deployment, CMS integration, migration, or ANY Astro-related development tasks.

Vercel for Platforms documentation and guidance for building multi-tenant and multi-project applications. Use when working with Vercel Platforms - building SaaS apps serving multiple tenants with custom domains, AI coding platforms, or any platform deploying multiple projects. Triggers on questions about multi-tenant architecture, multi-project platforms, wildcard domains, custom domains on Vercel, tenant middleware, Vercel SDK for platforms, platform elements, deploy actions, vibe coding platforms, or ANY Vercel Platforms-related development tasks.

Project issue tracking system. Use when creating, reading, updating, listing, searching, prioritizing, closing, reopening, or choosing project issues, tasks, bugs, improvements, or roadmap work.

Generate, edit, process, or batch-create AI assets with the ploof CLI. Use when working with generated images, videos, audio, arbitrary provider model endpoints, provider auth, asset manifests, image/video/audio context inputs, masks, OpenAI media jobs, fal.ai models, or agent-driven creative asset workflows.

Use the Loops CLI to manage contacts, send events, trigger transactional emails, manage mailing lists, and interact with the Loops (loops.so) email marketing platform. Use when the user asks to interact with Loops, manage email contacts, send transactional emails, or query mailing lists from the command line.

Use the Polar CLI to manage products, subscriptions, customers, orders, checkouts, license keys, webhooks, and other resources on the Polar (polar.sh) platform. Use when the user asks to interact with Polar, manage SaaS billing, create checkouts, issue license keys, or query monetization data from the command line.

Manage a Lemon Squeezy store from the command line. Use when the user needs to query or manage orders, subscriptions, customers, license keys, checkouts, discounts, webhooks, or any other Lemon Squeezy resource. Provides token-efficient output optimized for AI agents.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.