Minimal example skill for plugin-eval tests. Use when the user wants a compact demonstration of a well-structured skill.

Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations, help choosing the latest model for a use case, or model upgrade and prompt-upgrade guidance; prioritize OpenAI docs MCP tools, use bundled references only as helper context, and restrict any fallback browsing to official OpenAI domains.

Vercel app and REST API expert guidance. Use when the agent needs live access to Vercel projects, deployments, environment variables, domains, logs, or documentation through the connected Vercel app or REST API.

Sets up, develops, tests, and deploys Render Workflows. Covers first-time scaffolding (via CLI or manual), SDK installation (Python or TypeScript), task patterns (retries, subtasks, fan-out), local development, Dashboard deployment, and troubleshooting. Use when a user wants to set up Render Workflows for the first time, scaffold a workflow service, add or modify workflow tasks, test workflows locally, or deploy workflows to Render.

Turn plugin-eval findings into a concrete rewrite brief for a Codex skill. Use when the user already evaluated a skill and now wants Codex to improve it, especially after asking what to fix first.

Best practices and example-driven guidance for building native macOS SwiftUI scenes and components, including windows, commands, toolbars, settings, split views, inspectors, menu bar extras, and keyboard-driven workflows. Use when creating or refactoring macOS SwiftUI UI, choosing scene types, wiring menus or settings, or needing desktop-specific component patterns and examples.

Resize a Canva design into standard social media formats and prepare export-ready results. Use when the user wants one Canva design adapted across multiple social platforms such as Facebook, Instagram, and LinkedIn, especially when they want all variants produced in one pass.

Triage an Outlook inbox into actionable buckets such as urgent, needs reply soon, waiting, and FYI using connected Outlook data. Use when the user asks to triage the inbox, rank what needs attention, find what still needs a reply, or separate important mail from noise.

Guide for controlling caching on Netlify's CDN. Use when configuring cache headers, setting up stale-while-revalidate, implementing on-demand cache purge, or understanding Netlify's CDN caching behavior. Covers Cache-Control, Netlify-CDN-Cache-Control, cache tags, durable cache, and framework-specific caching patterns.

Guide for running tests in the openai-dotnet repository. Use this when asked to run, debug, or validate tests, or when writing new tests. Explains test modes (Playback, Record, Live), how to identify recorded vs non-recorded tests, environment variable configuration, and what to do when recordings are missing or stale.

Triage failing macOS tests across Xcode and SwiftPM workflows. Use when asked to run macOS tests, narrow failing scopes, explain assertion or crash failures, or separate real test regressions from setup and environment problems.

SWR data-fetching expert guidance. Use when building React apps with client-side data fetching, caching, revalidation, mutations, optimistic UI, pagination, or infinite loading using the SWR library.

Analyze CSV files in /mnt/data and return concise numeric summaries.

Run the mandatory verification stack when changes affect runtime code, tests, or build/test behavior in the OpenAI Agents Python repository.

Analyzes web performance using Chrome DevTools MCP. Measures Core Web Vitals (FCP, LCP, TBT, CLS, Speed Index), identifies render-blocking resources, network dependency chains, layout shifts, caching issues, and accessibility gaps. Use when asked to audit, profile, debug, or optimize page load performance, Lighthouse scores, or site speed. Biases towards retrieval from current documentation over pre-trained knowledge.

Browser automation CLI for AI agents. Use when the user needs to interact with websites, verify dev server output, test web apps, navigate pages, fill forms, click buttons, take screenshots, extract data, or automate any browser task. Also triggers when a dev server starts so you can verify it visually.

Route early browser-game work. Use when the user needs stack selection and workflow planning across design, implementation, assets, and playtesting before moving to a specialist skill.

Connector-first Google Docs editing in local Codex plugin sessions with no Browser Use, target-document checks, connector-readback verification, and reference routing for formatting, citations, tables, and write-safety.

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Analyze and edit connected Google Sheets with range precision. Use when the user wants to create Google Sheets, find a spreadsheet, inspect tabs or ranges, search rows, plan formulas, create or repair charts, clean or restructure tables, write concise summaries, or make explicit cell-range updates.

Guide for deploying web frameworks on Netlify. Use when setting up a framework project (Vite/React, Astro, TanStack Start, Next.js, Nuxt, SvelteKit, Remix) for Netlify deployment, configuring adapters or plugins, or troubleshooting framework-specific Netlify integration. Covers what Netlify needs from each framework and how adapters handle server-side rendering.

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

Use for new frontend applications, dashboards, games, creative websites, hero sections, and visually driven UI from scratch, or when the user explicitly asks for a redesign/restyle/modernization. Builds from high-taste image-generated concept design with faithful implementation and browser testing.

Turn Notion specs into implementation plans, tasks, and progress tracking; use when implementing PRDs/feature specs and creating Notion plans + tasks from them.

Draft Outlook email replies safely from connected mailbox context. Use when the user wants to reply to a thread, decide whether to reply-all, prepare a draft before sending, or turn the latest Outlook message into a polished response.

Build polished one-day Google Calendar briefs. Use when the user asks for today, tomorrow, or a specific date summary with an agenda, conflict flags, free windows, remaining-meeting readouts, or a calendar brief, and the Google Calendar connector is available.

Route broad or ambiguous life-sciences research requests to the right skills, normalize core entities, optionally parallelize independent evidence gathering with subagents when available, and synthesize a concise evidence-backed answer. Use when a user asks a general life-sciences question that could span multiple sources or analysis types.

Find ways to open up meaningful free time in Outlook Calendar. Use when the user wants to clear part of their schedule, make room for focus time, create a longer uninterrupted block, or see the smallest set of calendar changes that would give time back.

Clean up Outlook newsletters and recurring subscription email safely. Use when the user wants to unsubscribe, separate newsletters from human mail, move recurring senders into folders, or organize low-signal subscription traffic without losing important messages.

Plan and execute runtime-behavior investigations with temporary probe scripts, validation matrices, state controls, and findings-first reports. Use only when the user explicitly invokes this skill to verify actual runtime behavior beyond normal code-level checks, especially to uncover edge cases, undocumented behavior, or common failure modes in local or live integrations. A baseline smoke check is fine as an entry point, but do not stop at happy-path confirmation.

Fix the tiny credit-note formatting bug and rerun the exact targeted test command.

Guide for upgrading Stripe API versions and SDKs

Triage a Gmail inbox into actionable buckets such as urgent, needs reply soon, waiting, and FYI using connected Gmail data. Use when the user asks to triage the inbox, rank what needs attention, find what still needs a reply, or separate important mail from noise.

Automatically convert Confluence specification documents into structured Jira backlogs with Epics and implementation tickets. When an agent needs to: (1) Create Jira tickets from a Confluence page, (2) Generate a backlog from a specification, (3) Break down a spec into implementation tasks, or (4) Convert requirements into Jira issues. Handles reading Confluence pages, analyzing specifications, creating Epics with proper structure, and generating detailed implementation tickets linked to the Epic.

Build, run, and debug local macOS apps and desktop executables using shell-first Xcode and Swift workflows. Use when asked to build a Mac app, launch it, diagnose compiler or linker failures, inspect startup problems, or debug desktop-only runtime issues.

Edit SharePoint-hosted spreadsheet files while preserving workbook structure, formulas, and formatting. Use when the user wants to update a real spreadsheet in SharePoint rather than summarize extracted sheet text.

Build polished one-day Outlook Calendar briefs. Use when the user asks for today, tomorrow, or a specific date summary with an agenda, conflict flags, free windows, remaining-meeting readouts, or a calendar brief, and Outlook Calendar is available.

Vercel Flags guidance — feature flags platform with unified dashboard, Flags Explorer, gradual rollouts, A/B testing, and provider adapters. Use when implementing feature flags, experimentation, or staged rollouts.

Use when validating Android feature flows in an emulator with adb-driven launch, input, UI-tree inspection, screenshots, and logcat capture.

Agent-specific guidance. Read `CLAUDE.md` first for repo map and commands.

This document provides comprehensive context and guidelines for AI agents working on this repository.

This `Agents.md` file provides detailed instructions for OpenAI Codex and other AI agents collaborating on this repository. It includes project structure, conventions, testing, and update policies.

> **TL;DR**

- `lib/` — Flutter/Dart source (features, services, widgets). Do not edit generated files (`*.g.dart`, `*.freezed.dart`).

This file contains build commands, code style guidelines, and development practices for agentic coding agents working in this netlab repository.

Look through the /docs folder to learn details about:

This is a Swift 6+ [client library](https://www.rabbitmq.com/client-libraries) for RabbitMQ heavily

This repository is organized as a set of AI skills plus validation tooling.

See [ARCHITECTURE.md](./ARCHITECTURE.md) for more information about how the code

This repository is a coding-interview practice workspace with a Tk/Ttk GUI for generating problem stubs, editing code, and running tests. Everything lives under `/Users/andrewzhao/Documents/coding_int