plugins

Best practices for Remotion - Video creation in React

Analyze product data and manage product tooling in PostHog. Use when the user wants product analytics or insights, HogQL/SQL queries, feature flags, experiments and A/B tests, error tracking, session replay, surveys, LLM analytics, dashboards, data warehouse, or PostHog documentation.

Help engineers evaluate a local skill or plugin, explain why it scored that way, show what to fix first, measure real token usage, benchmark starter scenarios, or decide what to run next. Use when the user says things like "evaluate this skill", "give me an analysis of the game dev skill", "why did this score that way", "what should I fix first", "measure the real token usage of this skill", or "what should I run next?".

Design custom metric packs for plugin-eval so teams can add local evaluation rubrics that emit schema-compatible checks and metrics. Use when the user wants their own evaluation criteria or visualizations.

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.

Evaluate a local Codex skill in engineer-friendly terms. Use when the user says "evaluate this skill", "give me an analysis of the game dev skill", "audit this skill", "why did this score that way", "what should I fix first", or asks for a skill-specific report before benchmarking it.

Evaluate a local Codex plugin in engineer-friendly language. Use when the user says "evaluate this plugin", "audit this plugin", "why did this score that way", "what should I fix first", "help me benchmark this plugin", or asks for a plugin-wide report before comparing versions.

Triage Outlook mail, extract tasks, clean up subscriptions, draft responses, and route shared mailbox work. Use when the user asks to inspect an Outlook inbox or thread, summarize open actions and deadlines, clean up newsletters, draft replies or forwards, organize mailbox follow-up work, or act on a delegated/shared Outlook mailbox.

Extract action items, deadlines, commitments, and owners from Outlook email threads and mailbox searches. Use when the user wants a task list from one thread, several related messages, or a mailbox slice, including who owes what and when.

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.

Work with delegated or shared Outlook Email mailboxes. Use when the user explicitly wants to read another mailbox, send from or on behalf of a shared mailbox, mark shared mail read or unread, move shared mail, or browse folders in a shared mailbox.

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.

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.

Handle Outlook Calendar workflows, including delegated/shared calendar writes. Use when the user asks for schedule understanding, availability checks, meeting scheduling, intelligent rescheduling, meeting prep, reminder updates, RSVP responses, recurring maintenance, travel coordination, deadline planning, or safe create, update, reschedule, respond, attach, delete, or cancel changes with timezone-aware event times and attendee validation.

Safely write to delegated or shared Outlook calendars. Use when the user explicitly wants to create, update, respond to, cancel, delete, or add a small attachment to an event on a shared or delegated Outlook Calendar.

Build a practical meeting prep brief from an Outlook Calendar event and its nearby Microsoft context. Use when the user wants to prepare for an upcoming meeting, understand what to read beforehand, pull in linked notes or docs, or get a concise brief on what the meeting appears to require.

Find and rank good meeting times for several people using Outlook Calendar data. Use when the user wants to schedule a meeting, compare candidate slots across attendees, find the best compromise time, or add a room/resource check after narrowing the attendee-compatible options.

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.

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.

Use when Codex is asked to build, run, test, debug, or configure an OpenAI-backed or provider-unspecified AI app, UI, script, CLI, generator, or tool, especially requests phrased only as "using AI" or generators driven by forms/user input; also use for OPENAI_API_KEY or sk-proj setup. Treat this as the credential gate: inspect safely, ask reuse-vs-new before API work, and never expose plaintext.

Use when an OpenAI API request fails and Codex needs to classify the likely cause, explain the next step, and route to the right follow-up. Covers common runtime failures such as blocked outbound network access, invalid credentials, exhausted API quota or credits, rate limits, and model, project, or organization access issues; delegate key provisioning to openai-platform-api-key and current documentation lookups to openai-docs.

Inspect a ChatGPT Apps MCP server codebase and generate chatgpt-app-submission.json with app info suggestions, tool hint justifications, test cases, and negative test cases, then report review-check findings and outputSchema warnings for submission review.

Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design tools, register UI resources, wire the MCP Apps bridge or ChatGPT compatibility APIs, apply Apps SDK metadata or CSP or domain settings, or produce a docs-aligned project scaffold. Prefer a docs-first workflow by invoking the openai-docs skill or OpenAI developer docs MCP tools before generating code.

Build, run, deploy, and evaluate OpenAI Agents SDK apps from Codex. Use when the user asks to create or adapt an Agents SDK app, build from a prompt or Codex thread, prepare a runnable agent prototype, add a focused eval harness, or deploy locally through the Agents SDK Deployment Manager.

Guide Codex through instrumenting or extending repositories with OpenAI Ads Measurement Pixel and optional Conversions API (CAPI). Use when adding Ads conversion tracking, browser pixel events, server-side conversion events, event_id deduplication, CAPI secret placeholders, incremental conversion coverage, or validating Ads conversion setup. Applies to local repositories and PR review contexts; prioritize safe, reviewable diffs and never place API keys or secrets in source code or client bundles.