Build a lightweight 3D website — master prompt
Create a memorable 3D moment that respects the page’s loading and accessibility budget.
Build your own toolkit
Explore individual prompts, skills, plugins, and tools. Find what fits your task, understand why it helps, and set it up for your coding tool.
Create a memorable 3D moment that respects the page’s loading and accessibility budget.
Turn a recurring business question into a validated, rerunnable report with clear data boundaries.
Scope a coding-agent task, choose relevant context, and compare efficiency without sacrificing completion quality.
Search current OpenAI documentation through a read-only integration.
Give an AI agent browser inspection and interaction when the task requires it.
Keep tasks focused and compare usage alongside completion quality rather than prompt length.
Build a 3D scene when the interaction earns its rendering and transfer cost.
Make an explicit visual direction before implementing a new interface.
Use a reviewed browser-testing procedure for a local web application.
Deliver one complete user journey with honest state handling and useful verification.
Produce a sourced research or business report from supplied data while keeping observations, calculations, and recommendations distinct.
Add one integration because a task needs it, then verify its scope and connection.
Put stable project guidance and recurring procedures where your AI tool can discover them.
Retrieve focused library documentation when version details matter.
Run a reviewed repository workflow manually or on an approved schedule.
Give an agent scoped repository context and clearly authorized GitHub actions.
Find the dominant loading or interaction cost and prove whether a focused change helps.
Turn a vague failure into a reproducible case and a focused regression fix.
Find performance and accessibility leads, then verify actual fixes.
Verify a meaningful browser journey with observable assertions.
Create a concrete release package, verify environment requirements, and prepare a safe deployment.
Investigate a reported software defect and verify a minimal correction when a concrete failure or regression is supplied.
Produce a useful competitor comparison with traceable facts, dates, and explicit uncertainty.
Create a practical technical article whose claims can be traced to research and real evidence.