Awesome Agent Toolkit

Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.

Generate or update a project-level Product Requirements Document (PRD.md) after the user and AI have already discussed requirements, target users, product goals, implementation approach, workflow, and key technical decisions. Focuses on product overview, vision, core objectives, user personas, high-level feature groups, tech stack, system architecture key components, and phased roadmap / future work. Use when the user asks to create a PRD, write a product PRD, document project requirements, summarize the whole project direction, or produce a global project context file for future AI implementation work. Do not use for single-feature specs, acceptance criteria, detailed technical design, or implementation tasks.

Guide 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.

Safely query and summarize remaining Codex manual rate-limit reset credits and their expiration times without exposing local ChatGPT credentials or profile data. Use when the user asks about Codex banked resets, manual resets, reset credits, remaining reset count, earned reset count, reset status, or reset expiration.

IELTS Writing Task 1 examiner — evaluates, corrects, and rephrases Academic or General Training Task 1 essays. Use when the user pastes an IELTS Writing Task 1 question and their essay and wants: (1) band scores on each official criterion (TA, CC, LR, GRA) plus an overall band score, (2) inline Markdown corrections on the original essay (strikethrough errors, inline code for corrections), (3) detailed correction analysis, (4) a Band 7–9 model answer with selective HTML highlighting, (5) model answer analysis, and (6) a topic language bank covering chart/letter collocations, useful phrasal verbs where natural, high-band vocabulary, and synonyms. Triggers on phrases like "批改 Task 1", "evaluate my IELTS writing", "IELTS Task 1 correction", or any submission of an IELTS Task 1 prompt + essay.

IELTS Writing Task 2 examiner — evaluates, corrects, and rephrases Academic or General Training Task 2 essays. Use when the user pastes an IELTS Writing Task 2 question and their essay and wants: (1) band scores on each official criterion (TR, CC, LR, GRA) plus an overall band score, (2) inline Markdown corrections on the original essay (strikethrough errors, inline code for corrections), (3) detailed correction analysis, and (4) a Band 7–9 model paraphrase with analysis, and (5) a topic language bank covering collocations, phrasal verbs, high-band vocabulary, and synonyms. Triggers on phrases like "批改 Task 2", "evaluate my IELTS writing", "IELTS Task 2 correction", or any submission of an IELTS Task 2 prompt + essay.