Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading), reduced-motion, or the design foundations (feedback, spatial consistency, restraint) behind Apple-style interfaces.
This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.
Create or update public Gemini Power Kit website feature pages in this repository. Use when Codex is asked to document a new or changed feature on the Astro website, including user-facing feature explanations, screenshots, English and Chinese pages, SEO metadata, sidebar routes, and llms.txt updates.
Create, revise, review, or localize Gemini Power Kit Web Store product-detail copy in this repository. Use when a feature must be added to or rewritten in docs/web-store/product_detail/, including product positioning, English and Chinese draft approval, SEO-aware feature copy, i18n-subagent localization, and character-limit or locale-parity validation.
Live browser verification workflow for Gemini Power Kit on gemini.google.com using Codex's built-in chrome:control-chrome skill. Use when Codex has completed a feature, fixed a UI/runtime issue, or the user asks to verify plugin behavior on the live Gemini page, including settingPanel, SideNav entry, chat flows, temporary chats, model selection, quick follow-up, user-query/model-response interactions, or Gemini DOM selector checks.
Create or update Gemini Power Kit What's New releases. Use when Codex needs to plan or implement a What's New update for /Users/ronktsang/projects/gemini-chrome-plugin, including mandatory user confirmation of the promo image plan, mandatory user confirmation of whether to overwrite or append the existing config, 750x180 asset validation, concise release-note copy, locale updates via an i18n subagent, and code changes in src/entrypoints/content/overlay/whats-new/config.ts plus src/locales/*.json.
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.