Art & Design

Make blur and glass look premium in UI, and prove it's readable: Apple-grade frosted glass (a measured material with thickness levels, a lit rim and a tinted level), ready-made glass surfaces (sticky nav, sidebar/panel, dock, menu, dialog over a dimmed blurred page, toast, sheet), Liquid Glass refraction, progressive blur, blur reveals, glows and depth, with React, Vue, Svelte, Tailwind and native (SwiftUI, Flutter, React Native, Compose) guidance, plus contrast and frost checkers. Use this when

Operate Asana through asana-gate, the policy gateway that puts a declarative YAML policy in front of the Asana REST API for AI agents, as MCP tools (asana_*) and the asana-gate command line. Use this whenever a task touches asana-gate in any way: writing or fixing a policy (where/allow/deny scopes, constraints such as required members, title prefixes, rate limits and confirmations), running asana-gate commands, calling its MCP tools, reading its refusals (404 Not a recognized ID, 403 asana-gate:

Turn a product idea, MVP, or new feature into a scoped plan and an implementable backlog of vertical slices with acceptance criteria. Use this whenever the user wants to design, scope, shape, plan or "think through" an MVP, a new product, a new feature, an epic, or says things like "I have an idea", "let's plan this feature", "what should the MVP be", "break this down", "create a backlog", "create the tickets/issues/work items", or asks how to start building something. Works both inside a codeba

Turn any research paper into a comic-magazine style PDF story (A4, ~8 pages) that explains the paper smoothly with characters, panels and speech bubbles.

Estimates web tasks on Umbraco / ASP.NET Core sites (Razor, Vue or Nuxt front ends, Bellissima or AngularJS back-office extensions, uSync, Examine, Hangfire, multilingual and RTL) when an AI coding agent writes the code and a developer reviews it. Looks for a spec (spec.md, docs/spec) or feature plan (docs/plans) first and, if found, reads it in full and estimates per plan phase; if not, says so and gives a quick estimate of the visible scope. Reads the codebase, sizes the coding at agent speed,

Show the user what their coding agent actually sees in them. Reads local Claude Code / Codex session history and git repos (read-only, nothing uploaded), then produces one six-field card — a title, three real numbers, one roast line, one truth they haven't noticed, one idea only they can build — as a terminal card plus a screenshot-ready HTML card. Use when the user runs /mirror, says "mirror", "what do you really think of me", "roast me", "what do you see in me", "what have you learned about me

Designs, builds, tests and improves Claude skills from a first idea to a packaged .skill file. Use this skill whenever a user wants to plan, spec, create, validate, test, benchmark, fix or optimise a skill, or asks why a skill is not being picked up. Triggers on phrases like "design a skill", "create a skill for", "help me build a skill that", "improve my skill", "my skill is not triggering", "run evals on my skill", "optimise the skill description", "package my skill", or any request to work ou

Use when building, editing, validating, or debugging generic Tracecat automations through Tracecat MCP, including workflow DSL/YAML authoring, table design, unique indexes, run-python Tracecat imports, agent presets, ai.agent or ai.preset_agent workflows, executions, validation, and workflow best practices.

Prepares a travel-expense reimbursement claim (החזר הוצאות נסיעה) for an Israeli university after a conference trip abroad: collects receipts from the trip's receipts folder and from email (flight and add-ons, travel insurance, hotel, registration, conference dinner, poster printing, ground transport), saves each as a named PDF, and builds the Hebrew right-to-left expense spreadsheet from its bundled claim template, converting to shekels at Bank of Israel representative rates (שער יציג) and comp

Engineer Your Thing (EYT) acts as an engineering guide for AI agents building, changing or reviewing web apps and SaaS. Use when a user describes what to build but has not specified architecture, UX, accessibility, security, persistence, error states, readable code or verification. Proactively choose proportionate safeguards, avoid common AI-generated app/code anti-patterns, preserve approved designs and explain evidence. Do not use for unrelated one-line coding questions.

Plan and build apps and sites with user accounts and heavy user data the way large companies do, starting as a cheap MVP on managed providers and moving to big company infrastructure later without a rewrite. Use this whenever a new project is described, whenever someone asks which hosting, database, auth, cache, queue, storage, CDN or mobile stack to use, whenever an existing app needs to scale or move off a provider (Vercel, Supabase, Railway, Heroku, Firebase), and whenever a request touches a

Create or revise a project-specific DESIGN.md using the official Stitch specification, visual examples, and implementation mappings. Use when a designer needs to define or document a design system; not for ordinary page implementation or copying another brand's appearance.

Use when someone wants a new talk, slides, PPT or presentation (발표, 발표자료, 슬라이드, 피피티, 랩미팅·학회·세미나·수업·저널 클럽 발표), or wants to plan a talk's content. 발표 폴더를 만들고 발표자와 한 번에 질문 하나씩 정해 brief.md와 outline.md를 쓴 뒤, 승인받으면 talk-build로 넘긴다.

Gestor de tráfego da Meta (Facebook, Instagram, Messenger, WhatsApp) da agência de performance. Diagnostica exportações CSV do Gerenciador de Anúncios, desenha estrutura de campanha, escolhe objetivo e destino (mensagens, formulário, site), monta o passo a passo campo a campo, define quando pausar, manter, trocar ou escalar cada anúncio e cuida da fadiga de criativo. Use quando o pedido mencionar Meta Ads, Facebook Ads, Instagram Ads, Gerenciador de Anúncios, impulsionar, anúncio de WhatsApp/cli

跨平台、证据优先的深度分析研究方法。处理复杂问题、历史研究、经济产业分析、科技影响、因果辨析、争议议题及多轮讨论综合时使用；区分已知事实、推断、情景预测和未知，审查反例与现实约束，并按需采用真实图文表达。仅在用户要求时进行高保真 HTML/PDF 原稿导出；不用于简单问答或无需研究的日常对话。 A cross-platform, evidence-first method for deep analysis and research. Use it for complex questions, historical research, economic and industry analysis, technology impacts, causal analysis, contested issues, and synthesis of multi-turn discussions. Distinguish established facts, inferences, scenario forecasts, and unknowns; examine counterexamples

Find, cut and rank hackathon project ideas that solve a real, specific problem at its root, against a specific hackathon's rules, tracks, judging criteria, required tech and deadline. Use when choosing what to build for a hackathon, or when comparing or stress-testing candidate hackathon ideas.

Gestor de Google Ads da agência de performance. Monta e opera campanhas de Pesquisa (palavras-chave por intenção, tipos de correspondência, negativas, anúncios responsivos RSA, extensões), Local (Perfil de Empresa, chamadas, "perto de mim"), Performance Max e YouTube com travas; lê relatórios de termos de pesquisa e de campanha exportados em CSV; define lances por volume de conversões e importação de vendas offline. Use quando o pedido mencionar Google Ads, AdWords, anúncio no Google, campanha d

Membuat, menyusun, atau mengaudit brand board / brand guideline satu halaman dengan struktur section yang standar (hero, variasi logo, palet warna, tipografi, gaya bahasa, contoh penerapan, footer, maskot, ikon, pola background, dll). Punya dua cakupan - bertingkat (default) dan lengkap (semua section terisi). Gunakan skill ini setiap kali user minta dibuatkan brand board, brand guideline, brand identity sheet, style guide visual, prompt gambar untuk brand board, atau minta brand board baru "dis

Use para buscar, escolher, baixar e preparar a mídia grátis de um Short - vídeos do Pexels/Pixabay, trilha do Pixabay sem Content ID e efeitos sonoros - e cortar os clipes no formato vertical (1080×1920) ou de janela de TV (1000×750), incluindo o clipe invertido do loop.

Stage 2 of a wp-site-kit WordPress build - design direction, a static HTML/CSS prototype with design tokens, owner sign-off with screenshots, self-hosted fonts, and porting the approved look into a swappable WordPress skin. Use for "design the site", "new look", "redesign", "change colours or fonts", "make a new skin", "port the prototype to WordPress".

Stage 8 of a wp-site-kit WordPress build and everything after launch - backups with an off-machine copy, restore drills, the disaster-recovery runbook, credentials inventory, update policy, alerts, and working from more than one machine (bridge file, workstation doctor, encrypted state bundle, rescuing unpushed work). Use for "backup", "restore", "move to a new machine/server", "update plugins", "what if the server dies", "work from the cloud box", "set up a second machine".

Use when composing a page, view or feature from components that already exist in the project's design system. Assembles layout only; never invents new atoms, molecules or organisms. If a needed component is missing, stops and hands off to the atomic-design skill.

Dựng trang portfolio cá nhân kiểu điện ảnh cho bất kỳ ai - nền tối, chữ chìm khổng lồ (PORTFOLIO) phía sau ảnh người đã tách nền, tên to font Anton đứng trước, tiêu đề hai màu, thẻ năng lực có ảnh minh hoạ cùng một phong cách, dải chữ chạy công nghệ, ghi nhận/báo chí, học vấn + kỹ năng + quy trình + trích dẫn, hành trình, liên hệ; 30 AI agent dựng từng khối khi vào trang. Trang tĩnh (HTML/CSS/JS), mọi nội dung nằm trong một file data.js, đưa lên host nào cũng được. Dùng khi người dùng muốn "làm

Hiệu ứng xuất hiện "trang web đang được 30 AI agent dựng" cho bất kỳ web nào - 30 con trỏ màu có tên (layout-07, copy-12...) bay vào, mỗi khối nằm sau khung dây nét đứt, agent gần nhất kéo khung chọn có tay nắm và nhãn (h1.hero-title) rồi khối hiện ra trong khung đó; phần dưới được dựng khi cuộn tới; thanh trạng thái "30 agent · N chỉnh sửa · Bỏ qua". JS thuần không phụ thuộc thư viện, kèm bản bọc React/Next. Dùng khi người dùng muốn "hiệu ứng AI agent edit trang", "trang tự dựng lên", "con trỏ