Art & Design

ทำโปรไฟล์หน้าเดียว (one page) ว่าผู้ใช้เก่งอะไร นิสัยเป็นอย่างไร โตมาอย่างไร และไปต่อสายงานไหนได้ จากประวัติการใช้ Claude Code ในเครื่อง (และเครื่องอื่นผ่าน ssh) + แบบทดสอบ + สัมภาษณ์ · ใช้เมื่อผู้ใช้ขอ "ดูประวัติแล้วบอกว่าผมทำอาชีพอะไร เก่งแค่ไหน", "ทำ portfolio / โปรไฟล์ / one page ของผม", "ผมควรได้เงินเดือนเท่าไหร่", "ผมควรไปสายไหน", หรือพิมพ์ /portfolio-kup

Full-cycle design quality skill for AI-generated interfaces — evaluate, critique, and fix. Uses parallel subagents for Review and Fix modes. Detects AI slop (purple gradients, gradient text, glow effects, emoji icons, card-grid filler, Inter-everything typography, generic layouts) and guides creation with a product direction framework and investment gates. Use WHENEVER: reviewing or auditing a UI, asking if something looks AI-generated, looks like a template, feels generic, or has no character; creating a new page, dashboard, app screen, or landing page; redesigning, unslopping, or polishing an existing screen; improving any frontend interface. Even if the user does not say "design quality" — if they're building or evaluating any UI, use this skill. Produces: slop audit, scored critique (8 dimensions), P0–P3 fix list, creative direction, and code corrections. Works on React, Tailwind, HTML/CSS, Vue, Svelte, dashboards, apps, landing pages, components. Triggers on: "review this design", "does this look AI?", "

Site que não tem cara de "feito por IA": imagens de referência (Pinterest, fotos do cliente, um convite já impresso) viram um estilo medido (paleta + prompt de estilo), a IA PERGUNTA e PESQUISA antes de gerar, todas as imagens saem no mesmo estilo (Codex image_gen pela assinatura, com as referências anexadas), a página ganha transições em código e passa por um portão "visual × conversão" antes de publicar. Gatilhos: "/site-inspirado", "site a partir dessas referências", "site no estilo desta imagem", "site do meu casamento/evento", "landing que não pareça IA", "site bonito com imagens próprias". NÃO é para: filme na rolagem (site-movimento), filme da marca (filmarca), guia de projeto INEMA (projetos-landing-guia).

A complete design system and implementation guide for reproducing the

이력서를 바탕으로 개인 이력서 포트폴리오 웹사이트를 만든다. 템플릿 여섯 가지를 웹에서 미리보기로 비교하고 하나를 고른 뒤, 사용자의 이력서(PDF, DOCX, 텍스트)와 추가 정보를 채워 넣는다. "이력서 사이트", "포트폴리오 만들어줘", "내 경력으로 웹사이트", "resume website", "personal portfolio site", "이력서 템플릿 골라줘", 이력서 파일을 주며 웹으로 만들어 달라는 요청, 기존 포트폴리오의 내용 수정이나 템플릿 교체 요청에 반드시 사용한다. 사용자가 포트폴리오라는 말을 쓰지 않고 "내 소개 페이지"나 "구직용 사이트"라고만 해도 사용한다.

Draw quiet illustrations of a real product's interface (white cards, text as bars, one part lifted, tinted in the product's colour, transparent background) for case studies, landing pages, READMEs, slides or docs. Use when asked for product illustrations, drawn screens, a case study visual, a hero or feature drawing, or "show the app without screenshots". Draws from the product's real screens, tints each project from its own accent, checks the geometry and writes SVGs.

Creative direction, design systems and frontend engineering that eliminate generic AI-generated UI. Use whenever building, redesigning, improving or auditing a website, landing page, portfolio, SaaS app, dashboard, e-commerce or agency site, or any frontend — and whenever the user says a UI looks generic, templated, "AI-generated", like every other site, or asks to make it unique, premium, distinctive or award-level. Derives a direction from the product before writing code, implements it with real tokens and working functionality, then verifies with a static slop scanner, a real-browser page check and a scored quality gate.

Turn a user-provided video into an Apple-style, scroll-driven website with smooth canvas video scrubbing, optimized WebP frame sequences, progressive loading, and responsive motion. Use for cinematic product reveals, landing pages, scrollytelling, image-sequence animation, and scroll-controlled video; also optimize generated frame assets.

Cria uma landing page (LP) do zero no Claude Code e publica na Cloudflare Pages, de graça e sem servidor: estrutura do projeto, texto tirado só da fonte, layout que funciona no celular, prévia local e online, publicação, domínio próprio, formulário que captura lead (banco D1 e/ou webhook pra CRM, Make, planilha), página de obrigado e aposentadoria de LP com 301. Use sempre que pedirem pra criar, montar, publicar, subir, duplicar ou ajustar uma landing page, página de vendas, página de captura, página de inscrição ou página de obrigado, ou colocar um formulário numa página, mesmo sem a palavra 'LP'.

Develop software through a separate domain architect and implementation agent, ADRs, and a graph of evidence. Use for ADR-driven development, architecture decisions requiring explicit user approval, implementation, and independent verification. Supports business and technical domains in Codex and Claude Code.

Gives every change to AI-built work its own version number (v1.2.3), keeps every version until the user deletes it, and lets the user compare versions or go back without losing work. Use whenever you create or edit files for a user over several turns (designs, web pages, apps, documents, code), even if they never mention versions, and whenever the user asks to save a version, see history, compare, undo, restore, roll back, or go back to an earlier or "the previous" version.

Entity resolution and record matching — find which records across one or more datasets refer to the same real person, company, place, or thing, then merge them into one trusted "golden record" with full source history. Use this skill whenever the user wants to deduplicate a list, merge customer/patient/contact/vendor files, match records without a shared ID, link addresses, clean a CRM, build a master data (MDM) pipeline, score fuzzy name matches, choose blocking keys, set match thresholds, or a

智能戒指 / 健康穿戴品类「卖点文案 Guideline + 速评卡 + 改稿法则」。用于撰写、诊断、打分、改写标题 / 小标题 / 一句话卖点，以及审稿改稿，适用详情页、视频字幕、Meta/TikTok 广告、EDM 主题行、Google 搜索标题。触发词：「智能戒指文案」「戒指标题」「卖点文案」「标题速评」「文案打分」「标题诊断」「改稿」「审稿」「文案校正」「工程师语言」「翻译腔」「smart ring copywriting」「headline review」「copy scoring」「revision」。纯品牌口号创作与非健康穿戴品类不适用（规则可借鉴，品类词表不适用）。

Cost-optimized task segregation for building products and features. Captures the main task, saves it to a resumable ledger, splits it into atomic subtasks, scores each subtask's difficulty, routes it to the cheapest model + effort that can do it well (inline shell / haiku / sonnet / opus), batches subtasks that share the same model + effort into ONE subagent thread, runs independent batches in parallel waves, verifies with deterministic checks and escalates only failures one tier up. TRIGGER whe

Build web UI in a quiet industrial style distilled from game-menu conventions (paper and ink, one accent for "current" and "primary", selection that reads at a glance, pill secondary buttons, `//` path titles, faint closed contour lines). Use when asked for a page, portfolio, dashboard or component in this style, or in an "industrial", "terminal-like", "Endfield-inspired" or 终末地风格 look.

Release a new simctlhouse version end to end - bump the version, agree on release notes with the user, build the signed and notarized tarball with scripts/release.sh, tag, create the GitHub release, and publish the formula to the Homebrew tap. Use when asked to release, publish, ship or cut a simctlhouse version, or to update the Homebrew formula.

Improve a product's design in rounds until it is ready for real people: every user journey scores 9 or better from independent AI reviewers made by different companies, who agree within a point, with no high-severity fix open, held for two rounds. Uses at least two reviewers (for example Claude and Codex). Each round captures the same screens the same way, each reviewer drives the real product in a real browser in fresh context and scores every journey 0 to 10 with an "if fixed" score and specif

How this app is built, deployed, configured and kept alive on Data Clerk hosting (the data-clerk.com Kubernetes cluster). Use it whenever the user wants to deploy, publish, ship or "put live" the app, add or change an environment variable, API key or secret, edit secrets.env or use sops, install the tools for that, add a database table or migration, asks about the database, backups or restoring data, a domain or HTTPS, why the site is down or did not update after a push, the Dockerfile or the Gi

Raises the ceiling on a task before work starts, using the four kinds of ambition (speed, altitude, depth, range) from Felix Rieseberg's 13 October 2026 essay on being more ambitious with models. Use whenever someone commissions substantial work and the ask is pitched at the literal task rather than the outcome behind it: a tracker, report, letter, analysis, reconciliation, listing, plan, build or fix. Also use it on aim higher, be more ambitious, think bigger, what would an expert do, go deeper

Security and engineering red lines for designing, writing, or reviewing any website, backend, or API: hardened auth, injection prevention, business-logic and race-condition defense, high-concurrency database design, async-first architecture, API integrity and anti-tampering, secrets and operations, AI/LLM security, mobile and mini-program security, CORS and security headers, and scenario-aware 404 and indexing rules. 系统与网站开发的安全与工程红线：登录认证、注入与 XSS/CSRF/SSRF 防护、越权、业务逻辑与竞态、数据库高并发、异步架构、接口防抓包改包与重放、密钥运

Idiomatic use of the libraries and frameworks a project depends on: learning each one's model instead of reinventing the wheel or fighting the framework. Use before writing a general-purpose helper (retries, caching, pagination, concurrency, parsing, validation, date math); when building on or extending a library or framework (ORM, data-fetching client, UI kit, state manager, workflow engine, test runner); when a library, or the installed version of it, seems not to support what you need; when c

Run a repository's tests on Crucible (crucibl.sh) microVMs and act on the results. Use when asked to run the tests, check that a change passes, rerun failing tests, find out why CI or a PR check (`Crucible`) is red, handle flaky or quarantined tests, shard a slow suite, set up Crucible for a repo, or move GitHub Actions jobs onto Crucible runners (runs-on crucible-2vcpu-arm). Covers the hosted Crucible MCP server (run_tests, get_job, status, get_pr_check, actions_setup) and the `crucible` CLI.

Senior software-engineering partner for the whole code lifecycle — implementing changes, reviewing code and pull requests, assessing repositories, evaluating architecture and design proposals, finding and prioritising technical debt, planning and executing safe refactorings, security-focused code review (OWASP), improving tests, and writing ADRs. Use it whenever the user asks to review, audit, assess, refactor, clean up, harden or design code, or to implement a non-trivial change where maintaina

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