.agents

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.

Reviews code diffs, PRs, issue queues, release readiness, commits, pushes, publishing, and project audits. Use when users ask review/看看代码/合并前/看看issue/PR/release/push or to implement an approved plan, with safety gates for dirty and untracked worktrees. Not for exploring ideas, debugging root causes, or prose review.

Produces distinctive, production-grade UI for pages, components, visual interfaces, typography, and screenshot-driven polish. Use when users ask 设计/做页面/做组件/UI/前端/截图 or say a screen is ugly, unclear, inconsistent, or visually wrong. Not for backend logic or data pipelines.

Runs a budget-aware agent-assisted engineering health audit for instruction/config drift, hooks/MCP, verifier surfaces, and AI maintainability. Use when users ask 检查claude/检查codex/检查pi/配置检查/健康度 or report agents ignoring instructions, missing validation, or code becoming hard to maintain. Not for debugging code or reviewing PRs.

Finds root cause before applying fixes for errors, crashes, regressions, failing tests, broken behavior, and screenshot-reported defects. Use when users ask 排查/报错/崩溃/不工作/回归/判断为什么报错, or say something used to work and now fails. Not for code review or new features.

Typeset professional documents and product landing pages: resumes, one-pagers, white papers, letters, portfolios, slide decks, landing pages. Warm parchment, ink-blue accent, serif-led hierarchy. CN uses TsangerJinKai02, EN uses Charter, JA uses YuMincho (best-effort). Triggers on "做 PDF / 排版 / 一页纸 / 白皮书 / 作品集 / 简历 / PPT / slides / Marp / markdown slides / マークダウンのスライド / 落地页 / 官网 / landing page / product page", or "build me a resume / make a one-pager / design a slide deck / turn this into a PDF / make this presentable / create a landing page".

Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask 看这个链接/读一下/read this/check this URL. Not for local text files already in the repo.

Turns rough ideas into approved, decision-complete plans with validated structure before coding. Use when users ask 出方案/给方案/深入分析/怎么设计/有没有必要/值不值得/plan this/how should I/should we keep this for features, architecture, or value judgments. Not for bug fixes or small edits.

Rewrites and polishes prose in Chinese or English, removes AI-like wording, and reviews product localization copy while preserving intent for drafts, docs, release notes, launch copy, and social posts. Use when users ask 帮我写/改稿/润色/去AI味/写一段/审稿/本地化文案/tweet/rewrite/proofread. Not for code comments, commit messages, or inline docs.

Runs a six-phase research workflow that turns unfamiliar domains, source bundles, or collected material into publish-ready output. Use when users ask 学习一下/深入研究/研究一下/整理成文章/deep dive/compile sources or need one coherent reference from many inputs. Not for quick lookups or single-file reads.

Rewrite documentation with localization-aware style for a specified audience. MUST use when the user mentions any of these actions on a document: 重写/改写/润色/本土化/翻译/转写/rewrite/rephrase/localize/translate/polish/adapt. Also trigger when user says "写成中文/英文", "用中文重新写", "make this more natural", "这个文档读起来像翻译", "帮我改成面向XX的", or provides a doc asking for better wording, tone adjustment, or audience adaptation. Covers: markdown docs, specs, READMEs, design docs, product docs, guides, changelogs.

Generate rich, interactive, self-contained HTML artifacts instead of Markdown. Use this skill whenever the user asks for visual output that Markdown can't express well — explorations, code reviews, design systems, prototypes, research reports, slide decks, diagrams, status reports, or custom editing interfaces (triage boards, feature-flag editors, prompt tuners). Also use when the user says "make an HTML file", "make an artifact", "visualize this", "show me a comparison", or asks for anything interactive, spatial, or presentation-quality. Even if the user just asks for a "report" or "summary", consider whether HTML would serve them better than Markdown — if the content has tables, metrics, code diffs, timelines, or multiple sections, it almost certainly will.

Drizzle ORM best practices, schema patterns, relational queries, CRUD operations, migrations, and TypeScript type inference. Activate when working with drizzle-orm imports, database schemas, queries, or migrations in any TypeScript project.

Create comprehensive technical design documents in Chinese for software projects. Use when the user requests technical architecture design, system planning, or needs a detailed technical specification document (技术方案设计.md). Focus on gathering requirements, analyzing context, and producing structured design documents with architecture diagrams, component specifications, and implementation plans.