ZhanlinCui

每日资讯日报生成器。三阶段工作流：获取元数据、生成摘要、输出日报。 触发场景：每日新闻、资讯日报、信息监控、新闻聚合、daily news、生成日报。 也用于添加新信源（自动分析网页并生成 method 文件）。

所有联网操作必须通过此 skill 处理，包括：搜索、网页抓取、登录后操作、动态页面交互等。 触发场景：用户要求搜索信息、查看网页内容、访问需要登录的网站、操作网页界面、抓取社交媒体内容（小红书、微博、推特等）、读取动态渲染页面、以及任何需要真实浏览器环境的网络任务。

Use when creating new skills, editing existing skills, or verifying skills work before deployment

UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient. Integrations: shadcn/ui MCP for component search and examples.

Automate creating a GitHub repository and deploying a web project to Vercel. Use when the user asks to deploy a website/app to production, publish a project, or set up GitHub + Vercel deployment.

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 Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Generate bilingual GitHub release documentation (README.md + README.zh.md) from repo metadata and user input, and guide release prep with git add/commit/push. Use when the user asks to write or polish README files, create bilingual docs, prepare a GitHub release, or mentions release assistant/README generation.

Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks

Connect to Chrome via CDP proxy to automate web interactions — posting, scraping, form filling. Uses puppeteer-core (no bundled Chromium).

Short description — what this does and when to use it.

Orchestrate a multi-round implementation + review cycle. Use when coordinating a feature that requires implementation (FE/BE), design review (UIUX), security review, and QA verification. Ensures QA findings get routed back for fixes until clean.

Review recent edits and update all documentation including architecture docs, API specs, and edit history. Creates missing docs for new implementations.

Review code for best practices, modularity, scalability, abstraction, test coverage, redundancy, hardcoded values, type safety, performance, naming, API design, async patterns, config/env sync, template consistency, and documentation alignment. Generates detailed report with issues and recommendations.

Review recent edits and update all documentation including architecture docs, API specs, and edit history. Creates missing docs for new implementations.

[WHAT] Generate or edit images using AI via OpenRouter API (Gemini) [WHEN] User needs to create images, edit existing images, or generate visual content [TRIGGERS] generate image, create image, accompanying image, illustration, edit image

[WHAT] Generate Twitter/X operations strategy and weekly/monthly plan framework [WHEN] User needs a content calendar, posting schedule, or strategy plan for Twitter [TRIGGERS] operations plan, posting plan, weekly plan, monthly plan, twitter strategy, content calendar

[WHAT] Generate original X post drafts (NOT replies) via OpenRouter [WHEN] User needs new X content, hook options, or multiple draft variants [TRIGGERS] write tweet, generate tweet, compose post, viral tweet, X post draft

[WHAT] Complete X (Twitter) integration for social media automation [WHEN] Post/delete tweets, reply, quote, search tweets, manage engagement (like/unlike, retweet/unretweet, bookmark), follow/unfollow, mute/unmute, query user info/tweets/followers/following/likes, view home timeline, send/read DMs, account auth (check/bind/unbind/rebind)

[WHAT] Read and analyze images from URL or local path using OpenRouter vision models [WHEN] User asks to identify image content, OCR text, visual objects, or to explain what is in an image [TRIGGERS] view image, recognize image, image content, what is this image, image url, image path, analyze image, describe image, ocr image

[WHAT] AI-powered web search, answer generation, and content extraction [WHEN] Search the web, get AI answers with citations, find similar pages, extract URL contents [IMPORTANT] Always include current date/year in search queries for time-sensitive topics, and use --start-date to filter fresh results [TRIGGERS] search, web search, find similar, answer, research, extract content, get contents

Use when illustrating a Markdown article with high-finish editorial visuals, visual-bible planning, structured prompts, optional Qiniu upload, and inserted image references for article publishing workflows.

Use when converting Markdown into WeChat-compatible inline HTML with theme styles for preview, copy-paste, or downstream draft publishing.

Use when publishing HTML articles to WeChat Official Account drafts, especially when you need cover upload, automatic cover generation, body image rewriting, CSS-variable compatibility, or draft metadata like author and comment settings.

Use when generating a complete WeChat article from a topic, with optional source research, evidence tracking, illustration, HTML conversion, and draft-box publishing.

Memory-driven self-evolution layer for Agent Skills. Captures usage patterns, learns from errors, and automatically generates reusable knowledge. Use when you want your agent to learn from experience, track skill effectiveness, or generate improvement suggestions.

"[What this skill does]. Use when [trigger scenarios]."

Use when turning work experiences, internships, projects, hackathons, research, GitHub repos, folders, PDFs, screenshots, or Notion pages into private project retrospective assets for top AI FDE, AI Engineer, Agent Architect, AI Product Engineer, DevRel, product, research, or technical interviews; also use when optimizing hub pages that connect multiple projects.

Create minimalist, cinematic presentation decks in the style of the SpaceX IPO roadshow — pure-black slides, full-bleed photography faded into black with gradient scrims, uppercase light-weight headlines, and big white stat numbers. Use whenever the user wants a presentation/slide deck/pitch deck in a "SpaceX style", "minimalist black", "cinematic", "roadshow", or "Apple-keynote-like" aesthetic, or asks to turn an outline, topic, or content into such slides. The skill fetches and color-grades cohesive theme photography from Pexels and renders the deck to PDF + PNGs via headless Chrome.

Turn any long YouTube interview, talk, or podcast into high-retention Chinese short clips for Shorts/Reels/Douyin/TikTok. Triggers: YouTube URL + short clips / 切片 / 短视频 / 中文字幕 / hard subtitles. Pipeline: source fetch -> subtitle parsing -> candidate analysis -> user review -> clip export -> subtitle burn.

基于 Google ADK 5大设计模式的 Agent Skill 构建器。 用于从零创建高质量 Skills，或重构/评审现有 Skills。 触发场景： - "创建一个 skill" - "帮我写个 SKILL.md" - "这个 skill 怎么改进" - "如何设计一个 agent skill" - "review/audit/tidy an existing skill" - "哪个模式适合我的场景" - "skill 太复杂了，怎么拆分"