lovstudio

Analyzes one or more sample articles to extract a writing style profile (文风画像), then rewrites any target article in that exact style. Trigger when the user says: "分析这篇文章的文风", "模仿这个文风改写", "克隆某人的写作风格", "用 XX 的文风改写", "style clone", "rewrite in this style", or pastes articles asking for style analysis / imitation.

Analyze articles for AI-generated content indicators and rewrite to pass WeChat's 3.27 non-human automated content creation detection. Checks for template phrases, transition word density, sentence uniformity, paragraph pattern repetition, and other signals that WeChat uses to flag AI content. Outputs a risk report and an optional humanized rewrite. Use when the user wants to check if an article looks AI-generated, make an article more human-like, bypass WeChat AI detection, or humanize AI-written content. Also trigger when the user mentions "去AI痕迹", "人性化润色", "微信AI检测", "anti-ai-check", "humanize article", "公众号发文检查".

Generate professional slide deck images from content (Markdown, text, URLs). Creates outlines with style instructions, then generates individual slide images. Supports 16 visual styles, CJK/Latin mixed text, branding overlays, and PPTX/PDF export. Use when the user asks to "create slides", "make a presentation", "generate deck", "slide deck", "PPT", "做PPT", "生成幻灯片", "制作演示文稿", or wants to turn content into a visual slide deck.

Use when the user needs multi-source research with citation tracking, evidence persistence, and structured report generation. Triggers on "deep research", "comprehensive analysis", "research report", "compare X vs Y", "analyze trends", or "state of the art". Not for simple lookups, debugging, or questions answerable with 1-2 searches.

为文档原地插入 AI 配图。读取文档后全局规划插入点，并行生成所有图片， 异步插回原文。支持封面图、自定义比例和三种风格。 Use when: 用户要求为文档/文章/笔记生成配图、插图。 Also trigger when user mentions: 配图、插图、illustration、 generate images、document images、为文章加图。

Create event posters, exhibition posters, flyers, and promotional graphics from a brief. Outputs print-ready high-resolution PNG. Trigger words: 海报, poster, event poster, 展览海报, 展架, 活动海报, 宣传图, promotional, banner, flyer

Extract invoice data from images or text descriptions and generate a categorized Excel expense report. Supports receipt photos, scanned invoices, and manual text input. Auto-classifies into: business entertainment (客户餐费), travel-transport (机票/火车票/打车), travel-accommodation (酒店), travel-meals, office supplies, communication, and other. Use when the user mentions "发票报销", "expense report", "报销单", "发票整理", "invoice", "报销汇总", "发票分类", "reimbursement", or has invoice images to process.

Fetch a company/product logo from public sources (Clearbit, og:image, favicon) given a brand name or URL, score candidates (wide-aspect + transparent preferred), and archive the best + runner-ups to the configured logo collection directory. Trigger when the user says "find logo", "找 logo", "抓 logo", "收集 logo", "brand asset", "需要 <brand> 的 logo", or wants logos laid out for a website/PPT/poster.

Browse the XBTI Gallery — all community-created BTI personality tests at xbti.lovstudio.ai. Trigger when user says "XBTI Gallery", "xbti-gallery", "BTI列表", "浏览人格测试", "show BTI cases", or wants to see available BTI variants.

Create a complete custom BTI personality test (like LBTI, FBTI, etc.) based on the XBTI architecture. User provides a theme name and preferences, AI generates all content: dimensions, questions, personality types, descriptions, and avatar images via lovstudio-image-creator. Trigger when user says "创建BTI", "自定义人格测试", "make a BTI", "custom personality test", "XBTI变体", "xbti-creator", or mentions creating something like LBTI/FBTI/etc.

Convert Markdown documents to professionally typeset PDF files with reportlab. Handles CJK/Latin mixed text, fenced code blocks, tables, blockquotes, Obsidian callouts, inline images, emoji fallback, LaTeX-style formulas, cover pages, clickable TOC, PDF bookmarks, watermarks, and page numbers. Supports multiple color themes (Warm Academic, Nord, GitHub Light, Solarized, etc.) and is battle-tested for Chinese technical reports. Use this skill whenever the user wants to turn a .md file into a styled PDF, generate a report PDF from markdown, or create a print-ready document from markdown content — especially if CJK characters, code blocks, or tables are involved. Also trigger when the user mentions "markdown to PDF", "md2pdf", "any2pdf", "md转pdf", "报告生成", or asks for a "typeset" or "professionally formatted" PDF from markdown source.

Create new skills for the lovstudio ecosystem. Skills can be scaffolded as independent GitHub repos at lovstudio/{name}-skill or as bundled entries in the lovstudio/dev-skills aggregate repo under skills/{name}/. The workflow also sets up local symlinks for immediate use and registers the skill in the appropriate index (skills.yaml + README.md). Lovstudio conventions: Agent Skills-compatible `lovstudio-{name}` frontmatter, mandatory README.md per skill, `depends_on` frontmatter for required skill-level dependencies, AskUserQuestion interactive flow, standalone Python CLI scripts with argparse, CJK text handling, and a portable user configuration layer for local paths and brand settings. Use when the user wants to create a new skill, add a skill to the lovstudio ecosystem, scaffold a skill, or mentions "新建skill", "创建skill", "封装成skill", "new skill", "add skill", "scaffold skill", "生成skill".

Convert PNG images to high-quality SVG with optional white-background removal, vtracer spline vectorization, and svgo compression. Use when the user asks for "PNG to SVG", "png2svg", "转 SVG", "矢量化", "去白底", logo tracing, or converting raster icons into editable vector assets.

Fetch a company/product logo from public sources (Clearbit, og:image, favicon) given a brand name or URL, score candidates (wide-aspect + transparent preferred), and archive the best + runner-ups to the configured logo collection directory. Trigger when the user says "find logo", "找 logo", "抓 logo", "收集 logo", "brand asset", "需要 <brand> 的 logo", or wants logos laid out for a website/PPT/poster.

Analyze articles for AI-generated content indicators and rewrite to pass WeChat's 3.27 non-human automated content creation detection. Checks for template phrases, transition word density, sentence uniformity, paragraph pattern repetition, and other signals that WeChat uses to flag AI content. Outputs a risk report and an optional humanized rewrite. Use when the user wants to check if an article looks AI-generated, make an article more human-like, bypass WeChat AI detection, or humanize AI-written content. Also trigger when the user mentions "去AI痕迹", "人性化润色", "微信AI检测", "anti-ai-check", "humanize article", "公众号发文检查".

Review and annotate documents/contracts — output annotated docx with comments or tracked changes. Core: contract review (risk clauses, rights imbalance, vague wording, missing clauses); also general document review (grammar, logic, formatting). 批阅文档/合同 — 审阅任意文档并以批注或修订模式输出带标注的 docx。 核心场景：合同/协议审查（风险条款、权利义务、模糊表述、缺失条款）， 也支持通用文档审阅（语法、逻辑、格式）。 Trigger when: user asks to "审阅", "批阅", "批注", "review", "审查合同", "review contract", "review agreement", "annotate document", "check contract", "合同审查", "文档批注", or provides a document (.docx) for review.

Diagnose and repair application connectivity failures caused by Clash Verge Rev TUN routing, rule precedence, stale runtime state, proxy timeouts, or unusable IPv6 paths. Trigger for symptoms such as WeChat images failing to send, Moments images loading slowly, an app hanging after TUN is enabled, or requests unexpectedly matching DIRECT/proxy rules. Also trigger when the user mentions "Clash TUN 排障", "微信图片发不出去", "朋友圈图片加载慢", "修复微信 TUN 网络", or "diagnose Clash TUN app connectivity".

Adapt an existing web project for mobile devices: fix overflow, add responsive layouts, convert to multi-level page navigation with back support, handle notch/Dynamic Island safe areas, fix 100vh browser chrome issues, and optimize touch targets. Trigger when user says "mobile adapt", "移动端适配", "responsive optimization", "手机适配", "fix mobile overflow", "add safe area", "多级页面", "移动端布局", or mentions adapting a site for phones/tablets.

Generate or standardize Lovstudio apps, choosing web-only, PWA, or Tauri desktop case-by-case. Covers React/Vite or Next.js web apps plus Tauri + React + shadcn/ui + TanStack Query projects with Lovstudio branding, CI/CD, deploy/release, optional auto update, and lovinsp. Use when the user asks to create a Lovstudio app, web app, or Tauri app, initialize an app shell, apply Lovstudio app standards, or mentions "App生成器", "新建 Lovstudio Web App", "只创建 web", "生成跨端 App", "create Lovstudio app", or "Lovstudio app generator".

Optimize Tauri backend architecture and development ergonomics for Tauri 2 apps, especially Rust restart pain, oversized src-tauri/src/lib.rs files, excessive #[tauri::command] surfaces, stringly invoke APIs, long IPC streams, and dev-state recovery. Use when the user asks about Tauri hot reload, Rust-side restarts, "lib.rs 太大", "commands 太多", "降低到 100 个以内", "Tauri 后端优化", "optimize-tauri-backend", "Tauri backend refactor", or "Tauri dev reload".