Explore

Capture Playwright screenshots and embed them in GitHub PR descriptions

in the skill textscreenshots) { await page.goto(url, { waitUntil: 'networkidle' }); await page.screenshot({ path: `screenshots/${name}.png`, fullPage: false }); } await browser.close(); ``` ### 2. Host screenshots on a temporary branch GitHub PR descriptions

Official·Skill·MIT·★ 5.4k in collection·No key

AI Agent Skill to generate and render beautiful Mermaid diagrams as SVG or terminal ASCII — 15 themes, 6 diagram types, batch CLI, no browser.

in the skill textlocally, without a browser. Pretty Mermaid converts Mermaid source into themed SVG, PNG, and terminal ASCII diagrams  ![Node.js Version ]( ![GitHub stars

Skill·MIT·★ 1.5k·No key

AI logo animation skill: turn raster logos into smooth SVG animation, animated HTML demos, GIF/video previews, and motion QA evidence.

in the skill textfor **logo animation**, **SVG animation**, and AI-assisted brand motion. It turns PNG, JPG, WebP, or screenshot logos into clean motion-ready SVG, then exports animated

Skill·MIT·★ 2.4k·No key

MCP server that turns text prompts into premium iOS mobile UI mockups (PNG + HTML). Powered by Claude (Opus 4.7) + Playwright. Two backends: local CLI or Anthropic API. MIT.

Node.js·MIT·★ 5·No key

Claude Code skill: design embedded LVGL (MicroPython) UIs with a headless render→PNG feedback loop. Auto-adapts LVGL 8.x/9.x. Validated on K230 CanMV.

Skill·MIT·★ 3·Few stars·No key

Measurable image + document toolkit. Bit-exact SVG from flat art (SSIM 1.0000, verified by rendering it back); beats potrace, imagetracerjs and vtracer on photographs. 11 raster formats, every pair co

in the readmesource *file*, not just of its pixels. 3. **Embed, re-encoded as PNG** — always renders exactly, but no longer carries the original file. Measured across every

Node.js·MIT·★ 17·No key

Generate evidence-grounded interactive software diagrams with offline HTML, SVG and PNG export.

Skill·MIT·★ 112·No key

Headless Inkscape SVG automation via FastMCP — 60+ ops: create, boolean, LPE, export, text, fleet pipeline. Batch without GUI tour. For Cursor / Claude Desktop. Webapp + Tauri.

in the readmepresets - Live Path Effects — bend, roughen, envelope, spiro, power stroke - Export to PNG, PDF, EPS, DXF - Fleet pipeline — hand off to GIMP, Blender, Unity, Resonite - LPEs

Python·MIT·★ 85·No key

不依赖模型的多模态能力，用 HTML/CSS 渲染生成图片的 Claude Code skill · 32 套风格 · 20+ 尺寸预设 · 零依赖导出 PNG

Skill·MIT·★ 30·No key

Agent Skill：把文章／筆記／逐字稿提煉成 IG 輪播知識圖卡。Markdown DSL → lint 把關 → Puppeteer 產出 1080×1350 PNG，深淺主題一次搞定

Skill·MIT·★ 14·No key

Claude Code skill for designer-quality .pptx slides — HTML/SVG → headless Chrome → PNG → python-pptx embed pipeline. Layers on top of Anthropic's pptx skill.

Skill·MIT·★ 3·Few stars·No key

agent 零指令产出中文图表的技能——单文件 HTML、断网可开、CJK 排版全内置

in the skill textcoding agent 提供一套生成中文图表的规则与资源。你描述图表要表达的内容，技能会选择合适的类型，按中文排版规范生成可直接使用的成品。** 默认使用白底和通用样式，输出独立 HTML；需要时也可导出 SVG 或 PNG。图表不依赖远程字体，适合保存、转发和离线打开。 ## 能做什么 - **45 种图表类型**：覆盖系统结构、流程、计划、数据比较和数据平台等任务。 - **中文排版**：内置中文字体栈、字号下限

Skill·MIT·★ 41·No key

Convert HTML slides to high-res PNG, WebP, and PDF — CLI, Web App, MCP Server

Node.js·MIT·★ 2·Few stars·No key

A sleek Regex visualizer with enhanced Chinese support and elegant diagrams

in the skill text字符类节点的配色与圆角 - 🈯 **原生 Unicode / 中文** —— 图标签直接显示中文，不再渲染成 `你好` 转义 - 📏 **中英混排宽度修复** —— `visualize` 内部按字符可视宽度计算，避免标题挤压 - 🖼 **PNG 图片导出** —— 颜色与圆角内联到 SVG，2× DPR 高清下载 - 📦 **零后端依赖** —— 单文件 HTML，可通过 ` ` 嵌入到任意页面 ## 快速试用 直接打开线上

Skill·MIT·★ 3·Few stars·No key

MCP server and CLI tool for browser screenshots (using Playwright and Python)

in the readmejust fetch its source. - Scrolling capture: single shot, frame series, or animated PNG of the whole scroll - Extracts visible text (Markdown) and optionally minified HTML alongside

Python·MIT·★ 3·Few stars·No key

Render self-contained Satori .mjs design files to PNG — any size, no browser. Claude Code skill + CLI + MCP server for OG cards, README cards, banners and covers.

Skill·MIT·★ 5·No key

Expose the ChatGPT desktop app's browser bridge (formerly Codex Desktop) as an MCP server — drive Chrome and Edge from Claude Code and other agents.

in the readmebrowser tabs - Navigate pages, go back/forward, wait for loads - Capture screenshots (viewport PNG) - Read DOM / accessibility trees (including ARIA role+name search) - Click, type, scroll — via

Node.js·MIT·★ 21·No key

Official MCP server for oJo — turn HTML into images. Free live previews need no API key.

in the readmeare free and need no account; an oJo API key adds hosted PNG and PDF URLs and reusable templates through the user's own account. Transport

Node.js·MIT·Few stars·No key

Make share-worthy slides, posters, videos & interactive HTML with local zero-API open-source tools + a real methodology · 用本地零-API开源工具与方法论，制作值得分享的幻灯片、海报、视频与可交互HTML

in the skill text青…）来展示色彩范围——而单次产出会守住一个强调色。所有源文件都在 `examples/` 。 **幻灯片**——一套用 Marp 写的 deck（ `slides-deck.md` ）导出为 PNG。标题陈述结论、一页一个想法、最后一页是 call to action： | | | |:---:|:---:| | 标题页 | Step 0 页 | | 情绪优先页 | 收尾页 | **具名版式

Skill·MIT·★ 3·Few stars·No key

Open-source Paseo themes and skins with a local theme builder, one-click Agent Skill, and safe macOS CDP loader

in the skill text和动态内联样式。 - Theme v2 提供公开 JSON Schema；加载前校验图片类型、SHA-256、字节数、尺寸和像素数。 - 一张本地 PNG、JPEG 或 WebP 即可自动取色并生成完整性可验证的主题，浏览器端不会上传图片。 - 每套公开主题都提供 Paseo ZIP 直下；浏览器点击后只拉取该主题的清单与原图，校验 SHA

Skill·MIT·★ 12·No key

Open-source MCP server that gives AI assistants a visual design canvas, rendering HTML/CSS scene graphs to PNG via headless Chromium.

Node.js·MIT·★ 13·No key

MCP server for the Screenshotty API: screenshots (returned inline to the assistant) and PDFs of any web page

in the readmeclaude_desktop_config.json` (Windows). ## Tools | Tool | What it does | |------|--------------| | `screenshot_url` | Screenshot a page (PNG, JPEG, WebP). Returns the hosted URL, plus the image inline when

Node.js·MIT·Few stars·Needs a key

MCP server for Infyicon — search 161,000+ free hand-drawn icons and fetch ready-to-embed SVG/PNG from Claude, ChatGPT, Cursor, VS Code and any MCP client. Hosted endpoint: https://infyicon.com/mcp (no

in the readmeSVG markup for 1–20 icon ids in one call. | | `get_icon_png` | Transparent PNG URLs at 16 / 24 / 32 / 64 / 128 / 256 / 512 px. | | `list

Hosted by author·MIT·Few stars·No key

MCP server to convert PDF/Word/PPT/Image/HTML to Markdown via MinerU API.

in the readme使用 Python requests 调用 MinerU API - 📄 支持多种格式：PDF, DOC, DOCX, PPT, PPTX, PNG, JPG, JPEG, HTML - 📁 支持本地文件自动上传解析 - 🔍 支持 OCR、公式识别、表格识别 - 🧠 智能参数自动配置（根据文件类型自动选择模型和参数） - 📦 大文件智能拆分（>200MB 自动物理拆分

Python·MIT·★ 5·No key

The Model Context Protocol (MCP) service based on DrissionPage provides AI assistants with powerful browser automation capabilities. | 基于 DrissionPage 的模型上下文协议 (MCP) 服务，为 AI 助手提供强大的浏览器自动化能力。

in the readmepython.exe", "args": [ "-m", "drissionpage_mcp.main" ], "env": { "PYTHONPATH": "Yourpath\\DrissionPage-MCP-Server\\src" } } } } ``` MCP配置效果 .png) ## 📱 使用案例 ### 网页自动化操作 ### 复杂页面交互 ### 基本使用示例 ```python # 连接浏览器 result = await connect_browser(port=9222, headless

Python·MIT·★ 26·No key

Local always-on server for SnapStack: receives browser captures and serves them to any MCP-capable LLM client over MCP (Streamable HTTP + stdio). Listens on 127.0.0.1 only.

in the readme/mcp (HTTP) ← MCP client ``` - **Capture** — the extension encodes the shot as WebP (PNG fallback), downscales it, and POSTs it here. - **Stack** — one image file (`.webp`/`.png

Node.js·MIT·★ 1·Few stars·No key

Glasses MCP is a simple MCP server that lets your AI agent see and capture the web 👓

in the readmevariety of popular phones, tablets, and laptops. * **Selectable Format:** Choose between `png` and `jpeg` image formats. * **Full Page or Viewport:** Capture the entire scrollable page

Node.js·MIT·★ 9·No key

A lightweight, self-contained, agent-first web engine written in Rust: fetch, DOM, layout, PNG/PDF rendering, CDP and MCP, no headless browser required

in the readmepágina — ver "Interacción: click, escritura y submit de formularios"; renderiza a PNG y PDF además de SVG — ver "Renderizado PNG/PDF"; se puede correr como servidor MCP

Skill·MIT·Few stars·No key

Render 32 diagram and chart types to SVG/PNG with browser preview and HTML reports.

in the readmedoes | Over HTTP | | ------------------------ | --------------------------------------------------------------------------- | --------- | | `render_diagram` | Render DGMO markup to **SVG or PNG** | yes | | `validate_diagram` | Check markup and report parse errors, without rendering | yes | | `sugg

Node.js·MIT·★ 3·Few stars·No key

Browser acceptance checks for agent-built web apps. Zero-key starter, CLI, MCP and GitHub Action; inspect explicit assertions and reports.

in the readmeexit 1 -> failed-report/report.html ``` Open either HTML report with its adjacent PNG file. The failing spec deliberately expects wrong text; inspect the assertion and screenshot

Node.js·MIT·★ 2·Few stars·No key

All-in-one MCP server for visual captures: terminal, code, browser, markdown, diffs, HTML, and PDF — via Playwright

in the readmeterminal screenshot of `git log --oneline -5` and a syntax-highlighted PNG of `src/index.ts`." The agent calls `capture_terminal` and `capture_file` — images land in `./captures

Node.js·MIT·Few stars·No key

Figma MCP server: list frames in a file and fetch one frame's JSON and image safely. Runs in production at Scalably.

in the readmetop-level frames in a file and fetch one frame's rendered PNG plus its node JSON and image-fill map into a local output directory

Node.js·MIT·Few stars·Needs a key

Turn a topic, URL, or draft into 800x800 Korean card-news images (카드뉴스). Agent skill for Claude Code & Codex CLI.

in the skill textKorean docs below).** --- ## What it produces - A set of **800×800 square PNG cards** (typically 8–15: cover → body → closing) - Each card follows a **kicker → headline

Skill·MIT·Few stars·No key

MCP Server that gives AI coding assistants QA testing capabilities — point at bugs, AI fixes them

in the readmecomputed styles + React/Vue component name | | Draw on a screenshot → done | Gets: annotated PNG as inline image content | | Type a behavior bug ("scroll doesn't auto-jump

Node.js·MIT·★ 4·Few stars·No key

a free, open-source 2D map editor for metroidvania games. Create connected rooms, paint tilemaps, and design minimaps. Export JSON for multiple engines, or automate with Lua, CLI, and MCP.

in the readmeback and connect the first room ## Configure Tile Palettes Import a grassland PNG into a color palette and update an existing room ## Resize, Rotate & Connect Rooms

Node.js·MIT·★ 1·Few stars·No key

Zyte API MCP — unified web fetch + AI extraction (zyte.com)

in the readmeAPI (rendered in a headless browser). Returns metadata about the base64-encoded PNG (its length) rather than inlining the full blob. Example: zyte_screenshot({ url: " _apiKey

Hosted by author·MIT·Few stars·No key

Official ImgVX AI MCP server: find the free browser image tool for any job (background removal, upscaling, compression, 87 tools, 40 languages) from Claude, ChatGPT, Cursor, VS Code, Zapier, Make or n

in the readmephoto, compressing to a file size, resizing, cropping or converting HEIC, PNG, JPG, WebP or PDF. - **Get a link in the user's language**: the most

Hosted by author·MIT·Few stars·No key

Browserless MCP — wraps the Browserless headless-Chromium REST API (browserless.io)

in the readmerendered page. Returns the image byte-length and metadata only (the binary PNG is NOT inlined). Example: browserless_screenshot({ url: " fullPage: true, _apiKey: "your-token" }) | | `browserless

Hosted by author·MIT·Few stars·No key

Design QR codes in your browser — live preview, gradient and dot styling, logo overlays, and shareable links. No backend, no accounts.

in the skill textrecipient's browser rebuilds the design with nothing stored server-side - **Export:** PNG at 2× resolution or SVG - **Workspace UI:** three-pane desktop layout

Skill·MIT·Few stars·No key

PolyDoc MCP server: HTML/URL to PDF, screenshots, and EU e-invoices (Factur-X / ZUGFeRD) for MCP clients.

in the readmePDFs, PDF/A and PDF/UA conformance). - **`polydoc_screenshot`** - HTML, URL, or template to PNG / JPEG / WebP, with viewport and device-pixel-ratio control. Returns an inline image

Node.js·MIT·Few stars·Needs a key

Archive any URL to a shareable snapshot (rrweb/pdf/png) + agent-driven web QA — an MCP server for siteglass.io. No CAPTCHA, no signup.

in the readmeselectable text, working links), a single-page **PDF**, or a full-page **PNG**. No CAPTCHA, no signup, no ownership check, callable programmatically — a bot-friendly alternative

Node.js·MIT·Few stars·No key

PhotoS——跨平台批量照片处理工具箱：给人用的 GUI，给 AI agent 用的 CLI / REST / MCP（统一版本化 JSON 契约）。RAW 解码、降噪、白平衡、LOG 还原、EXIF 打标、去重、智能选片、HTML 画廊、文件夹监视、预设。

in the readmeGUI | CLI | 说明 | |---|---|---|---| | 批量压缩 | ✅ | ✅ | JPEG/WebP/HEIC/AVIF 质量调优、色度子采样（444/422/420） | | 目标体积模式 | ✅ | ✅ | 自动调优质量以控制在目标文件体积以内 | | 格式转换 | ✅ | ✅ | JPEG / PNG / WebP / TIFF / BMP / HEIC / AVIF | | RAW 解码 | ✅ | ✅ | 22+ 种相机 RAW 格式，内置支持（rawpy/libraw

Python·MIT·Few stars·No key

MCP server that renders JavaScript SPA pages and extracts Markdown via headless Chromium

in the readmeCookies for auth | | `headers` | object | — | Custom HTTP headers | ### `spa_screenshot` Capture a PNG screenshot after JS rendering. | Parameter | Type | Default | Description | |-----------|------|---------|-------------| | `url` | string | — | URL to capture

Node.js·MIT·★ 1·Few stars·No key

MCP server that gives an agent a real browser: url to markdown, screenshot a url, url to pdf. No signup.

in the readmetools: - `read_page` turns any url into clean markdown - `screenshot` returns a png of the rendered page - `pdf` turns a url or raw html into

Node.js·MIT·Few stars·No key

GroupDocs.Viewer for .NET MCP server — render PDF, Word, Excel, PowerPoint, and image documents to HTML, PNG, JPG, or PDF and inspect view info via AI agents.

Skill·MIT·Few stars·No key

Gemini 3 Online is a web-based AI creative platform built around Google's Gemini Pro models and Veo 3 video generation technology. It gives users access to a suite of image and video creation tools di

in the readmelanguages for prompt input and outputs files in common formats including PNG, JPG, WebP, and 4K MP4, making it practical for both personal and professional workflows

Skill·MIT·Few stars·No key