Results for “web”

Automate website interactions through a command-line browser tool. Navigate pages, fill forms, extract text, save screenshots or PDFs, reuse login sessions, and compare page states to check the effects of actions or website changes.

• Automating form entry and submission
• Extracting page text and saving screenshots
• Comparing page appearance before and after changes

Build and modify Native SDK apps with guidance on project structure, configuration, native features, packaging, and testing. Explains the default TypeScript and Native markup approach, plus WebViews, embedded web interfaces, and their permissions.

• Identify where to change an existing app
• Connect a web interface to native features
• Configure permissions for windows and dialogs

Assess web applications and APIs for SQL injection, where input changes database queries. The skill covers finding vulnerable inputs, testing different database systems, automating checks, and documenting findings with remediation suggestions.

• Assessing web application inputs for SQL injection
• Reviewing GraphQL and WebSocket injection risks
• Combining SQLmap automation with manual verification

Build animated videos with HTML and CSS for appearance and GSAP for motion, then export MP4 or WebM files. Create captioned narration, product tours, animated titles, and website-based videos, with checks for contrast and layout.

• Create animated titles and text intros
• Make narration videos with synchronized captions
• Turn a website into a promotional video

Create complex HTML artifacts for claude.ai using React and Tailwind. The skill follows Anthropic’s reference workflow to produce rich web content that can be embedded, supporting artifact development with these tools.

• Creating complex HTML artifacts for claude.ai
• Building web artifacts with React and Tailwind
• Preparing rich web content for embedding

Reproduce an existing website locally by examining source code, collecting assets, and checking browser behavior. Follow paths for static, framework-based, or graphics-heavy sites, then compare the result with the original and replace content as needed.

• Reproducing a website locally for study
• Examining WebGL or Canvas effects
• Comparing a recreation with the original site

Automate website navigation, form filling, screenshots, data extraction, and web app testing while keeping page state between scripts. Works with a fresh Chromium session or an existing Chrome session through an extension.

• Automating navigation and form entry
• Saving screenshots of web pages
• Extracting website data

Test a running web application with Strix to find authentication, access control, and other security flaws. Review working proof-of-concept exploits, which demonstrate each issue, and use the evidence to guide fixes and retesting.

• Security testing a staging web application
• Checking access between accounts and organizations
• Testing a local development server

Capture a public webpage through Latchshot and save a local PNG, JPEG, or PDF. Use viewport images, full-page screenshots, or website thumbnails for reports, visual checks, archives, and social previews.

• Save webpage screenshots for reports
• Capture full pages for visual quality checks
• Archive public webpages as PDFs

Help integrate the familiar full-page Zoom meeting interface into a web application. Covers SDK setup, joining meetings, interface options, event handling, and troubleshooting issues such as hidden meeting screens or invalid optional parameters.

• Embed the standard Zoom meeting interface in a web app
• Implement SDK initialization and meeting entry
• Handle participant and meeting status events

Plan and improve webinars from promotion through follow-up. Build event plans, reminder emails, and segmented outreach, then use funnel metrics—the steps from registration to purchase—to identify weak stages and prioritize fixes.

• Plan a webinar and its promotion calendar
• Improve low registration or attendance rates
• Write follow-up emails for attendees and no-shows

Reduce image file sizes by compressing individual files or whole folders into WebP, PNG, or JPEG. The skill selects an available compression tool automatically and lets you control quality, include subfolders, and choose whether to keep originals.

• Converting images to WebP
• Compressing a folder and its subfolders
• Adjusting compression quality

Build, test, and format CubeSandbox components using make targets and a Docker builder. Also covers the web dashboard’s development workflow, API type synchronization, and troubleshooting for missing services, outdated build tools, and environment requirements.

• Build all components or a specific CubeSandbox component
• Run component tests or a single targeted test
• Format Go and Rust code and lint the web interface

Build working web pages, components, and app interfaces around a clear visual concept. Coordinate typography, color, spacing, motion, and interaction details, adapting layouts to different screen sizes while avoiding repetitive visual templates.

• Building a landing page with a distinct visual direction
• Creating a dark-themed analytics dashboard
• Implementing responsive web components

Build a globe-like 3D visual in Three.js, a library for browser graphics. Combine a dense sphere of glowing particles with a thin orbital ring, then adjust color, density, tilt, and gentle motion.

• Adding a planetary particle visual to a website
• Creating a data-globe effect for an infrastructure service
• Matching orbital ring colors to a brand

当接入 webmcp-nexus-sdk 的项目中需要新增 WebMCP 工具函数、将现有业务方法改造为 WebMCP 工具函数，或配置 vite-plugin-webmcp-nexus / webpack-plugin-webmcp-nexus 时使用本技能。本技能约束工具函数的签名、JSDoc、TS 类型写法，并提供零风险的改造流程（仅改签名与注释，不动原方法业务逻辑）。触发示例："新增一个 WebMCP 工具"、"把这个函数改造成能被 AI Agent 调用的工具"、"让 xxx 函数接入 WebMCP"、"配置 webmcp 构建插件"。

The English summary is being prepared. Showing the original description.

吉里吉里Z (krkrz) の -replweb HTTP+SSE サーバ (WebServer クラス) にブラウザ UI を載せて、本体アプリの操作/編集/観測パネルをブラウザ側に組み込む方法論。ゲーム本体は 3D 表示やゲーム内 UI に専念させ、編集ツール・インスペクター・ダッシュボード・REPL コンソールをブラウザ (別ウィンドウ/別PC) から使う構成を作るときに読む。プラグインや TJS がサーバへエンドポイントを追加公開する手順 (WebServer.register / serveStatic / broadcast)、ハンドラ呼び出し規約 (req %[method,path,query,body,bytes] → 文字列/octet/整数/辞書)、状態同期パターン (fetch POST + SSE /sub push + throttle + 差分/tick 配信)、既存 REPL コンソール (/events + /cmd) の UI 埋め込み、ブラウザのアプリモード起動 (Chromium --app / -webui)、json.dll 連携、TJS2 由来のハマりどころ (ローカル関数クロージャ不在→クラス化 / ブロックコメントのネスト誤爆 / startup 例外の致命性 / ハンドラは必ずメインスレッド実行) を網羅。エンジン側 WebServer クラスそのものの仕様は krkrz core doc/REPL.md、REPL/Agent 駆動は skill krkrz-repl、Elements ネイティブ UI は skill elements、TJS2 言語は skill tjs2、本体 API は skill krkrz を参照。

The English summary is being prepared. Showing the original description.

Complete knowledge domain for Firecrawl v2 API - web scraping and crawling that converts websites into LLM-ready markdown or structured data. Use when: scraping websites, crawling entire sites, extracting web content, converting HTML to markdown, building web scrapers, handling dynamic JavaScript content, bypassing anti-bot protection, extracting structured data from web pages, or when encountering "content not loading", "JavaScript rendering issues", or "blocked by bot detection". Keywords: firecrawl, firecrawl api, web scraping, web crawler, scrape website, crawl website, extract content, html to markdown, site crawler, content extraction, web automation, firecrawl-py, firecrawl-js, llm ready data, structured data extraction, bot bypass, javascript rendering, scraping api, crawling api, map urls, batch scraping

The English summary is being prepared. Showing the original description.

Use Parallel from the terminal to search the web, extract page content, and conduct detailed research. Add researched fields to tables, discover matching companies or other entities, and monitor sources for changes.

• Comparing services through detailed web research
• Adding headquarters and revenue to company lists
• Discovering companies that match specific criteria

Create landing pages, websites, and app interfaces with restrained composition and a clear visual presence. The skill draws on OpenAI's frontend production playbook to guide the appearance and arrangement of interface elements.

• Creating landing pages with restrained composition
• Designing visually composed websites
• Creating app user interfaces

Build web pages and interface components with a clear visual direction and working code. Shape typography, colors, layouts, and animation around the intended audience and purpose, with support for HTML/CSS/JS, React, and Vue implementations.

• Build a landing page with a clear visual identity
• Refine a dashboard’s layout and typography
• Create React components with coordinated colors and motion

Investigate complex topics using web sources, stored knowledge, and relevant code. Break questions into smaller parts, compare evidence, and produce a structured report with confidence assessments, unresolved questions, and next steps.

• Investigating a complex topic through smaller research questions
• Comparing web sources with stored knowledge and code
• Summarizing evidence quality and conflicting findings

Export recorded AI usage costs and budgets as Prometheus metrics or JSON. Feed external dashboards with totals, model tier breakdowns, session costs, and budget utilization, or send the same data to a webhook endpoint.

• Refreshing cost metrics for Grafana or Prometheus
• Sending a one-time cost report to a webhook
• Providing budget utilization data for monitoring

Review visual design choices before creating or styling web pages, components, apps, dashboards, or interactive reports. It flags repetitive colors, typography, layouts, and motion patterns to avoid, while keeping explicit user requests and other specified styles in control.

• Review design choices before creating a web page
• Check repetitive card layouts in a dashboard
• Review typography and color choices in components