Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Category: Web & browsing
2,453 results · page 42 of 82
- View details
edgeone-pages-saasSkillWeb & browsing
This skill scaffolds and customizes a production-ready SaaS website on top of the TencentEdgeOne/saas-starter template (Next.js 14 + TypeScript + Tailwind + Supabase + Stripe + AI), and prepares it for deployment to EdgeOne Pages. It should be used when the user wants to start a new SaaS project, AI
Ready to connect★ 172
- View details
edgeone-pages-website-skeletonSkillWeb & browsing
Full-stack website generation solution based on EdgeOne Pages. When a user makes a single request (e.g., "build me an e-commerce site", "make an AI customer service site", "create an admin dashboard"), the AI automatically combines five major modules—Auth, Cart, Payment, AI Chat, and Admin—to genera
Ready to connect★ 172
- View details
portfolio-flowSkillWeb & browsing
Generates a complete designer portfolio website with admin login, portfolio CRUD management, AI-powered project description generation, theme customization (5 presets or custom hex), and visit analytics. Deploys to EdgeOne Pages with Edge Functions, KV Storage, JWT auth, and middleware. Use when a u
Ready to connect★ 172
- View details
saas-landing-genSkillWeb & browsing
Generate a complete SaaS landing page with EdgeOne Pages deployment. Includes hero section, features, pricing, testimonials, and CTA sections. Supports React + Tailwind CSS, one-command deploy to EdgeOne Pages.
Ready to connect★ 172
- View details
- View details
automating-the-browserSkillWeb & browsing
Use when extracting a page needs scripted interaction first — click, type, press a key, scroll, wait, screenshot, or run JS before capturing the DOM. Covers `crawlberg interact URL --actions` with the real action schema, result shape, limits, and external-CDP options.
Ready to connect★ 171
- View details
- View details
crawlbergSkillWeb & browsing
Crawl, scrape, and convert websites to Markdown using the local crawlberg CLI and its MCP server. Use when the user wants to fetch a page, follow links across a domain, enumerate URLs, or drive a real browser. Covers installation, the subcommands (scrape, crawl, map, interact, batch-scrape, batch-cr
Ready to connect★ 171
- View details
crawling-a-siteSkillWeb & browsing
Use when the user wants to follow links across a domain and capture every reachable page as Markdown. Covers `crawlberg crawl` with depth, page caps, concurrency, rate limiting, domain scoping, robots, and output selection.
Ready to connect★ 171
- View details
dev-cycleSkillWeb & browsing
Crawlberg iteration loops codified as Taskfile tasks — alef install/generate/format/bump, core and binding builds, e2e generate/build/test cycles, cleanup tiers, and the mock-server / stale-.so / precompiled-NIF / generated-e2e gotchas. Load when running or debugging crawlberg build, alef regenerati
Ready to connect★ 171
- View details
headless-fallbackSkillWeb & browsing
Use when a static fetch returns nothing useful and the page needs a real browser. Covers `--browser-mode auto|always|never`, external CDP via `--browser-endpoint`, symptoms of JS-only pages and WAF blocks, and the performance cost.
Ready to connect★ 171
- View details
mapping-urlsSkillWeb & browsing
Use when the user wants the list of URLs on a site rather than the page content — sitemap analysis, link planning, or seeding another tool. Covers `crawlberg map URL` with `--limit`, `--search`, robots, output, and how it differs from a full crawl.
Ready to connect★ 171
- View details
- View details
scraping-html-to-markdownSkillWeb & browsing
Use when the user wants a single page rendered as clean Markdown plus structured metadata. Covers `crawlberg scrape URL`, JSON vs Markdown output, what metadata is returned, and how to handle JS-heavy pages.
Ready to connect★ 171
- View details
serving-the-apiSkillWeb & browsing
Use when the user wants a long-running HTTP service for scrape/crawl/map instead of one-shot CLI calls or the MCP server — for example wiring crawlberg into other apps over REST. Covers `crawlberg serve`, the Firecrawl-v1-compatible endpoints, `--host`/`--port`, and when to prefer it.
Ready to connect★ 171
- View details
competitor-monitorSkillWeb & browsing
Monitor competitor websites, content changes, social activity, and market positioning through SandBase. Use when asked for competitive intelligence, competitor tracking, market positioning research, or competitive content monitoring.
Ready to connect★ 164
- View details
exa-similar-finderSkillWeb & browsing
Find web pages and content similar to a given URL using Exa's neural similarity search. Ideal for competitor discovery, alternative source finding, related content research, and expanding research beyond known sources.
Ready to connect★ 164
- View details
pricing-page-analyzerSkillWeb & browsing
Extract and analyze pricing information from competitor websites. Identifies pricing tiers, features per tier, billing models, and positioning relative to market alternatives. Ideal for competitive pricing strategy and market positioning research.
Ready to connect★ 164
- View details
site-auditSkillWeb & browsing
Audit a website's content, structure, SEO health, and technical setup through SandBase. Use when asked for website audit, content audit, SEO health check, site structure analysis, or technical assessment.
Ready to connect★ 164
- View details
tech-stack-detectorSkillWeb & browsing
Identify the technology stack powering any website — frameworks, CMS, analytics, hosting, CDN, payment processors, and marketing tools. Useful for competitive intelligence, sales prospecting, and technology landscape research.
Ready to connect★ 164
- View details
url-to-markdownSkillWeb & browsing
Convert any public web page into clean, structured Markdown. Preserves headings, links, images, code blocks, and tables while removing ads, navigation, and clutter. Perfect for content archival, knowledge base building, and research note-taking.
Ready to connect★ 164
- View details
website-monitorSkillWeb & browsing
Monitor any website for content changes, availability, performance, and security status. Combines page scraping, screenshot comparison, SSL monitoring, and security header checks for comprehensive website health and change detection.
Ready to connect★ 164
- View details
browser-02898b15SkillWeb & browsing
事件冒泡 / 事件-事件冒泡 / 浏览器事件——冒泡传播路 / 事件传播路径 / 目标 → 祖先链（冒泡顺。用户提到这些词时使用本技能。 场景：对照：浏览器事件——冒泡传播路径（目标→祖先链，DOM 事件冒泡语义）。 【不适用】Not for 以下场景：条件不满足即不适用（负路由：输入不满足生效条件时返回 None/不执行）
Ready to connect★ 164
- View details
browser-03b04f98SkillWeb & browsing
表单验证 / 浏览器-表单验证 / 浏览器表单——必填 / 邮箱 / 数字验证 / 必填 + 格式。用户提到这些词时使用本技能。 场景：对照：浏览器表单——必填/邮箱/数字验证（提交前校验）。 【不适用】Not for 以下场景：条件不满足即不适用（负路由：输入不满足生效条件时返回 None/不执行）
Ready to connect★ 164
- View details
browser-0754386dSkillWeb & browsing
Fetch请求 / 网络-Fetch请求 / 请求封装。用户提到这些词时使用本技能。 场景：对照：浏览器网络——Fetch API（请求方法/URL/头/体封装）。 【不适用】Not for 以下场景：条件不满足即不适用（负路由：输入不满足生效条件时返回 None/不执行）
Ready to connect★ 164
- View details
browser-093c03abSkillWeb & browsing
预加载 / 浏览器-预加载 / preload——关 / add 登。用户提到这些词时使用本技能。 场景：对照：preload——关键资源提前加载（命中统计）。 【不适用】Not for 以下场景：op 非 {add, stats, use} 时
Ready to connect★ 164
- View details
browser-09e60b35SkillWeb & browsing
画中画 / 浏览器-画中画 / open 打。用户提到这些词时使用本技能。 场景：对照：Picture-in-Picture——画中画窗口开关。 【不适用】Not for 以下场景：op 非 {active, close, open} 时
Ready to connect★ 164
- View details
browser-0ab4f2dbSkillWeb & browsing
网络记录 / 浏览器-网络记录 / 开发者工具 / record 记。用户提到这些词时使用本技能。 场景：对照：开发者工具网络面板——请求记录/过滤/汇总。 【不适用】Not for 以下场景：op 非 {filter, record, stats} 时
Ready to connect★ 164
- View details
browser-0c7f88d6SkillWeb & browsing
盒模型 / 渲染-盒模型 / 浏览器渲染——盒模型。用户提到这些词时使用本技能。 场景：对照：浏览器渲染——盒模型（padding/border 计入元素尺寸，margin 不计）。 【不适用】Not for 以下场景：条件不满足即不适用（负路由：输入不满足生效条件时返回 None/不执行）
Ready to connect★ 164
- View details
browser-0f598430SkillWeb & browsing
页面可见性 / 浏览器-页面可见性 / document.vis / set 切。用户提到这些词时使用本技能。 场景：对照：document.visibilityState——页面可见性（visible/hidden 切换）。 【不适用】Not for 以下场景：op 非 {events, get, set} 时
Ready to connect★ 164
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
54,764 of the 55,196 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.