Web Analytics

wzdavid/ThinkWiki

Use this skill when the user wants to create, maintain, query, or visualize a local Markdown knowledge base. ThinkWiki can initialize a wiki, import files or webpages, collect inbox items, answer from existing knowledge, save higher-value outputs, and generate HTML viewer and graph artifacts.

brettdavies/crawl4ai-skill

Use when scraping JavaScript-heavy pages or SPAs, crawling multiple URLs concurrently, extracting structured data with reusable CSS/JSON schemas, or building automated web data pipelines. Wraps the Crawl4AI library (`crwl` CLI and Python SDK) with schema-generation patterns for LLM-free extraction. Triggers on crawl4ai, crwl, scrape JS-heavy site, scrape SPA, headless browser scrape, schema-based extraction, batch crawl, sitemap crawl, web data pipeline. SKIP when a static HTML page can be read with `defuddle` / `fetch-web` — those are faster cold-start and don't need a browser.

OpenCesium/SuperGIS-Skills

Implement maps and geospatial visualization for OpenLayers, Cesium, Leaflet, MapLibre, Mapbox, maptalks, SuperMap, MapGIS, ArcGIS, GeoScene, AMap, Baidu Map, Tencent Map, Tianditu, KQGIS, NavInfo, Google Maps, Three.js, deck.gl, AntV L7, and MapV. Use when the user says supergis or names one of these libraries and asks for a map, layer, terrain, 3D Tiles, vector tile, GeoJSON, WMS, WMTS, draw, measure, query, or visualization. Open modules/<library>/index.md and the matching example, then adapt that example's full code to the host project.

TseringYuu/anyviz

Use when 用户请求选择、创建、改进或统一数据可视化，并需按数据与意图选择图表、主题及 D3.js、ECharts、Mapbox、Three.js、Matplotlib、Plotly 或 ggplot2 技术栈。

DrMultivac/notebooklm-learner-pack

Generate branded, topic-specific HTML NotebookLM Learner Packs — 29 copy-paste prompt cards (10 infographics + 5 slide decks + 5 audio overviews + 4 video storyboards + 5 knowledge tests) with a sticky dual-filter UI that toggles between six audience lenses (ELI5, Newbie, Clinical, Operator, Finance, Deep Dive) and five asset types. Triggers on "NotebookLM learner pack," "learner site," "learner prompts," "explainer prompt pack," "build a prompt library for [topic]," "make a NotebookLM pack on [topic] in [brand] voice," or the workflow of ingesting source material into NotebookLM and wanting a

qkgecn93/bys-personal-dashboard

不一书个人工作台生成器。通过一场引导式访谈，帮用户（包括完全不懂代码的人）做出一个属于自己的手机端个人工作台—— 左侧常驻功能栏、右侧卡片流，打开就是今日计划、打卡、记账、体重、日程、单词、树洞等自己每天真正要用的东西， 可以部署上线并添加到手机桌面，像一个 App 一样用。 当用户说"初始化不一书个人工作台生成器"、"初始化 bys-personal-dashboard"、"我想做一个自己的个人工作台"、 "抖音上那种个人工作台我也想要一个"、"把我的日常安排做成一个手机页面"时必须触发； 即使用户只是丢来一张别人的工作台截图说"我也想要这种"，也应触发。 已有工作台后说"给我的工作台加个XX功能"、"工作台换个配色"、"工作台改一下"时，走迭代流程而不是重新初始化。 用户没说"工作台"这个词时，用三个特征判断：①在手机上用 ②每天都会打开 ③装的是用户自己的私人数据 （体重、账目、打卡、待办、日记）。三个同时成立就该触发，比如"我想把体重记账待办整理到一个地方、 手机上能点开"——这就是工作台，只是用户不知道这个叫法。三个缺任何一个都不要触发。 功能只有一个也算——"我老忘记吃药，想每天在手机上勾一下"就是种子需求，别因为"听起来只是个小功能"就不触发。 判据是数据属于谁，不是数据存在哪：用户自己的记账 Excel 想做成手机上每天看的页面，是工作台；公司销售数据做报表，不是。