Research skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

crawlee

Expert guide for building web scrapers and crawlers using Crawlee (JavaScript/TypeScript and Python). Use this skill whenever the user wants to: scrape a website, build a web crawler, extract data from web pages, automate browser navigation, handle anti-bot blocking, manage proxies or sessions for scraping, use Playwright/Puppeteer/Cheerio/BeautifulSoup for web data extraction, crawl sitemaps, download files from URLs, or deploy a scraper to the cloud. Trigger even for loosely related phrases like "get data from a website", "automate browser", "scrape prices", "extract links", "crawl URLs", or "bypass bot detection". Covers CheerioCrawler, PlaywrightCrawler, PuppeteerCrawler, HttpCrawler, JSDOMCrawler (JS), and BeautifulSoupCrawler, ParselCrawler, PlaywrightCrawler (Python).

2.09k repo starsObserved in 1 repos

Research

GitHub

daydreamer

Use this skill when the user says "daydream", "start daydreaming", "force a daydream", "run daydream cycles", or when a scheduled daydream is triggered. Also activates on first install to configure daydream frequency and cycles. Use when maintaining the Daydreams.MD memory log or writing new memories. This skill emulates the human act of daydreaming by randomly traversing accumulated memories and web searches to generate novel ideas.

2.09k repo starsObserved in 1 repos

Research

GitHub

deep-reading

书/长文/研报/论文的深度消化，产出结构笔记+原子笔记+知识网络连接。关键词：深度阅读、深度学习、结构笔记、deep learning。

2.09k repo starsObserved in 1 repos

Research

GitHub

dopewars-online

Game rules, strategy guide, and API reference for DopeWars Online.

2.09k repo starsObserved in 1 repos

Research

GitHub

elsewhere-news

Browse and read articles and podcasts from Elsewhere (elsewhere.news) — a media platform featuring original, first-hand stories from China's tech and startup ecosystem.

2.09k repo starsObserved in 1 repos

Research

GitHub

fengniao-search

风鸟企业数据查询引擎，用于查询中国企业的结构化工商、关系与风险信息，并在需要时生成报告、摘要等衍生输出。当用户想查询企业基本信息（如法定代表人、注册号、统一社会信用代码、成立日期、注册地址、经营范围及基础联系方式）、股东结构、主要人员、对外投资、工商变更，或查询被执行人、失信被执行人、限制高消费、经营异常、严重违法、行政处罚等风险信息时使用。也适用于合作方背景核查、供应商管理、客户风险识别等场景。支持输入企业简称并先做模糊搜索获取企业主体。

2.09k repo starsObserved in 1 repos

Research

GitHub

geo-fact-checker

GEO-focused fact-checking and evidence collection assistant for written content. Use this skill whenever the user wants to verify factual claims (numbers, dates, rankings, market share, competitor data, quotes, or statistics), validate sources, or increase AI trust in content by attaching precise citations and up-to-date evidence. Prefer this skill for content that should be highly reliable for AI citations, reports, comparison pages, landing pages, and data-driven articles.

2.09k repo starsObserved in 1 repos

Research

GitHub

gork-analysis

Gork data API. Uses Grok model to analyze tweet comments, extract valuable intelligence from replies, and fetch latest community sentiment on projects or topics.

2.09k repo starsObserved in 1 repos

Research

GitHub

guided-learning

Guided learning skill — one concept at a time, gentle guidance, comprehension checks, chapter review

2.09k repo starsObserved in 1 repos

Research

GitHub

init-kb

Initialize or update a knowledge base for a project, business, or client. Triggers on "init kb", "build kb", "create kb for X", "set up kb", "new kb" (init), and "update kb", "refresh kb", "re-scrape kb", "kb update" (update). Scrapes websites and social profiles via the Firecrawl API, runs deep analysis, asks targeted questions to fill gaps, and generates 9 structured KB files. Each KB loads on-demand (not at boot) to avoid context bloat. Files are designed to be comprehensive references for specialized agents.

2.09k repo starsObserved in 1 repos

Research

GitHub