Scraping
Web scraping and data extraction
video-downloader
by LeeFeee
通用视频下载工具。基于 yt-dlp 支持从 YouTube、Bilibili、Twitter/X、抖音、小红书等 1000+ 视频网站下载视频并保存到本地。首次使用会自动安装 yt-dlp 依赖。当用户提供视频链接、要求下载视频、或提到"保存视频"、"下载视频"时触发此技能。支持指定输出目录、选择视频质量、仅下载音频等选项。
site-crawler
by mindmorass
Crawl and extract content from websites
claude-command-firecrawl-scrape
by monkey1sai
Converted from Claude plugin command "scrape" (firecrawl). Use when the
by wollfoo
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Factory needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale. Sử dụng khi: xử lý PDF, trích xuất, ghép file, chia nhỏ, điền form PDF.
remotion-best-practices
by vishalsachdev
Best practices for Remotion - Video creation in React
PR Feedback Training-First Loop
by violetio
Extract, learn, and integrate PR feedback into the Violet brain
claude-command-firecrawl-map
by monkey1sai
Converted from Claude plugin command "map" (firecrawl). Use when the
playwright-py-skill
by akaihola
Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.
claude-command-firecrawl-crawl
by monkey1sai
Converted from Claude plugin command "crawl" (firecrawl). Use when the
firmware-decryption
by tangjunyi23
Firmware decryption, deobfuscation, and unpacking for encrypted IoT firmware images. Use when firmware entropy analysis reveals encrypted/obfuscated content, when binwalk extraction fails due to encryption, when decrypting vendor-specific firmware encryption (D-Link, Netgear, TP-Link, Hikvision, Dahua, ZTE), or when reversing custom XOR/AES/DES encryption applied to firmware update files.
brightdata
by multicam
Progressive four-tier URL content scraping with automatic fallback strategy. USE WHEN user says "scrape this URL", "fetch this page", "get content from", "can't access this site", "use Bright Data", "pull content from URL", or needs to retrieve web content that may have bot detection or access restrictions.
by alfredang
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
e2e-bugfix
by penkzhou
This skill should be used when the user asks to "debug E2E tests", "fix Playwright failures", "fix Cypress tests", "analyze timeout errors", or mentions keywords like "Playwright", "Cypress", "Timeout exceeded", "locator", "selector", "flaky test". It provides the complete bugfix workflow knowledge including error classification, confidence scoring, and E2E-specific debugging techniques.
拼多多/1688 商品爬虫
by MimonWish
Pinduoduo 1688 ecommerce product scraper
cloudflare-browser-rendering
by ma1orek
Add headless Chrome automation with Puppeteer/Playwright on Cloudflare Workers. Use when: taking screenshots, generating PDFs, web scraping, crawling sites, browser automation, or troubleshooting XPath errors, browser timeouts, binding not passed errors, session limits, page.evaluate __name errors, or waitForSelector timeout issues.
aico-frontend-style-extraction
by yellinzero
Extract design tokens (colors, typography, spacing, effects) from reference website or screenshot to create project design system. UNIQUE VALUE: Creates standardized design-system.md file with all design tokens extracted systematically. Use this skill when: - User shares reference website URL and wants to extract its style - User provides screenshot or image and asks to "extract design", "extract style" - Running /frontend.init and need to create design system from reference - User asks to "create design system", "extract colors", "extract typography" - Need to establish consistent design tokens before starting frontend work Methods: URL (via Playwright MCP screenshot) or direct screenshot analysis Output: ALWAYS write to docs/reference/frontend/design-system.md
redbook-creator-publish
by yanquankun
"小红书帖子创作与发布技能。用于:(1) 生成小红书风格的帖子内容(标题+正文+标签)(2) 获取/生成帖子配图 (3) 自动上传到小红书创作者平台。触发词:小红书创作、create redbook、小红书、红书、笔记创作、帖子创作"
stock_ticker
by cliuxinxin
Get real-time stock prices and financial info for US stocks (like AAPL, TSLA, NVDA).
impeccable-extract
by SebastiaanWouters
"Skills-only equivalent of impeccable.style /extract. Extract and consolidate reusable components, design tokens, and patterns into your design system. Identifies opportunities for systematic reuse and enriches your component library. Use for frontend and UI design tasks."
article-extractor
by jrajasekera
Extract clean article content from URLs and save as markdown. Triggers when user provides a webpage URL and wants to download it, extract content, get a clean version without ads, capture an article for offline reading, save an article, grab content from a page, archive a webpage, clip an article, or read something later. Handles blog posts, news articles, tutorials, documentation pages, and similar web content. Supports Wayback Machine for dead links or paywalled content. This skill handles the entire workflow - do NOT use web_fetch or other tools first, just call the extraction script directly with the URL.
url_reader
by cliuxinxin
Read and extract text content from a specific URL.
code-polisher
by k1lgor
Use this when the user asks to refactor, clean up, optimize, or improve code quality.
by Krosebrook
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
by ashleytower
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.