抓取
网页抓取与数据提取
sync
Alexu0317-FATHER
"Read extract-buffer.md, distribute signals to Domain State, surface thinking patterns and core candidates in report, then clear buffer. Must run in a NEW dedicated session."
writing-email-subjects
danbars
Use when an email draft exists but the subject line is unclear, too long, or needs options tailored to a specific audience and tone.
observe
Crawlio-app
Use this skill when the user asks to "check observations", "what did Crawlio see", "show crawl timeline", "query the observation log", or wants to review what happened during a crawl session. Queries the append-only observation log with filtering by host, source, operation, and time range.
worklog-skillify
taika-izumi
"worklog-extract で採用された候補から、writing-skills 委譲で新規スキル作成または既存スキル拡張を行う。スコープ（汎用/プロジェクト固有/固有ルール）で成果物の配置先を振り分け、汎用パスをガイドライン配信元リポジトリ以外で実行しようとした場合は警告する。ユーザーまたは worklog-extract から起動。"
Jackiexiao
（中文）Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
postgis-extract-xy
mmbmf1
Extract longitude and latitude from PostGIS geometries using ST_X and ST_Y safely.
doc-convert
spoonbobo
Convert and extract text from PDFs, DOCX, images (OCR), and other document formats using the gateway's built-in document processing stack.
writing-analyzer
qingchunwuhui
快速拆解文章写作结构，提取可复用的写作模板。无需审计流程，直接分析。适合学习写作技巧、建立模板库。支持快捷指令 /analyze-writing。
ui-extractor
alpex-ai
Analyze screen recordings and websites to extract implementation specs, design systems, and UI patterns.
zhongjis
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
deep-research-firecrawl
wottpal
Conducts citation-backed research using Firecrawl MCP search, scrape, map, crawl, and agent tools with selectable quick, standard, deep, and ultradeep modes. Use for multi-source comparisons, technical evaluations, market research, and high-stakes decision support.
crawl-site
Crawlio-app
Use this skill when the user asks to "crawl a site", "download a website", "mirror a site", "scrape a site", or wants to download web pages for offline access or analysis. Configures Crawlio settings based on site type, starts the crawl, monitors progress, and reports results.
replay-playwright
replayio
Set up and run Playwright tests with Replay Browser to record test executions for debugging and performance analysis.
quote-extractor
qingchunwuhui
快速从文章中提取可直接引用的金句，建立素材库。无需审计流程，直接提取。支持快捷指令 /extract-quotes。
excel-reader
totophe
"Read and inspect Excel workbooks (.xlsx). List sheets with dimensions, extract headers, read specific rows or row ranges, extract columns by name or index. Handles large files (50k+ rows, 100MB+) via streaming. Use when the user wants to explore, preview, or extract data from spreadsheets, when building import or ETL scripts from Excel sources, or when analyzing spreadsheet structure and content."
firecrawl
YPYT1
Web search and scraping via Firecrawl API. Use when you need to search the web, scrape websites (including JS-heavy pages), crawl entire sites, or extract structured data from web pages. Requires FIRECRAWL_API_KEY environment variable.
webapp-testing
TheWatcher01
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
remotion-best-practices
jyasuu
Best practices for Remotion - Video creation in React
webapp-testing
enoch-robinson
Webåºç¨æµè¯å·¥å ·å ãä½¿ç¨ Playwright è¿è¡å端èªå¨åæµè¯ãUI è°è¯ãæªå¾æè·ãæµè§å¨æ¥å¿æ¥çãå½éè¦æµè¯æ¬å° Web åºç¨ãéªè¯å端åè½ãè°è¯ UI è¡ä¸ºæ¶ä½¿ç¨æ¤æè½ã
video-audio-extractor
kantylee
Extract audio from video files or URLs (including YouTube). Supports MP3, WAV, M4A, FLAC, OGG, and OPUS formats. Can process local video files or download from URLs. For YouTube videos, uses yt-dlp for direct audio extraction when possible.
mcp-playwright
janjaszczak
Automate browser flows and capture evidence (screenshots, console/network errors). Use for UI verification, repro steps, and end-to-end smoke tests.
youtube-rapidapi-transcript
zxhfighter
Extract transcripts from YouTube videos. Use when the user asks for a Youtube video transcript, subtitles, or captions of a YouTube video and provides a YouTube URL (youtube.com/watch?v=, youtu.be/, or similar).
ai
jyasuu
Cheat sheet for AI tools including GEMINI and CODEX configurations.
qiaomu-markdown-proxy
NJMathwig
Fetch any URL as clean Markdown via proxy services or built-in scripts. Works with login-required pages like X/Twitter, WeChat 公众号, Feishu/Lark docs. Supports PDFs (remote and local). Use this BEFORE other fetch tools. Triggers on any URL the user shares, "fetch this", "read this link", "get content from".