1.1K skills · sorted by relevance
Automate Chrome using an existing login session through CDP, Chrome’s remote control interface. Open pages, click elements, enter text, extract page content, run JavaScript, and inspect authentication tokens with agent-browser.
Extract readable text from PDFs with pdftotext when read_file returns garbled or binary content. Choose page ranges, preserve text layout where needed, and send the extracted content to standard output or a text file for further processing.
Extract readable text from PDFs when normal file reading returns garbled or unusable content. The workflow switches between extraction tools, checks the results, and includes optical character recognition for scanned pages when needed.
Extract PDF text when read_file returns unreadable binary content or little usable output. Try pdftotext with layout preservation, then use pdfplumber as an alternative when the command is unavailable or produces insufficient text.
Extract text from Word DOCX files and save it as plain text. The skill checks available tools, tries shell utilities, and falls back to Python’s standard library when needed.
Extract text, tables, and headings from Word documents when standard file reading tools fail. The workflow uses Python and python-docx through run_shell to recover document content for further review or analysis.
Inspect unfamiliar Excel workbooks before building extraction scripts. Map sheets, headers, columns, and row patterns, then use those findings to distinguish actual records from summaries and blank rows when extracting data.
Turn cryptographic code or specifications into sequence diagrams showing who sends each message, which cryptographic operations occur, and where failures stop the exchange. Outputs include Mermaid source, a plain text diagram, and a protocol summary.
Search HTTP traffic and security findings stored in Burp Suite project files from the command line. Filter response headers or bodies with text patterns, extract affected URLs, and review selected proxy history or site map data.
Collect channel information and video details from a YouTube channel through BrowserAct API. Choose latest, popular, or earliest videos and receive structured metrics, including views, publication dates, and subscriber counts, for content research and reporting.
Search Zhihu articles by keyword and publication period through the BrowserAct API. Retrieve full article text, titles, authors, dates, cover image URLs, and source links as structured data for industry research, brand monitoring, or competitor updates.
Find YouTube channels by keyword and collect channel names, links, subscriber counts, descriptions, and verification status through the BrowserAct API. Filter by recent uploads to research competitors, discover creators, or compile a channel database.
Find YouTube creators by keyword and recent upload period, then collect structured channel profiles through BrowserAct. Results include subscriber counts, total views, video counts, descriptions, visible social links, and contact email addresses when available.
Collect business information from Google Maps using search keywords, language, and a country preference. Retrieve names, addresses, phone numbers, websites, ratings, and operating status for local market research or sales lead lists.
Clean Excel columns by removing unwanted prefixes from numeric values and extracting Chinese characters from text. Add the cleaned results as new columns, then save an Excel file and provide a download link.
Convert protein sequences into numerical features with Meta AI's ESM-2 for machine learning. Extract features for individual amino acids or whole sequences, score mutations, and predict which positions in a protein may contact each other.
Check whether medicinal chemistry papers are indexed in ChEMBL, a curated database of biological activity measurements. Look up papers by DOI, report available data counts, and retrieve structured measurements before extracting tables from PDFs.
Automate website tasks through a command-line browser tool. Agents can navigate pages, fill forms, extract text, capture screenshots, and test web apps, with saved login state available for later sessions.
Extract Markdown and metadata from PDFs, Office documents, emails, archives, and other formats using Apache Tika. Keep attachments and embedded items separate in structured output, detect parsing problems, and read selected portions without overwhelming the agent's context.
Extract text from photos, screenshots, and scanned PDFs with PaddleOCR, supporting over 100 languages. Return recognized text with its location and confidence score, and process sources such as business cards, receipts, and multilingual documents.
Retrieve web page content from a URL or search query through Firecrawl MCP. Export it as Markdown, HTML, or plain text, with support for extracting structured data from pages.
Retrieve company filings from the SEC, the US securities regulator, using Python. Extract financial statements, insider transactions, and institutional holdings to research companies and compare financial data across reporting periods.
Prepare pathology image datasets by detecting tissue in whole slide images and extracting smaller image tiles. Use random, grid, or score-based selection, preview extraction locations, and apply preprocessing filters to review and prepare the resulting tiles.
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.
The English summary is being prepared. Showing the original description.