Word, Excel, PowerPoint, PDF, meeting notes, and manuals (3.6K skills)
Process Excel files with Python after checking that input files and source URLs are accessible. The workflow covers data transformations, formulas, and formatting, with alternative sources and error logs when access fails.
Process complex Excel files by running Python scripts directly through run_shell. Use pandas for data transformations and openpyxl for workbook editing, including multiple sheets, formulas, and formatting, with explicit saving and error reporting.
Create internal and external documents from one reference source. Extract deadlines, responsibilities, procedures, and policies, tailor content for each audience, and check that terminology, formatting, versions, and references stay consistent while internal information remains appropriately restricted.
Create or edit Excel workbooks with checks for sheet names, row counts, formulas, and merged cells. Reopen the saved file and verify each requirement, recording explicit results rather than relying on a completion summary.
Verify saved Excel files directly with Python and openpyxl, a workbook library. Check sheets, headers, row counts, marked rows, and output files to resolve conflicting agent reports and summarize what actually exists on disk.
Create medical visit notes in SOAP format, which separates patient reports, observed findings, clinical assessment, and care plans. Organize the available information into a complete Markdown or plain text file written in one operation.
Gather web information and turn it into an Excel workbook with explicit checks. Handles search failures through delegated research, records sources and missing data, and verifies the saved workbook against requested requirements.
Update or create Excel workbooks with checks against the requested structure. Identify the correct file before editing, then reread the saved workbook to verify sheet names, populated columns, row counts, and selected sample counts.
Audit an Excel workbook before editing, then verify the saved file with Python and openpyxl. Each requested requirement receives an explicit status, so completion depends on checks of the actual file.
Extract text from PDFs by trying several methods in sequence and checking the results. When ordinary extraction yields too little text, switch to OCR, which recognizes text in images, to process scanned documents.
Troubleshoot CSV and XLSX processing when execute_code_sandbox fails. The workflow locates input files, saves processing code as a Python script, captures execution errors, checks dependencies and file access, and confirms output exists before reading it.
Inspect PowerPoint files with python-pptx when standard readers fail or return incomplete information. Retrieve slide counts and titles, compare them with presentation requirements, and report missing or problematic content without installing PowerPoint.
Extract text from PDFs when read_file fails or returns unreadable data. Use dedicated command-line tools or Python libraries to retrieve text and tables, preserve spacing where possible, inspect document properties, and validate the extracted content.
Extract readable text from PDFs when ordinary file readers return garbled or binary content. The skill guides agents through detecting failed reads and using pdftotext, a command-line PDF text extractor, with layout-preserving options.
Extract text from existing PDFs and assemble it into a new PDF report using command-line tools. Choose an available conversion method, combine source content, and check the resulting file’s pages and included text.
Inspect PowerPoint files when standard readers fail by using python-pptx through the shell. Produce structured results showing slide counts, titles, and shape counts to check presentation structure before delivery.
Inspect PowerPoint files when read_file returns errors or incomplete content. Using python-pptx, a Python library for presentations, the skill extracts slide counts, titles, and text to check whether the deck meets expected structural requirements.
Check generated PDFs with PyPDF2 before reporting completion. A Python script verifies that each file can be opened and has the expected page count, helping identify outputs that need regeneration.
Debug PowerPoint generation with python-pptx, a Python library for presentations. Follow a sequence of installation checks, minimal tests, error logging, and fixes for tables and charts, then inspect the generated slides.
Create PDF reports from existing PDFs using command-line tools. The workflow checks source files, extracts text, organizes report sections, and generates or merges PDFs, with alternative output methods depending on the tools available.
Provides fallback methods for extracting PDF text when the usual file reader fails or returns incomplete content. Uses command-line tools or Python libraries to retrieve text, preserve spacing, inspect metadata, and extract tables.
Create PowerPoint presentations with specified slide content and structure. If generation through shell_agent fails, the workflow switches to Python, captures error details, locates the output, and checks the file format, size, and slide count.
Check generated PDFs with PyPDF2, a Python library for reading PDF files. Verify that files exist, contain data, open successfully, and match expected page counts, then use failures to guide regeneration and another verification pass.
Recover readable text from PDFs when read_file or Python extraction fails. Use pdftotext, a command-line text extractor, with options to preserve layout, specify character encoding, or save extracted content to a file.