858 skills · sorted by relevance
Create a structured Markdown report when multiple retrieval tools fail. Using available domain knowledge, the workflow separates verified facts from general guidance, marks missing data, and saves a document with limitations and practical next steps.
Validate spreadsheet sources before running Python scripts to transform data, update multiple sheets, or apply formatting. Check required data first, try backup sources when needed, and report errors clearly if processing cannot proceed.
Recover from repeated code execution tool failures by writing a script through the shell and running it with an absolute path. Check output files and investigate syntax, permissions, disk space, or execution errors when needed.
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.
Continue drafting research-based documents when web search or page reading tools fail. The workflow uses the agent’s existing knowledge, identifies information gaps, and flags claims that need external verification before completing the requested deliverable.
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.
Recover from failed inline Python execution by saving the code as a script, running it through the shell, and checking the output. The four-step workflow helps diagnose errors in multiline code and spreadsheet generation tasks.
Extract data from supplied spreadsheets and documents, check for missing or truncated content, and try alternative reading methods when needed. Results identify source files and clearly separate extracted facts from external information or estimates.
Recover from file creation failures in automated tools by creating directories with shell commands and writing files individually. This workflow separates each step so project structures can be created and checked more easily.
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, switching from shell_agent to python-pptx if generation fails. The workflow also locates misplaced files, checks their size and type, and records errors to help diagnose problems.
Create PowerPoint presentations with shell_agent, then switch to Python and python-pptx if generation fails. The workflow captures error details, locates output files, and checks that the presentation opens and contains the expected slides.
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.
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.
Continue analysis after repeated tool failures by embedding known data in Python scripts run through run_shell. Save intermediate results as JSON with timestamps and source metadata, creating records that can be checked and reused in later steps.
Troubleshoot PDF creation by trying pandoc, then reportlab, then fpdf2. Check tool availability, install missing Python libraries as needed, run generation with an explicit working directory, and verify that the output file exists.
Organizes creation of a spreadsheet, a diagram, and a summary PDF as a related report package. Allocates attempts across components, checks generated files, and provides fallback methods when a tool or output fails.
Generate PDF documents when sandbox execution fails with unclear errors. Check available Python libraries, switch to direct shell execution, and verify the resulting file while collecting error details to help diagnose problems.
Handle failed video encoding by checking available encoders, testing a short clip, and trying alternatives. The workflow covers copying without re-encoding, switching codecs, which define video compression, and using MoviePy as another processing option.
Continue Excel file creation and editing when execute_code_sandbox repeatedly fails with openpyxl errors. Use run_shell to run Python directly, then check that the workbook was saved with the expected sheets and content.
Diagnose PDF conversion failures in pandoc by checking installed conversion engines, capturing full error logs, and investigating missing fonts or packages. Follow a structured sequence of retries and fallback methods to find a working conversion route.
Retrieve PDFs from web sources and extract their text through an ordered sequence: direct reading, pdftotext, then PyMuPDF. Includes file validation, extraction checks, and guidance for documenting inaccessible sources and distinguishing supplementary content.
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 readable PDF text when read_file returns binary or image data. Check the filetype parameter, run pdftotext, a command-line text extractor, and inspect output and errors, with temporary file output as an alternative.