Continue file reading and data processing when read_file or execute_code_sandbox fails. The skill uses run_shell with short Python commands or multiline scripts to inspect files, parse data, and save transformed output.
Recover from repeated web search failures by delegating information gathering to shell_agent. Define the required data and output format, allow retries and alternative collection methods, then check source citations and completeness before using the results.
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.
Apply ReportLab’s built-in paragraph styles to PDF titles, headings, and body text. Learn how to reuse existing styles and create named variations without duplicate style names that can cause KeyError exceptions.
Extract PDF text when the usual file reader returns errors or unusable output. Choose command-line tools or Python libraries for plain text, metadata, tables, and complex layouts, with checks for scanned or copy-protected documents.
Create and edit Excel workbooks by running a complete Python script through the shell. Covers multiple sheets, data entry, formatting, formulas, and saving files when other file-reading or code-execution tools fail.
Continue regulatory research when government pages or PDFs cannot be retrieved. Use alternative sources to draft compliance checklists, clearly distinguish the basis of each finding, and identify requirements that need confirmation from the relevant authority.
Check PDF page counts, document details, and required text using command-line tools. This skill provides a verification workflow for environments without Python PDF libraries, including text extraction from selected pages and searches for expected sections.
Check generated PDFs with Python and PyPDF2 before delivery. Verify expected page counts, detect unreadable or zero-page files, and collect results across multiple documents, with optional file size checks for unusually small outputs.
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.
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.
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.
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.
Prepare Markdown for pandoc PDF conversion by replacing problematic Unicode symbols with ASCII alternatives. The skill covers reusable substitution scripts, broader character conversion, and alternative PDF engines for documents that need to retain Unicode.
Troubleshoot unclear errors when converting documents to PDF with pandoc. Check installation, capture error logs, identify missing fonts or packages, and try alternative PDF engines, the tools that render the final document.
Locate missing files and verify their full paths before processing them. This workflow checks directory contents, searches by filename, and inspects permissions, size, and modification time to help resolve FileNotFoundError, an error indicating a file could not be found.
Check which H.264 video encoders are available before writing FFmpeg scripts. Choose an available encoder or copy an existing video stream when appropriate, then test a short clip to catch compatibility problems before processing the full file.
Use shell heredocs, which pass multiline text directly to a command, when write_file fails on complex code. Save TypeScript, JSX, JSON, or shell scripts with literal quotes and formatting, then verify the file and its contents.
Build complex Excel files in four stages: extraction, preparation, calculation, and formatted output. Intermediate CSV files let agents and reviewers inspect data, validate forecasts, locate errors, and rerun individual stages without repeating the entire workflow.
Extract data from Excel sheets with misplaced headers, merged header cells, or introductory rows. Uses text patterns to locate headers, clean column names, and remove empty rows so the data can be processed with pandas.
Find generated files that are missing from their expected locations in isolated or temporary execution environments. Search confirmed directories, identify the right file, copy it to the intended destination, and verify that it is readable and nonempty.
Track tasks that require several outputs by listing every deliverable, updating a visible checklist, and verifying that each result exists. Helps prevent work from ending while requested files, reports, or other outputs remain unfinished.
Build Excel spreadsheets with merged titles and headers using openpyxl, a Python library for spreadsheet files. Follow a sequence for entering values, merging cells, and applying formatting, with guidance for updating existing merged ranges and checking saved results.
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.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)