Extract text, tables, citations, forms, and metadata from PDFs as grounded context for downstream M365 Copilot work. Use whenever a source for research-synthesis, decision-memo, or document-summarization arrives as a PDF (contracts, regulatory filings, policy documents, vendor reports, scanned forms, fillable intake forms, academic papers), including encrypted, permission-restricted, hybrid native-plus-scan, or large multi-hundred-page packs. Triggers: "extract from this PDF", "summarize this filing", "pull table from PDF", "OCR this scan", "read the fillable form", "this PDF is password-protected".
$npx -y skills add andreaswasita/copilot-cowork-dojo --skill pdf-extractionInstalls into the current project.
Run `npx skills use "https://github.com/andreaswasita/copilot-cowork-dojo" --skill "andreaswasita/copilot-cowork-dojo/pdf-extraction"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/andreaswasita/copilot-cowork-dojo" that are relevant to the current task. Run `npx skills add "https://github.com/andreaswasita/copilot-cowork-dojo"` and select the relevant skills, then follow their instructions.