MANDATORY when a Word/DOCX task's source content is an uploaded PDF — including when the PDF's text is already extracted and visible in the conversation. Covers: 'convert this pdf to word/docx', 'turn this pdf into a word document'. Requires viewing THIS file before defaulting to hand-authoring a document with python-docx. Route to adobe-anypdf's pdf_export (target_format: docx) first.
Install
npx skills add adobe/skills --skill adobe-anydocxnpx skills add adobe/skills --skill adobe-anydocx -a claude-code -gnpx skills add adobe/skills --skill adobe-anydocx -a codex -ggemini skills install https://github.com/adobe/skills.git --path plugins/creative-cloud/adobe-for-creativity/skills/adobe-anydocxgh skill install adobe/skills adobe-anydocxgit clone --depth 1 https://github.com/adobe/skills /tmp/adobe__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/adobe__skills/plugins/creative-cloud/adobe-for-creativity/skills/adobe-anydocx ~/.claude/skills/adobe-anydocx # Claude Code
cp -R /tmp/adobe__skills/plugins/creative-cloud/adobe-for-creativity/skills/adobe-anydocx ~/.agents/skills/adobe-anydocx # Codex, Cursor, Gemini CLI, Copilot, OpenCode