Extract meaningful images, photos, diagrams, charts, maps, screenshots, illustrations, and visual evidence from uploaded PDFs with arbitrary layouts. Use when a user asks to extract, crop, classify, caption, deduplicate, inventory, or package images from PDF documents while preserving page context and source traceability.
Install
npx skills add microsoft/cat-agent-skills --skill semantic-pdf-image-extractornpx skills add microsoft/cat-agent-skills --skill semantic-pdf-image-extractor -a claude-code -gnpx skills add microsoft/cat-agent-skills --skill semantic-pdf-image-extractor -a codex -ggemini skills install https://github.com/microsoft/cat-agent-skills.git --path submissions/semantic-pdf-image-extractorgh skill install microsoft/cat-agent-skills semantic-pdf-image-extractorgit clone --depth 1 https://github.com/microsoft/cat-agent-skills /tmp/microsoft__cat-agent-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/microsoft__cat-agent-skills/submissions/semantic-pdf-image-extractor ~/.claude/skills/semantic-pdf-image-extractor # Claude Code
cp -R /tmp/microsoft__cat-agent-skills/submissions/semantic-pdf-image-extractor ~/.agents/skills/semantic-pdf-image-extractor # Codex, Cursor, Gemini CLI, Copilot, OpenCode