メニュー
Extract embedded JPEG and PNG images from a PDF at their native resolution, without rasterizing. Use when a PDF is primarily a wrapper around photos or images and you want to recover them at full quality without the page rendering overhead.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Batch-stamp copyright, artist, and rights information on all images in a directory. Use when you need to quickly add copyright metadata to a photo library before distribution or archival — a convenience wrapper around exiftool.
Decode JPEG XL images (.jxl) to PNG or JPEG. Use when you need to convert JXL files back to standard formats for compatibility, display, or further editing.
Rasterize PDF pages to numbered image files (JPEG, PNG, or TIFF) at a specified resolution (DPI). Use when you need to convert PDF content to standalone images — one image per page — with optional page range selection.
Read and display EXIF, IPTC, XMP, and other metadata from images as structured JSON. Use when you need to inspect image metadata without modifying it — opposite of scrub-metadata, which removes metadata.
Write EXIF, IPTC, and XMP metadata tags to image files. Use when you need to add or update metadata like artist name, copyright, description, keywords, or GPS coordinates on individual images.
Convert images to JPEG XL format (.jxl) with quality presets (lossless, visually lossless, or web). Use when you want optimal compression for photo archival or long-term storage, especially from JPEG originals where lossless transcoding preserves the original bitstream at smaller file size.
| name | pdf-extract-embedded-images |
| description | Extract embedded JPEG and PNG images from a PDF at their native resolution, without rasterizing. Use when a PDF is primarily a wrapper around photos or images and you want to recover them at full quality without the page rendering overhead. |
| disable-model-invocation | false |
| allowed-tools | Bash(pdfimages *), Bash(ls *), Bash(mkdir *), Read, Write |
Pull out JPEG and PNG objects embedded in a PDF using pdfimages. Extracts at native resolution without rasterizing the page. Different from pdf-to-images — this recovers the original embedded image files, not a rasterized page render.
command -v pdfimages || echo "pdfimages not installed — install with: sudo apt install poppler-utils"
Abort if missing.
file "<input.pdf>"
pdfimages -list "<input.pdf>"
The -list flag shows a summary of embedded images: page number, index, width, height, bits per component, color space, encoding. This helps set expectations (e.g., "3 JPEG images at 2400×3000px").
pdfimages -all "<input.pdf>" "<output-prefix>"
The -all flag extracts both the raw image stream (if JPEG, as .jpg; if PNG, as .png, etc.) plus any alternate-format versions.
Alternatives:
-j — extract JPEG objects only (faster if there are many PNG/PNG variants).-png — convert all images to PNG (may re-encode non-JPEG content; slower but lossy compression converted to lossless).Recommend -all unless the user specifies otherwise.
After extraction:
prefix-000.jpg, prefix-001.png, etc. (depends on PDF content).pdfimages extracts the raw embedded objects at the resolution they were embedded, not the page rendering resolution. For a photo book PDF with 2400×3000px JPEGs embedded, you get those 2400×3000px files directly — much faster and lossless compared to rasterizing the 8.5"×11" page at 300 DPI.pdfimages does not re-encode, the original embedded images may already be JPEG-compressed by the PDF creator. You cannot recover quality that was lost before embedding. Check output sizes and quality to verify.pdfimages preserves PNG, TIFF, and other formats within the PDF. The -all flag ensures you get them all. The -png flag is useful if you want everything as PNG but will re-encode and potentially change file size.pdfimages appends sequential suffixes (e.g., prefix-000.jpg, prefix-001.jpg). No files are overwritten.apt install poppler-utils.