菜单
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.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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.
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.
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-to-images |
| description | 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. |
| disable-model-invocation | false |
| allowed-tools | Bash(pdftoppm *), Bash(ls *), Bash(mkdir *), Read, Write |
Convert PDF pages to raster images (JPEG, PNG, or TIFF) using pdftoppm. Each page becomes a numbered image file. Different from pdf-extract-embedded-images — this rasterizes the entire page content.
jpeg, png, or tiff. Default: jpeg (good balance of size and quality). PNG for lossless, TIFF for archival.command -v pdftoppm || echo "pdftoppm not installed — install with: sudo apt install poppler-utils"
Abort if missing.
file "<input.pdf>"
pdfinfo "<input.pdf>" # shows page count, dimensions, etc.
If invalid, abort. Print page count for user awareness.
Base command:
pdftoppm -r <DPI> -<format> "<input.pdf>" "<output-prefix>"
Examples:
pdftoppm -r 300 -jpeg input.pdf output_pdftoppm -r 150 -png -f 5 -l 10 input.pdf output_pdftoppm -r 600 -tiff input.pdf output_Flags:
-r <DPI> — resolution in DPI.-<format> — output format: jpeg, png, tiff.-f <N> — first page (optional).-l <N> — last page (optional).pdftoppm -r <DPI> -<format> <page-flags> "<input.pdf>" "<output-prefix>"
Show progress and warn if the PDF is large (many pages or high DPI — processing may take a minute or more).
After conversion:
output_001.jpg, output_002.jpg, ...).prefix-000001.png). Naming convention depends on pdftoppm version; typically zero-padded 6-digit page numbers.pdftoppm rasterizes the entire page at the specified DPI. This is lossy compared to the original PDF vector content, but suitable for archival, sharing, or thumbnail workflows. See pdf-extract-embedded-images for extracting embedded photos without rasterization.apt install poppler-utils.