Unified document optimization skill that chains docling-converter, imagemagick-expert, and markdown-to-pdf. Automatically detects input format, applies appropriate conversion pipeline, optimizes embedded images, and produces web/print-ready output with configurable quality presets. Use when converting documents through multi-step pipelines, optimizing PDF images, creating print-ready documents from various sources, or batch processing documents with image optimization.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Chain multiple document processing tools (docling, ImageMagick, markdown-to-pdf) into unified conversion pipelines. Automatically detect input formats, route through appropriate converters, optimize embedded images for target use case (web/print/archive), and produce publication-ready output with a single command.
Typical user requests:
pip install docling)brew install imagemagick or apt install imagemagick)pip install fpdf2 mistune pyyamlpip install markdown2 playwright && playwright install chromiumpip install PyMuPDF for PDF analysisDetect input format and assess processing requirements.
python scripts/document_optimizer.py analyze input.pdf
python scripts/document_optimizer.py analyze input.docx
python scripts/document_optimizer.py analyze ./documents/
Output includes:
Choose a quality preset based on target use case:
| Preset | Image Quality | DPI | Format | Use Case |
|---|---|---|---|---|
web | 80% | 96 | WebP/JPEG | Online viewing, fast load |
print | 95% | 300 | PNG/JPEG | Professional printing |
archive | 90% | 150 | JPEG | Long-term storage, balanced |
minimal | 70% | 72 | WebP | Maximum compression |
custom | User-defined | User-defined | User-defined | Full control |
Run the document through the optimization pipeline.
# Single document with preset
python scripts/document_optimizer.py convert input.pdf output.pdf --preset web
# With explicit preset
python scripts/document_optimizer.py convert input.docx output.pdf --preset print
# Custom settings
python scripts/document_optimizer.py convert input.pptx output.pdf \
--image-quality 85 \
--image-dpi 150 \
--image-format jpeg
# Batch processing
python scripts/document_optimizer.py batch ./input_docs/ ./output/ --preset archive
Extract, optimize, and re-embed images from an existing PDF.
python scripts/document_optimizer.py optimize-images input.pdf output.pdf --preset web
python scripts/document_optimizer.py optimize-images input.pdf output.pdf \
--image-quality 75 \
--max-width 1200
Validate the output document meets quality requirements.
python scripts/document_optimizer.py verify output.pdf
Output includes:
Input PDF → Extract Images → Optimize Images → Re-embed → Output PDF
(PyMuPDF) (ImageMagick) (fpdf2)
Input (DOCX/PPTX/HTML) → Markdown (docling) → Optimize Images → PDF (markdown-to-pdf)
(ImageMagick)
Scanned PDF → OCR + Extract (docling) → Clean Images → Markdown → Optimized PDF
(ImageMagick) (fpdf2)
analyze Commandpython scripts/document_optimizer.py analyze <input> [options]
Options:
--format json|text Output format (default: text)
--verbose Include detailed image analysis
convert Commandpython scripts/document_optimizer.py convert <input> <output> [options]
Options:
--preset PRESET Quality preset: web|print|archive|minimal|custom
--image-quality N JPEG/WebP quality 0-100 (default: preset-dependent)
--image-dpi N Target DPI for images (default: preset-dependent)
--image-format FMT Output image format: jpeg|png|webp (default: preset-dependent)
--max-width N Maximum image width in pixels
--max-height N Maximum image height in pixels
--ocr Enable OCR for scanned documents
--ocr-lang LANG OCR language (default: en,ja)
--keep-temp Retain intermediate files for debugging
--verbose Print detailed progress
batch Commandpython scripts/document_optimizer.py batch <input_dir> <output_dir> [options]
Options:
--preset PRESET Quality preset for all documents
--pattern GLOB File pattern to match (default: *.pdf,*.docx,*.pptx)
--parallel N Number of parallel workers (default: 4)
--skip-existing Skip files that already exist in output
optimize-images Commandpython scripts/document_optimizer.py optimize-images <input.pdf> <output.pdf> [options]
Options:
--preset PRESET Quality preset
--image-quality N Target quality 0-100
--max-width N Maximum width in pixels
--max-height N Maximum height in pixels
--strip-metadata Remove EXIF/XMP metadata from images
verify Commandpython scripts/document_optimizer.py verify <document> [options]
Options:
--format json|text Output format
--check-images Verify image quality metrics
--reference FILE Compare against reference document
{
"schema_version": "1.0",
"input_file": "document.pdf",
"format": "pdf",
"page_count": 15,
"file_size_bytes": 5242880,
"images": {
"count": 12,
"total_bytes": 4500000,
"formats": ["jpeg", "png"],
"max_resolution": "3000x2000"
},
"recommended_pipeline": "pdf_optimize",
"recommended_preset": "web",
"estimated_output_size_bytes": 1048576
}
{
"schema_version": "1.0",
"input_file": "document.docx",
"output_file": "document.pdf",
"pipeline": "docx_to_pdf",
"preset": "web",
"input_size_bytes": 8388608,
"output_size_bytes": 1572864,
"compression_ratio": 0.19,
"images_processed": 8,
"processing_time_seconds": 12.5,
"status": "success"
}
Optimized for fast loading on web pages and online viewers.
High quality for professional printing.
Balanced quality and size for long-term storage.
Maximum compression for constrained environments.
scripts/document_optimizer.py — Main CLI tool for document optimization pipelinesreferences/pipeline_guide.md — Detailed pipeline configurations and customization optionsreferences/image_optimization_guide.md — Image optimization strategies and quality settingsThis skill integrates with:
The optimizer automatically invokes these tools in the appropriate sequence based on input format and target preset.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Track and update action item status from natural language updates like 'Seanのメールには返信しておいた' or 'Lu対応予定'. Integrates with daily-comms-ops workflow. Use when managing action items across communication channels.
The English summary is being prepared. Showing the original description.
AI活用提案の専門コンサルタントスキル。LLM・AIエージェントの活用事例知識を基に、業界別、部門別、シーン別に最適なAI導入提案を行います。システム化、業務改善、効率化を得意とし、具体的な活用事例、期待効果、導入ステップを含む実践的な提案を提供します。Use when proposing AI/LLM adoption strategies for specific industries, departments, or business scenarios.
The English summary is being prepared. Showing the original description.
Generate AI-powered BPO service proposals for Japanese companies in the US market. Use when creating outsourcing proposals with AI service menus, ROI estimation, implementation roadmaps, and bilingual (JA/EN) proposal documents for 在米日系企業向けAI実装.
The English summary is being prepared. Showing the original description.
AI（LLM）が生成した日本語テキストの「AI臭」を検出・診断し、人間らしい文章にリライトするスキル。 Use when: 「AIっぽい文章を直して」「人間らしくリライトして」「AI臭を消して」「この文章をもっと自然にして」 「テキストのAI感を減らして」「機械っぽさを取りたい」 "make this sound more human", "remove AI tone", "humanize this text", "detect if this is AI-generated". 6つのAI特有パターン（視覚的マーカー、単調なリズム、マニュアル的構成、非コミット姿勢、抽象語の濫用、 定型メタファー）を正規表現ベースで検出し、0-100のAI臭スコアを算出。3つの人間化技法 （バランスを崩す・客観を崩す・論理を崩す）でリライトを実行する。 Note: 検出スクリプトは日本語テキスト専用。英語テキストの場合はClaude自身がreferences/を参照して分析・リライトする。
The English summary is being prepared. Showing the original description.
Generate audit-ready internal control design documents from As-Is business process inventories. Produces control IDs, assertion mappings, procedures, SoD analysis, KPIs, materiality thresholds, and implementation roadmaps. Use when building internal controls for new audit engagements, SOX/J-SOX compliance, or process improvement initiatives.
The English summary is being prepared. Showing the original description.
Review audit-related documents (control design documents, bottleneck analyses, requirements definitions, etc.) for quality, scoring them 0-100 with a severity-rated findings list. Use when reviewing audit documents, checking control design quality, or verifying cross-document consistency. Supports documents governed by US GAAP, IFRS, or J-GAAP.
The English summary is being prepared. Showing the original description.