무료GitHub에 공개

multi-format-document-optimizer

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

takusaotome/claude-skills-library

연동 도구Word PowerPoint Playwright

설치 방법 보기

포함된 파일(6)

SKILL.md9.3 KB
references/image_optimization_guide.md9.4 KB
references/pipeline_guide.md8.5 KB
scripts/document_optimizer.py30.2 KB
scripts/tests/conftest.py3.0 KB
scripts/tests/test_document_optimizer.py10.0 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Multi-Format Document Optimizer

Overview

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.

When to Use

Convert PDF/DOCX/PPTX to optimized PDF with compressed images
Create web-ready documents with WebP images from source documents
Generate print-ready PDFs with high-DPI images from mixed sources
Batch process multiple documents through consistent optimization pipeline
Extract, optimize, and re-embed images from existing documents
Convert scanned documents with OCR and image enhancement
Create archive-quality PDFs with optimized file size

Typical user requests:

"Convert this PPTX to PDF and optimize images for web"
"Make this scanned PDF smaller while keeping it readable"
"Convert these Word docs to print-ready PDFs"
"Batch process all documents in this folder for web publishing"
"Optimize this PDF's embedded images"

Prerequisites

Python 3.9+
docling CLI (pip install docling)
ImageMagick 7+ (brew install imagemagick or apt install imagemagick)
markdown-to-pdf dependencies:
- fpdf2 mode: pip install fpdf2 mistune pyyaml
- Playwright mode: pip install markdown2 playwright && playwright install chromium
Optional: pip install PyMuPDF for PDF analysis

Workflow

Step 1: Analyze Input Document

Detect 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:

Detected format(s)
Page count and dimensions
Embedded image count and total size
Recommended pipeline based on content

Step 2: Select Quality Preset

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

Step 3: Execute Conversion Pipeline

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

Step 4: Optimize Existing PDF Images

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

Step 5: Verify Output

Validate the output document meets quality requirements.

python scripts/document_optimizer.py verify output.pdf

Output includes:

File size comparison (before/after)
Image quality assessment
Page render verification
Compression ratio achieved

Pipeline Reference

PDF Optimization Pipeline

Input PDF → Extract Images → Optimize Images → Re-embed → Output PDF
              (PyMuPDF)      (ImageMagick)     (fpdf2)

Document Conversion Pipeline

Input (DOCX/PPTX/HTML) → Markdown (docling) → Optimize Images → PDF (markdown-to-pdf)
                                                (ImageMagick)

Scanned Document Pipeline

Scanned PDF → OCR + Extract (docling) → Clean Images → Markdown → Optimized PDF
                                         (ImageMagick)            (fpdf2)

CLI Options

`analyze` Command

python scripts/document_optimizer.py analyze <input> [options]

Options:
  --format json|text     Output format (default: text)
  --verbose              Include detailed image analysis

`convert` Command

python 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` Command

python 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` Command

python 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` Command

python 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

Output Format

Analysis JSON

{
  "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
}

Conversion Report

{
  "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"
}

Quality Presets Detail

Web Preset

Optimized for fast loading on web pages and online viewers.

Image format: WebP (JPEG fallback)
Quality: 80%
DPI: 96
Max dimensions: 1920x1080
Strip metadata: Yes

Print Preset

High quality for professional printing.

Image format: PNG (photos as JPEG 95%)
Quality: 95%
DPI: 300
Max dimensions: No limit
Strip metadata: No (preserve color profiles)

Archive Preset

Balanced quality and size for long-term storage.

Image format: JPEG
Quality: 90%
DPI: 150
Max dimensions: 2400x2400
Strip metadata: Preserve essential only

Minimal Preset

Maximum compression for constrained environments.

Image format: WebP
Quality: 70%
DPI: 72
Max dimensions: 1280x720
Strip metadata: Yes

Resources

scripts/document_optimizer.py — Main CLI tool for document optimization pipelines
references/pipeline_guide.md — Detailed pipeline configurations and customization options
references/image_optimization_guide.md — Image optimization strategies and quality settings

Integration with Other Skills

This skill integrates with:

docling-converter — Document format conversion and OCR
imagemagick-expert — Image processing and optimization
markdown-to-pdf — Final PDF generation with professional styling

The optimizer automatically invokes these tools in the appropriate sequence based on input format and target preset.

Key Principles

Single command, complete pipeline — Analyze, convert, and optimize in one step
Preset-driven simplicity — Sensible defaults for common use cases
Format-aware routing — Automatic pipeline selection based on input type
Quality-preserving compression — Optimize size without visible quality loss
Batch-friendly — Process entire directories with consistent settings

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

같은 저장소의 스킬

action-status-updater

무료

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

takusaotome/claude-skills-library92026년 10월 5일 업데이트

ai-adoption-consultant

무료

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

takusaotome/claude-skills-library92026년 10월 5일 업데이트

ai-bpo-proposal-generator

무료

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

takusaotome/claude-skills-library92026년 10월 5일 업데이트

ai-text-humanizer

무료

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。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

takusaotome/claude-skills-library92026년 10월 5일 업데이트

audit-control-designer

무료

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

takusaotome/claude-skills-library92026년 10월 5일 업데이트

audit-doc-checker

무료

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

takusaotome/claude-skills-library92026년 10월 5일 업데이트

takusaotome의 스킬 모두 보기

이 스킬의 문제 신고

설치

명령으로 설치

npx skills add https://github.com/takusaotome/claude-skills-library --skill multi-format-document-optimizer

터미널에 붙여 넣고 실행합니다(Node.js 필요). Claude Code, Codex 등 설치할 에이전트를 고를 수 있습니다.

에이전트에게 부탁하기

다음 Agent Skill을 설치해 주세요.
https://github.com/takusaotome/claude-skills-library/tree/main/skills/multi-format-document-optimizer

먼저 SKILL.md와 첨부 파일의 내용을 확인해 수상한 처리(외부 전송, 인증 정보 읽기 등)가 없는지 확인한 뒤 Claude Code는 ~/.claude/skills/multi-format-document-optimizer/, Codex는 ~/.agents/skills/multi-format-document-optimizer/ 에 배치해 주세요.

이 문장을 그대로 Claude Code나 Codex에 보내면 내용을 확인한 뒤 설치해 줍니다.

GitHub에서 소스 보기

저장소: takusaotome/claude-skills-library
스타: 9
포크: 3
카테고리: 동영상·이미지·음성
라이선스: MIT
원문 언어: 영어
최종 업데이트: 2026년 10월 5일

스킬은 에이전트를 위한 지시와 스크립트의 묶음입니다. cccskills는 내용의 안전성을 보증하지 않습니다. 설치하기 전에 내용을 확인하세요.

포함된 파일(6)

SKILL.md(원문)

Multi-Format Document Optimizer

Overview

When to Use

Prerequisites

Workflow

Step 1: Analyze Input Document

Step 2: Select Quality Preset

Step 3: Execute Conversion Pipeline

Step 4: Optimize Existing PDF Images

Step 5: Verify Output

Pipeline Reference

PDF Optimization Pipeline

Document Conversion Pipeline

Scanned Document Pipeline

CLI Options

analyze Command

convert Command

batch Command

optimize-images Command

verify Command

Output Format

Analysis JSON

Conversion Report

Quality Presets Detail

Web Preset

Print Preset

Archive Preset

Minimal Preset

Resources

Integration with Other Skills

Key Principles

리뷰

댓글

같은 저장소의 스킬

action-status-updater

ai-adoption-consultant

ai-bpo-proposal-generator

ai-text-humanizer

audit-control-designer

audit-doc-checker

`analyze` Command

`convert` Command

`batch` Command

`optimize-images` Command

`verify` Command