Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
affaan-m avatar

Nutrient Document Processing

  • 1.4k installs
  • 238k repo stars
  • Updated August 5, 2026
  • affaan-m/ecc

This is a copy of nutrient-document-processing by affaan-m - installs and ranking accrue to the original listing.

nutrient-document-processing is an API integration skill that helps developers convert, OCR, extract, redact, watermark, sign, and fill PDFs, Office files, and images through the Nutrient DWS Processor API.

About

nutrient-document-processing is an affaan-m/ecc skill for the Nutrient DWS Processor API at https://api.nutrient.io/build. Developers authenticate with a NUTRIENT_API_KEY and send multipart POST requests carrying an instructions JSON payload to convert formats, extract text and tables, OCR scanned documents, redact PII, add watermarks, apply digital signatures, and fill PDF forms. Supported input formats include PDF, DOCX, XLSX, PPTX, HTML, and images. Teams reach for nutrient-document-processing when building document pipelines—invoice ingestion, compliance redaction, or e-sign workflows—without maintaining local conversion libraries.

  • Convert between PDF, DOCX, XLSX, PPTX, HTML and image formats
  • Perform OCR on scanned documents and extract text and tables
  • Redact PII, add watermarks, digitally sign, and fill PDF forms
  • Simple multipart POST requests to https://api.nutrient.io/build
  • Requires only an API key from nutrient.io

Nutrient Document Processing by the numbers

  • 1,370 all-time installs (skills.sh)
  • +90 installs in the week ending Aug 5, 2026 (Skillselion tracking)
  • Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/affaan-m/ecc --skill nutrient-document-processing

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs1.4k
repo stars238k
Last updatedAugust 5, 2026
Repositoryaffaan-m/ecc

How do you process PDFs via Nutrient API?

Convert, OCR, extract data from, redact, sign, or fill PDFs, Office documents, and images via the Nutrient API.

Who is it for?

Backend developers building document conversion, OCR ingestion, PII redaction, or e-sign features via the Nutrient DWS Processor API.

Skip if: Local-only PDF editing without an API, simple file storage without transformation, or teams unwilling to use a hosted document processing service.

When should I use this skill?

A task requires Nutrient API document conversion, OCR, table extraction, PII redaction, watermarking, digital signing, or PDF form filling.

What you get

Converted document files, extracted text and tables, OCR output, redacted PDFs, watermarked documents, digital signatures, and filled PDF forms.

  • converted documents
  • extracted text and tables
  • redacted or signed PDFs

By the numbers

  • Supports 6 input formats: PDF, DOCX, XLSX, PPTX, HTML, and images

Files

SKILL.mdMarkdownGitHub ↗

Nutrient Document Processing

Nutrient DWS Processor API でドキュメントを処理します。フォーマット変換、テキストとテーブルの抽出、スキャンされたドキュメントの OCR、PII の編集、ウォーターマークの追加、デジタル署名、PDF フォームの入力が可能です。

セットアップ

[nutrient.io](https://dashboard.nutrient.io/sign_up/?product=processor) で無料の API キーを取得してください

export NUTRIENT_API_KEY="pdf_live_..."

すべてのリクエストは https://api.nutrient.io/buildinstructions JSON フィールドを含むマルチパート POST として送信されます。

操作

ドキュメントの変換

# DOCX から PDF へ
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "document.docx=@document.docx" \
  -F 'instructions={"parts":[{"file":"document.docx"}]}' \
  -o output.pdf

# PDF から DOCX へ
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "document.pdf=@document.pdf" \
  -F 'instructions={"parts":[{"file":"document.pdf"}],"output":{"type":"docx"}}' \
  -o output.docx

# HTML から PDF へ
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "index.html=@index.html" \
  -F 'instructions={"parts":[{"html":"index.html"}]}' \
  -o output.pdf

サポートされている入力形式: PDF、DOCX、XLSX、PPTX、DOC、XLS、PPT、PPS、PPSX、ODT、RTF、HTML、JPG、PNG、TIFF、HEIC、GIF、WebP、SVG、TGA、EPS。

テキストとデータの抽出

# プレーンテキストの抽出
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "document.pdf=@document.pdf" \
  -F 'instructions={"parts":[{"file":"document.pdf"}],"output":{"type":"text"}}' \
  -o output.txt

# テーブルを Excel として抽出
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "document.pdf=@document.pdf" \
  -F 'instructions={"parts":[{"file":"document.pdf"}],"output":{"type":"xlsx"}}' \
  -o tables.xlsx

スキャンされたドキュメントの OCR

# 検索可能な PDF への OCR(100以上の言語をサポート)
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "scanned.pdf=@scanned.pdf" \
  -F 'instructions={"parts":[{"file":"scanned.pdf"}],"actions":[{"type":"ocr","language":"english"}]}' \
  -o searchable.pdf

言語: ISO 639-2 コード(例: engdeufraspajpnkorchi_simchi_traarahinrus)を介して100以上の言語をサポートしています。englishgerman などの完全な言語名も機能します。サポートされているすべてのコードについては、完全な OCR 言語表を参照してください。

機密情報の編集

# パターンベース(SSN、メール)
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "document.pdf=@document.pdf" \
  -F 'instructions={"parts":[{"file":"document.pdf"}],"actions":[{"type":"redaction","strategy":"preset","strategyOptions":{"preset":"social-security-number"}},{"type":"redaction","strategy":"preset","strategyOptions":{"preset":"email-address"}}]}' \
  -o redacted.pdf

# 正規表現ベース
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "document.pdf=@document.pdf" \
  -F 'instructions={"parts":[{"file":"document.pdf"}],"actions":[{"type":"redaction","strategy":"regex","strategyOptions":{"regex":"\\b[A-Z]{2}\\d{6}\\b"}}]}' \
  -o redacted.pdf

プリセット: social-security-numberemail-addresscredit-card-numberinternational-phone-numbernorth-american-phone-numberdatetimeurlipv4ipv6mac-addressus-zip-codevin

ウォーターマークの追加

curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "document.pdf=@document.pdf" \
  -F 'instructions={"parts":[{"file":"document.pdf"}],"actions":[{"type":"watermark","text":"CONFIDENTIAL","fontSize":72,"opacity":0.3,"rotation":-45}]}' \
  -o watermarked.pdf

デジタル署名

# 自己署名 CMS 署名
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "document.pdf=@document.pdf" \
  -F 'instructions={"parts":[{"file":"document.pdf"}],"actions":[{"type":"sign","signatureType":"cms"}]}' \
  -o signed.pdf

PDF フォームの入力

curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "form.pdf=@form.pdf" \
  -F 'instructions={"parts":[{"file":"form.pdf"}],"actions":[{"type":"fillForm","formFields":{"name":"Jane Smith","email":"jane@example.com","date":"2026-02-06"}}]}' \
  -o filled.pdf

MCP サーバー(代替)

ネイティブツール統合には、curl の代わりに MCP サーバーを使用します:

{
  "mcpServers": {
    "nutrient-dws": {
      "command": "npx",
      "args": ["-y", "@nutrient-sdk/dws-mcp-server"],
      "env": {
        "NUTRIENT_DWS_API_KEY": "YOUR_API_KEY",
        "SANDBOX_PATH": "/path/to/working/directory"
      }
    }
  }
}

使用タイミング

  • フォーマット間でのドキュメント変換(PDF、DOCX、XLSX、PPTX、HTML、画像)
  • PDF からテキスト、テーブル、キー値ペアの抽出
  • スキャンされたドキュメントまたは画像の OCR
  • ドキュメントを共有する前の PII の編集
  • ドラフトまたは機密文書へのウォーターマークの追加
  • 契約または合意書へのデジタル署名
  • プログラムによる PDF フォームの入力

リンク

Related skills

FAQ

What file formats does nutrient-document-processing support?

nutrient-document-processing handles PDF, DOCX, XLSX, PPTX, HTML, and image inputs through the Nutrient DWS Processor API for conversion, extraction, OCR, redaction, signing, and form filling.

How do you authenticate Nutrient API requests?

nutrient-document-processing requires exporting NUTRIENT_API_KEY and sending multipart POST requests to https://api.nutrient.io/build with an instructions JSON field defining the document operation.

Backend & APIsintegrationsbackend

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.