nutrient-document-processing by pspdfkit-labs/nutrient-agent-skill
npx skills add https://github.com/pspdfkit-labs/nutrient-agent-skill --skill nutrient-document-processing当文档保真度、合规性或多步骤处理比本地工具便利性更重要时,使用 Nutrient DWS 进行托管文档工作流。
在 https://dashboard.nutrient.io/sign_up/?product=processor 获取 Nutrient DWS API 密钥。
直接 API 调用使用 Authorization: Bearer $NUTRIENT_API_KEY。
export NUTRIENT_API_KEY="nutr_sk_..."
MCP 设置通常使用 @nutrient-sdk/dws-mcp-server 和 NUTRIENT_DWS_API_KEY。
脚本位于相对于此 SKILL.md 文件的 scripts/ 目录中。使用包含此 SKILL.md 的目录作为工作目录:
cd <directory containing this SKILL.md> && uv run scripts/<script>.py --help
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
页面范围使用 start:end 格式,基于 0 的索引,且 end 是排他的。负数索引表示从末尾开始计数。
scripts/*.py。assets/templates/custom-workflow-template.py。references/ 文档和直接 API 负载。convert.py -> 在 pdf、pdfa、pdfua、docx、xlsx、pptx、png、jpeg、webp、html 和 markdown 之间转换merge.py -> 将多个文件合并为一个 PDFsplit.py -> 按页面范围将一个 PDF 拆分为多个 PDFadd-pages.py -> 追加空白页delete-pages.py -> 删除特定页面duplicate-pages.py -> 将页面重新排序或复制到新的 PDF 中rotate.py -> 旋转选定的页面ocr.py -> 对扫描的 PDF 或图像进行 OCRextract-text.py -> 将文本提取为 JSONextract-table.py -> 提取表格extract-key-value-pairs.py -> 提取键值对watermark-text.py -> 应用文本水印redact-ai.py -> 检测并应用 AI 驱动的信息擦除sign.py -> 对本地 PDF 进行数字签名password-protect.py -> 写入加密的输出 PDFoptimize.py -> 通过 JSON 应用优化和线性化选项不要在 scripts/ 目录下添加新的已提交的流水线脚本。
当用户要求在一次运行中执行多个操作时:
assets/templates/custom-workflow-template.py 复制到临时位置,例如 /tmp/ndp-workflow-<task>.py。uv run /tmp/ndp-workflow-<task>.py ... 运行它。split.py 需要一个多页 PDF,无法从单页文档中提取范围。delete-pages.py 必须至少保留一页,不能删除整个文档。sign.py 仅接受主 PDF 的本地文件路径。file.url 输入。output.type 进行转换和最终目标格式设置。在构建直接 API 负载时,使用 actions 进行转换。scripts/ 目录下。按需阅读:
references/request-basics.md -> 端点模型、身份验证、multipart 与 JSON、积分、限制和错误references/generation-and-conversion.md -> HTML/URL 生成和格式转换references/pdf-manipulation.md -> 合并、拆分、页面范围、旋转和扁平化工作流references/extraction-and-ocr.md -> OCR、文本提取、表格和键值对工作流references/security-signing-and-forms.md -> 信息擦除、水印、签名、表单和密码references/compliance-and-optimization.md -> PDF/A、PDF/UA、优化和线性化references/workflow-recipes.md -> 常见业务文档工作流的端到端排序模式asyncio.run(main()) 运行。uv add nutrient-dws 安装依赖项。npm i -g @nutrient-sdk/dws-mcp-server@<pinned-version>NUTRIENT_DWS_API_KEY 存储在已提交的 JSON 配置文件中。
SANDBOX_PATH 将文件访问限制在所需的最小工作目录。每周安装数
102
代码仓库
GitHub 星标数
1
首次出现
2026年2月6日
安全审计
安装于
opencode102
gemini-cli100
github-copilot100
codex99
kimi-cli98
cursor98
Use Nutrient DWS for managed document workflows where fidelity, compliance, or multi-step processing matters more than local-tool convenience.
Get a Nutrient DWS API key at https://dashboard.nutrient.io/sign_up/?product=processor.
Direct API calls use Authorization: Bearer $NUTRIENT_API_KEY.
export NUTRIENT_API_KEY="nutr_sk_..."
MCP setups commonly use @nutrient-sdk/dws-mcp-server with NUTRIENT_DWS_API_KEY.
Scripts live in scripts/ relative to this SKILL.md. Use the directory containing this SKILL.md as the working directory:
cd <directory containing this SKILL.md> && uv run scripts/<script>.py --help
Page ranges use start:end with 0-based indexes and end-exclusive semantics. Negative indexes count from the end.
scripts/*.py for covered single-operation workflows.assets/templates/custom-workflow-template.py for multi-step jobs that should still run through the Python client.references/ docs and direct API payloads for capabilities that do not yet have a dedicated helper script, especially HTML/URL generation and compliance tuning.convert.py -> convert between pdf, pdfa, pdfua, docx, xlsx, pptx, png, jpeg, webp, html, and markdownDo not add new committed pipeline scripts under scripts/.
When the user asks for multiple operations in one run:
assets/templates/custom-workflow-template.py to a temporary location such as /tmp/ndp-workflow-<task>.py.uv run /tmp/ndp-workflow-<task>.py ....split.py requires a multi-page PDF and cannot extract ranges from a single-page document.delete-pages.py must retain at least one page and cannot delete the entire document.sign.py only accepts local file paths for the main PDF.file.url inputs when the source already lives at a stable URL and you want to avoid local uploads.output.type for conversion and finalization targets. Use actions for transformations when building direct API payloads.scripts/.Read only what you need:
references/request-basics.md -> endpoint model, auth, multipart vs JSON, credits, limits, and errorsreferences/generation-and-conversion.md -> HTML/URL generation and format conversionreferences/pdf-manipulation.md -> merge, split, page-range, rotate, and flatten workflowsreferences/extraction-and-ocr.md -> OCR, text extraction, tables, and key-value workflowsreferences/security-signing-and-forms.md -> redaction, watermarking, signatures, forms, and passwordsreferences/compliance-and-optimization.md -> PDF/A, PDF/UA, optimization, and linearizationreferences/workflow-recipes.md -> end-to-end sequencing patterns for common business document workflowsasyncio.run(main()).uv add nutrient-dws.npm i -g @nutrient-sdk/dws-mcp-server@<pinned-version>NUTRIENT_DWS_API_KEY in committed JSON config files.
SANDBOX_PATH to the minimum required working directory.Weekly Installs
102
Repository
GitHub Stars
1
First Seen
Feb 6, 2026
Security Audits
Gen Agent Trust HubWarnSocketPassSnykWarn
Installed on
opencode102
gemini-cli100
github-copilot100
codex99
kimi-cli98
cursor98
GitHub Actions 官方文档查询助手 - 精准解答 CI/CD 工作流问题
45,200 周安装
merge.py -> merge multiple files into one PDFsplit.py -> split one PDF into multiple PDFs by page rangesadd-pages.py -> append blank pagesdelete-pages.py -> remove specific pagesduplicate-pages.py -> reorder or duplicate pages into a new PDFrotate.py -> rotate selected pagesocr.py -> OCR scanned PDFs or imagesextract-text.py -> extract text to JSONextract-table.py -> extract tablesextract-key-value-pairs.py -> extract key-value pairswatermark-text.py -> apply a text watermarkredact-ai.py -> detect and apply AI-powered redactionssign.py -> digitally sign a local PDFpassword-protect.py -> write encrypted output PDFsoptimize.py -> apply optimization and linearization-style options via JSON