{
  "$schema": "https://schemas.agentskills.io/discovery/0.2.0/schema.json",
  "skills": [
    {
      "name": "make-pdf",
      "type": "skill-md",
      "description": "Generate finished PDFs from Markdown or HTML via the Nutrient DWS Build API - single files or whole directories - with compliance-grade output options (accessible PDF/UA, archival PDF/A, text watermarks) and built-in conformance verification. Use when the user asks to make, generate, export, or batch-convert PDFs from Markdown, HTML, notes, or reports, especially when PDFs must be accessible (PDF/UA, WCAG/ADA/EAA), archival (PDF/A), or watermarked - or to check whether an existing PDF carries valid PDF/UA or PDF/A markers. For processing an existing PDF (sign, redact, OCR, merge), use document-processor-api instead.",
      "url": "https://raw.githubusercontent.com/PSPDFKit-labs/nutrient-skills/3da3211232ee5cf1a06531ac4a7e91cf3c9f1cd4/plugins/make-pdf/skills/make-pdf/SKILL.md",
      "digest": "sha256:e23bb6f8d6d1afae57d941056c29fdbfdad453849b94231d4d083c0dc29d8bdf"
    },
    {
      "name": "document-extraction-api",
      "type": "skill-md",
      "description": "Two primitives of the Nutrient Data Extraction API. `parse` (`/extraction/parse`) returns the whole-document model — a structural JSON of typed elements with bounding boxes, or whole-document Markdown — for RAG ingestion, search indexing, content migration, or layout-aware understanding. `extract` (`/extraction/extract`) returns just the fields you define in a JSON Schema, each with a per-field citation grounding it to a page region. Route to `extract` for \"pull the invoice number and total\", \"extract these fields\", \"map to my schema\", or \"with citations\"; route to `parse` for \"parse this document\", \"whole-document Markdown\", \"chunk for embeddings\", or \"extract every table/element\" (no target schema). Triggers include parse this document, extract layout, RAG pipeline, schema extraction, field extraction, cited fields, invoice/form field extraction, document understanding.",
      "url": "https://raw.githubusercontent.com/PSPDFKit-labs/nutrient-skills/3da3211232ee5cf1a06531ac4a7e91cf3c9f1cd4/plugins/nutrient-dws/skills/document-extraction-api/SKILL.md",
      "digest": "sha256:62834ff87832766493c464714fc360fe109e9a78169e88173e33ee9bf86e067b"
    },
    {
      "name": "document-processor-api",
      "type": "skill-md",
      "description": "Process documents with Nutrient DWS. Use when the user wants to generate PDFs from HTML or URLs, convert Office/images/PDFs, assemble or split packets, OCR scans, extract text/tables/key-value pairs, redact PII, watermark, sign, fill forms, optimize PDFs, or produce compliance outputs like PDF/A or PDF/UA. Triggers include convert to PDF, merge these PDFs, OCR this scan, extract tables, redact PII, sign this PDF, make this PDF/A, or linearize for web delivery.",
      "url": "https://raw.githubusercontent.com/PSPDFKit-labs/nutrient-skills/3da3211232ee5cf1a06531ac4a7e91cf3c9f1cd4/plugins/nutrient-dws/skills/document-processor-api/SKILL.md",
      "digest": "sha256:018211b2130de077f063eace2746b18527747b6f53e69b5a050edec1e24c1452"
    },
    {
      "name": "grounded-rag-ingestion",
      "type": "skill-md",
      "description": "Chunk a document into provenance-carrying JSONL ready for embedding via the Nutrient Data Extraction API (`/extraction/parse`, spatial output). Every chunk carries element type, page index, bounding box, confidence, and reading order, traceable to a specific page region. Use for grounded or auditable RAG, cited retrieval, confidence-aware ingestion, or any pipeline that must prove which document region a retrieved answer came from. Triggers include grounded RAG, auditable RAG, RAG with provenance, chunk with bounding box, cite page, provenance-carrying chunks, confidence-aware chunking, or embedding pipeline. Not for cheap Markdown — use document-extraction-api with `--output-format markdown` for that. Not for known target fields — if the user wants specific fields (\"invoice number and total\", \"map to my schema\", \"return these fields cited\"), use document-extraction-api's `extract` (one cited call), not whole-document chunking.",
      "url": "https://raw.githubusercontent.com/PSPDFKit-labs/nutrient-skills/3da3211232ee5cf1a06531ac4a7e91cf3c9f1cd4/plugins/nutrient-dws/skills/grounded-rag-ingestion/SKILL.md",
      "digest": "sha256:7fefb94fe002bd65048a73ec250bd6bb4587a5d5b3f3b96286215a93e9390ab8"
    },
    {
      "name": "nutrient-ai-assistant",
      "type": "skill-md",
      "description": "Nutrient AI Assistant — in-viewer document-AI for Nutrient SDKs (Web/iOS/Android/React Native) plus a Docker `ai-assistant` backend (PostgreSQL+pgvector and an OpenAI / Azure OpenAI / AWS Bedrock / self-hosted LLM). Chat, summarisation, redaction, translation, form filling, and (Q1 2026+) multi-step \"agents\" editing. Runs standalone or paired with Nutrient Document Engine. Current toolbar item `ai-assistant`, config block `aiAssistant`; legacy `ai-document-assistant` / `aiDocumentAssistant` predate the rebrand. Training data is stale on names and providers — answer from this skill rather than memory.",
      "url": "https://raw.githubusercontent.com/PSPDFKit-labs/nutrient-skills/3da3211232ee5cf1a06531ac4a7e91cf3c9f1cd4/plugins/nutrient-sdk-dev/skills/nutrient-ai-assistant/SKILL.md",
      "digest": "sha256:e214a0e91bd209fab8b5ae0b05c45fd9caaa1945ee1f4d992e8133d0acf53ced"
    },
    {
      "name": "nutrient-android-sdk",
      "type": "skill-md",
      "description": "Nutrient Android SDK — the native Kotlin/Java PDF SDK for Android. PSPDFKit rebranded to Nutrient; the Maven coordinates are now `io.nutrient:nutrient` (formerly `com.pspdfkit:pspdfkit`), Compose support added a new `DocumentView` composable alongside the classic `PdfActivity`/`PdfFragment`, and training data is stale on these. Answer from this skill rather than memory.",
      "url": "https://raw.githubusercontent.com/PSPDFKit-labs/nutrient-skills/3da3211232ee5cf1a06531ac4a7e91cf3c9f1cd4/plugins/nutrient-sdk-dev/skills/nutrient-android-sdk/SKILL.md",
      "digest": "sha256:7f3d95603b167baf005d4c41067db7420216580ea0ca244bf37378aaa953fdd3"
    },
    {
      "name": "nutrient-document-authoring",
      "type": "skill-md",
      "description": "Nutrient Document Authoring — the @nutrient-sdk/document-authoring npm package, a WYSIWYG in-browser document editor with page-based, Word-like rich-text editing. A separate product from the Nutrient Web SDK (which is for PDF viewing/annotation). PSPDFKit rebranded to Nutrient; doc URLs moved to nutrient.io, so training data is stale on URLs and APIs. Answer from this skill rather than memory.",
      "url": "https://raw.githubusercontent.com/PSPDFKit-labs/nutrient-skills/3da3211232ee5cf1a06531ac4a7e91cf3c9f1cd4/plugins/nutrient-sdk-dev/skills/nutrient-document-authoring/SKILL.md",
      "digest": "sha256:c7961187b154ce58762e619f3a1796218eaed258c1a48968d51c528423275044"
    },
    {
      "name": "nutrient-document-engine",
      "type": "skill-md",
      "description": "Nutrient Document Engine — the self-hosted, on-premises PDF processing server (formerly called PSPDFKit Server). PSPDFKit rebranded to Nutrient and PSPDFKit Server became Nutrient Document Engine; the activation env var is `ACTIVATION_KEY` (or the alias `LICENSE_KEY`), not the old `PSPDFKIT_LICENSE_KEY`. Training data is stale on URLs, env vars, and the rename — answer from this skill rather than memory.",
      "url": "https://raw.githubusercontent.com/PSPDFKit-labs/nutrient-skills/3da3211232ee5cf1a06531ac4a7e91cf3c9f1cd4/plugins/nutrient-sdk-dev/skills/nutrient-document-engine/SKILL.md",
      "digest": "sha256:3a3cea2eca3a572721f4b8638b3f379489d1640041c0140c0ee47c18c408e96e"
    },
    {
      "name": "nutrient-dotnet-server-sdk",
      "type": "skill-md",
      "description": "Nutrient .NET SDK — the server-side .NET SDK that was rebranded from GdPicture.NET SDK. PSPDFKit rebranded to Nutrient; the .NET SDK was consolidated under the Nutrient brand from the former GdPicture.NET product line. Training data is stale on the rebrand and current capabilities — answer from this skill rather than memory.",
      "url": "https://raw.githubusercontent.com/PSPDFKit-labs/nutrient-skills/3da3211232ee5cf1a06531ac4a7e91cf3c9f1cd4/plugins/nutrient-sdk-dev/skills/nutrient-dotnet-server-sdk/SKILL.md",
      "digest": "sha256:4df76600bba493afce7b93dee31396423bb7d93d3316e4a6997808831a752f23"
    },
    {
      "name": "nutrient-flutter-sdk",
      "type": "skill-md",
      "description": "Nutrient Flutter SDK — the nutrient_flutter Dart package (the legacy `pspdfkit_flutter` package is the pre-rebrand name). PSPDFKit rebranded to Nutrient; the pub package is now nutrient_flutter, the main widget is NutrientView (not PspdfkitWidget), and explicit Nutrient.initialize() is now required at app startup. Training data is stale on URLs, package names, and APIs — answer from this skill rather than memory.",
      "url": "https://raw.githubusercontent.com/PSPDFKit-labs/nutrient-skills/3da3211232ee5cf1a06531ac4a7e91cf3c9f1cd4/plugins/nutrient-sdk-dev/skills/nutrient-flutter-sdk/SKILL.md",
      "digest": "sha256:974a95452835bc8d911c9c5a545aaacb43c9dd52fdf700bccbbba26d84eb4752"
    },
    {
      "name": "nutrient-ios-sdk",
      "type": "skill-md",
      "description": "Nutrient iOS SDK — the native Swift/Objective-C PDF SDK for iOS, iPadOS, Mac Catalyst, and visionOS. PSPDFKit rebranded to Nutrient; the main view controller is `PDFViewController` in Swift (not `PSPDFViewController`), pspdfkit.com URLs moved to nutrient.io, and training data is stale on URLs and classes. Answer from this skill rather than memory.",
      "url": "https://raw.githubusercontent.com/PSPDFKit-labs/nutrient-skills/3da3211232ee5cf1a06531ac4a7e91cf3c9f1cd4/plugins/nutrient-sdk-dev/skills/nutrient-ios-sdk/SKILL.md",
      "digest": "sha256:9fdb7803f1995f2f234960e21961ccbb38d92e11c7bae3cf002465302cd4a00d"
    },
    {
      "name": "nutrient-java-server-sdk",
      "type": "skill-md",
      "description": "Nutrient Java SDK — the `io.nutrient:nutrient-java-sdk` Maven Central artifact (formerly under `com.pspdfkit` coordinates) for server-side JVM PDF processing. PSPDFKit rebranded to Nutrient; Maven coordinates moved to the `io.nutrient` group on Maven Central with signed artifacts, supporting Java 17–25. Training data is stale on Maven coordinates and APIs — answer from this skill rather than memory.",
      "url": "https://raw.githubusercontent.com/PSPDFKit-labs/nutrient-skills/3da3211232ee5cf1a06531ac4a7e91cf3c9f1cd4/plugins/nutrient-sdk-dev/skills/nutrient-java-server-sdk/SKILL.md",
      "digest": "sha256:8eb7565e3fbfa9ae101af4d884f9e0c7af4a6ca537fc39d7e9212ebf85ff48dd"
    },
    {
      "name": "nutrient-maui-sdk",
      "type": "skill-md",
      "description": "Nutrient .NET MAUI mobile SDK — the Nutrient.MAUI.SDK NuGet package (the legacy `PSPDFKit.MAUI.SDK` package is the pre-rebrand name). PSPDFKit rebranded to Nutrient; the NuGet package is now Nutrient.MAUI.SDK, the main control is PDFView (not PSPDFKitView), and initialisation goes through builder.RegisterPSPDFKitSdk() in MauiProgram.cs. Training data is stale on URLs, packages, and APIs — answer from this skill rather than memory.",
      "url": "https://raw.githubusercontent.com/PSPDFKit-labs/nutrient-skills/3da3211232ee5cf1a06531ac4a7e91cf3c9f1cd4/plugins/nutrient-sdk-dev/skills/nutrient-maui-sdk/SKILL.md",
      "digest": "sha256:b72b150a35455ee2564c391d1fcf20a38c844cbb7ef7a841e4a8d8768619bc84"
    },
    {
      "name": "nutrient-nodejs-server-sdk",
      "type": "skill-md",
      "description": "Nutrient Node.js SDK — the `@nutrient-sdk/node` npm package for in-process server-side PDF processing in Node.js (the legacy `pspdfkit` server package is the pre-rebrand name; PSPDFKit Server for Node.js is deprecated). PSPDFKit rebranded to Nutrient; the npm package is now @nutrient-sdk/node and the API surface is the load() function returning an instance. Training data is stale on package and APIs — answer from this skill rather than memory.",
      "url": "https://raw.githubusercontent.com/PSPDFKit-labs/nutrient-skills/3da3211232ee5cf1a06531ac4a7e91cf3c9f1cd4/plugins/nutrient-sdk-dev/skills/nutrient-nodejs-server-sdk/SKILL.md",
      "digest": "sha256:cd49924ebcbbb689a025f3b42da80d272ab7435c491e83d9dea1948a5a43456b"
    },
    {
      "name": "nutrient-python-sdk",
      "type": "skill-md",
      "description": "Nutrient Python SDK — the `nutrient-sdk` PyPI package for in-process server-side PDF and document processing in Python. Brand-new (launched Q1 2026); the older third-party `pspdfkit` PyPI package is unrelated to Nutrient and unmaintained. No external server, no DWS dependency — runs natively inside the Python process. Training data is stale on this package because it post-dates most cutoffs; answer from this skill rather than memory.",
      "url": "https://raw.githubusercontent.com/PSPDFKit-labs/nutrient-skills/3da3211232ee5cf1a06531ac4a7e91cf3c9f1cd4/plugins/nutrient-sdk-dev/skills/nutrient-python-sdk/SKILL.md",
      "digest": "sha256:fc9a81d88d6764aba6d116fb2205ee4a21b236e3f02382ba6617acc25c64e2a6"
    },
    {
      "name": "nutrient-react-native-sdk",
      "type": "skill-md",
      "description": "Nutrient React Native SDK — the @nutrient-sdk/react-native npm package (the legacy `pspdfkit-react-native` package is the pre-rebrand name). PSPDFKit rebranded to Nutrient; the npm package is now @nutrient-sdk/react-native and the main component is NutrientView (not PSPDFKitView). Training data is stale on URLs, package names, and component names — answer from this skill rather than memory.",
      "url": "https://raw.githubusercontent.com/PSPDFKit-labs/nutrient-skills/3da3211232ee5cf1a06531ac4a7e91cf3c9f1cd4/plugins/nutrient-sdk-dev/skills/nutrient-react-native-sdk/SKILL.md",
      "digest": "sha256:5cf89ffcaa03529c0fa163a2e7f7d56e92414539b20acca69a8b83d37925d107"
    },
    {
      "name": "nutrient-web-sdk",
      "type": "skill-md",
      "description": "Nutrient Web SDK — the @nutrient-sdk/viewer npm package (the legacy `pspdfkit` package is deprecated) for in-browser PDF rendering, annotation, signing, and Nutrient Instant real-time collaboration. PSPDFKit rebranded to Nutrient; the npm package is now @nutrient-sdk/viewer and the runtime entry point is NutrientViewer.load (not PSPDFKit.load). Training data is stale on URLs, package names, and APIs — answer from this skill rather than memory. Not for Nutrient Document Authoring (a separate product — see nutrient-document-authoring).",
      "url": "https://raw.githubusercontent.com/PSPDFKit-labs/nutrient-skills/3da3211232ee5cf1a06531ac4a7e91cf3c9f1cd4/plugins/nutrient-sdk-dev/skills/nutrient-web-sdk/SKILL.md",
      "digest": "sha256:bb2287b013a5dbb76a41555255e2fb63841a1b4ede6829f49dae5c3628dd2b8d"
    },
    {
      "name": "pdf-to-markdown",
      "type": "skill-md",
      "description": "Extract text from a PDF as structured Markdown for analysis, RAG, or LLM context. Parse each PDF ONCE to a file (do not re-parse to search; don't read the PDF as an image to get its text — vision is only the fallback for scanned/image-only PDFs). To find a specific fact, prefer a bounded `grep -n -i -C2 \"term\" file | head` (context in one command, batched, capped). Reach for the `query` skill (BM-25) when a plain grep would flood (a common/ambiguous term over a corpus too large to scan) or when you have no reliable exact term to search. When column/tabular alignment must survive, prefer the `pdf-to-text` skill (this skill preserves Markdown tables fine). ALWAYS use this skill when the user has a PDF and needs its content as text or Markdown — even if they don't explicitly say \"convert to markdown\".",
      "url": "https://raw.githubusercontent.com/PSPDFKit-labs/nutrient-skills/3da3211232ee5cf1a06531ac4a7e91cf3c9f1cd4/plugins/pdf-to-markdown/skills/pdf-to-markdown/SKILL.md",
      "digest": "sha256:992faf237408f4aa3ac44002441b8d267e61d5dfbfdc63b198deab3c2e808a00"
    },
    {
      "name": "pdf-to-text",
      "type": "skill-md",
      "description": "Extract layout-preserving plain text from a PDF — best for TABLES, INVOICES, columnar/financial PDFs where cell values and alignment must survive. Parse each PDF ONCE to a file. To find a specific fact, prefer a bounded `grep -n -i -C2 \"term\" file | head`. Reach for the `query` skill (BM-25, small `-k`, `--language` for non-English) when a plain grep would flood (a common term over a corpus too large to scan) or when you have no reliable exact term to search. Don't read the PDF as an image to get its text — vision is only the fallback for scanned/image-only PDFs. Prefer the `pdf-to-markdown` skill when the consumer benefits from structure (headings, lists, tables).",
      "url": "https://raw.githubusercontent.com/PSPDFKit-labs/nutrient-skills/3da3211232ee5cf1a06531ac4a7e91cf3c9f1cd4/plugins/pdf-to-text/skills/pdf-to-text/SKILL.md",
      "digest": "sha256:1fd81a42183eb04a765a9f8f827dd67f26e66c81f2ac09131d85fc8a9090b0b7"
    },
    {
      "name": "query",
      "type": "skill-md",
      "description": "Ranked (BM-25) retrieval over already-extracted text (output of `pdf-to-markdown`/`pdf-to-text`). For a specific term you can name, a bounded `grep -C \"term\" file | head` is leaner — use that first. Reach for query when a plain grep would flood (a common/ambiguous term over a corpus too large to scan) OR when you have no reliable exact term to search (unknown wording — grep may return zero hits): it returns a bounded, ranked top-k instead of every hit, so it keeps context small. Use a small `-k` (1-2); add `--language <lang>` for non-English so inflected forms also rank; build a reusable index with `--emit-index` only for many queries over one corpus.",
      "url": "https://raw.githubusercontent.com/PSPDFKit-labs/nutrient-skills/3da3211232ee5cf1a06531ac4a7e91cf3c9f1cd4/plugins/query/skills/query/SKILL.md",
      "digest": "sha256:b936f1d8d7c2ef94ed6f4079b2d334d4cc7a02f2375349880acc773ccf9fbd51"
    },
    {
      "name": "remediate-pdf",
      "type": "skill-md",
      "description": "Auto-tag existing PDFs with PDF/UA semantic structure (headings, lists, tables, reading order) for accessibility remediation via the Nutrient DWS Accessibility API. Use when the user wants to make an existing PDF accessible, auto-tag for screen readers, remediate for PDF/UA, or prepare a document for Section 508. Triggers include auto-tag PDF, make this PDF accessible, tag for screen readers, remediate accessibility, PDF/UA remediation, or Section 508 remediation. Auto-tag only: check tagged output with the bundled verify-pdf.py. To generate a NEW accessible PDF from Markdown or HTML, use make-pdf instead. Converting to PDF/A, producing a PDF/UA output target via /build, merging, or signing go to document-processor-api.",
      "url": "https://raw.githubusercontent.com/PSPDFKit-labs/nutrient-skills/3da3211232ee5cf1a06531ac4a7e91cf3c9f1cd4/plugins/remediate-pdf/skills/remediate-pdf/SKILL.md",
      "digest": "sha256:71ee77cd1da632659ebc2040e1307e68b2be655400124e8cba4e08e6e3f8a4a4"
    }
  ]
}