Nutrient’s remediate-pdf skill auto-tags existing PDFs
with PDF/UA semantic structure through the dedicated DWS Accessibility
API — and the sibling verifier proves what the tagging achieved.
remediate-pdf ships in the same nutrient-dws
plugin as make-pdf. One install
gives your agent both skills. Set NUTRIENT_ACCESSIBILITY_API_KEY
before auto-tagging an existing PDF.
Add the
Nutrient skills marketplace, then install the nutrient-dws plugin. The plugin includes
both make-pdf and remediate-pdf.
/plugin marketplace add pspdfkit-labs/nutrient-skills/plugin install nutrient-dws@nutrient-skills
The skill uses the dedicated Nutrient DWS Accessibility API. It is
a separate product from the DWS Build API and requires its own NUTRIENT_ACCESSIBILITY_API_KEY. A Processor key returns a 403 response.
The Accessibility API analyzes the document and adds the structure assistive technology needs to interpret its content and order.
Add heading structure from H1 through H6 and semantic list structure.
Identify tables with TR, TD, and TH structure.
Establish reading order and mark content that should be treated as an artifact.
In a live run, the same structural verifier checked an untagged PDF, then checked its output after one Accessibility API auto-tag call.
It was missing the pdfuaid claim, MarkInfo,
StructTreeRoot, Lang, and DisplayDocTitle.
The remediated output had pdfuaid:part 1, Lang en-US, and its title in XMP. The verifier’s final verdict was PASS.
This is structural PDF/UA-1 verification, not certification. Use an
optional full veraPDF audit when deeper conformance evidence
is needed.
Auto-tagging improves document structure, but it does not guarantee PDF/UA conformance. Nutrient’s benchmark cites approximately 96.5% PDF/UA conformance, not 100%.
The Accessibility API has no conformance-validation endpoint.
Check the tagged PDF with make-pdf’s verify-pdf.py for structural PDF/UA-1 signals, with an optional full veraPDF audit. Human review is still needed for requirements such as alt text.
The free tier includes 20 auto-tagged pages per month, and the
script includes a quota-confirmation gate. Files can be up to 150
MiB. The call requires its own NUTRIENT_ACCESSIBILITY_API_KEY; a Processor key returns 403.
PDF remediation is relevant to WCAG, ADA, EAA, and Section 508 work, including the US ADA Title II deadline in April 2026.
remediate-pdf is an AI-agent skill that fixes existing PDFs by using the dedicated Nutrient DWS Accessibility API to add PDF/UA semantic structure, including headings, lists, tables, reading order, and artifact marking.
Set NUTRIENT_ACCESSIBILITY_API_KEY to a key for the Nutrient DWS Accessibility API. This is a separate product and key from the DWS Build API used by make-pdf. A Processor key returns a 403 response.
The free tier includes 20 auto-tagged pages per month, and the script has a quota-confirmation gate before it makes the call. The maximum input file size is 150 MiB.
No. Auto-tagging improves accessibility but does not guarantee conformance; Nutrient’s benchmark cites approximately 96.5% PDF/UA conformance. Treat the output as remediated, not certified. Verify it with make-pdf’s verify-pdf.py, optionally escalate to a full veraPDF audit, and include human review for needs such as alt text.
They cover different parts of the document lifecycle. remediate-pdf fixes existing PDFs through the Accessibility API, while make-pdf generates new PDFs from Markdown or HTML through the DWS Build API. Both skills come with the same nutrient-dws plugin.
The skill’s PDF/UA semantic tagging is relevant to accessibility work connected to Section 508, WCAG, ADA, and EAA requirements. Auto-tagging is a remediation step, not certification, so verification and human review remain necessary.
Remediate existing PDFs, generate new ones, or work directly with Nutrient’s document and accessibility products.