Collaboratively annotate PDF section-by-section: propose markup (highlights, notes, stamps), apply on approval, review via screenshots, iterate.
From pdf-viewernpx claudepluginhub anthropics/knowledge-work-plugins --plugin pdf-viewer[path-or-url]/annotateAdds inline documentation (JSDoc, docstrings, comments) to under-documented functions, methods, complex logic blocks, parameters, returns, and modules.
/annotateAdd visual annotations (boxes, highlights, callouts) to the current page and take a screenshot. Use during user testing to highlight issues or confusion points.
/annotateConstruction document annotation and markup for superintendents. Mark up plan sheets with work areas, hold zones, and redlines. Extract and annotate spec sections for trade distribution. Annotate construction photos with deficiency callouts and measurement overlays. Create annotated drawing markups for RFI submission packages. All annotations are tracked as structured records with full traceability to source data.
If you need to check which tools are connected, see CONNECTORS.md.
Walk through a document with the user, proposing and applying annotations section by section. The user reviews each batch in the live viewer before you continue.
display_pdf (or use existing viewUUID if already open)interact → get_text on the first page range
(≤20 pages) to read content"I'll highlight the termination clause on page 2, add a note 'Review 30-day window' next to it, and stamp page 1 as DRAFT. Sound good?"
interact with batched commands:
add_annotations + get_screenshot of the affected pageIf the user gives explicit instructions ("highlight paragraph 3", "stamp CONFIDENTIAL on every page"), skip the proposal step and execute directly. Still confirm with a screenshot.
highlight_text (auto-finds text — preferred),
highlight, underline, strikethrough/pdf-viewer:sign)highlight_text over manual rects for text — it finds
coordinates automaticallyinteract callget_screenshot so the user sees the result