Doc Extract Skill for Claude
Extract plain text from a document file - PDF, DOCX, XLSX, PPTX, RTF, or plain text/markdown/HTML. Use when a binary document needs to be turned into text, for example a contract PDF or an EHR DocumentReference attachment. Other skills (fhir) invoke scripts/extract.ts directly; the contracts MCP server bundles its own copy (servers/documents/src/extract.mjs) so its bundle stays self-contained — port fixes to both.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/anthropics/healthcare --skill doc-extractWhat comes with it
16 465 bytes besides the instructionWhat it tells the agent to use
found in the instruction textThe instruction itself
5 sections, as written by the authordoc-extract
Shared document-to-text extraction. One script, no state: reads an input file, prints JSON to stdout, writes nothing to disk (PHI-safe — no caches, no temp files; callers own any caching).
Setup (once)
cd <this skill dir> && bun install
This pulls liteparse (the lit bin, used for PDF/DOCX/XLSX/PPTX, OCR included) and rtf-to-text (RTF). Without it, PDFs still work via a pdftotext -layout fallback if poppler is installed; other binary formats require liteparse.
Use
bun <this skill dir>/scripts/extract.ts <input-file> [--content-type <mime>]
Output on stdout:
{ "text": "...", "method": "liteparse | pdftotext | rtf-to-text | passthrough", "pages": 12 }
textis page-anchored for paged formats:=== [page N] ===markers between pages.pagesis present when page markers exist.methodis the extractor that actually produced the text.- Format is taken from the file extension; pass
--content-type(e.g.application/pdf) when the file has no useful extension, as with downloaded EHR attachments. Note liteparse refuses extension-less files, so those PDFs go through thepdftotextfallback. - Errors print
{"error": "..."}to stderr and exit 1.
Table caveat
Tables with multiple value columns (option A vs option B, in-tier vs out-of-tier) can interleave columns line-by-line in the extracted text: fragments of adjacent cells alternate, and a cell's text can even land mid-sentence inside a neighboring column. Values usually survive, but which column a value belongs to can become ambiguous. When an answer comes from one column of a multi-column table and the document has no redundant restatement of the value elsewhere, verify it by reading the original page directly before treating it as ground truth. The extracted text's === [page N] === anchor tells you which page: pass it to the Read tool's pages parameter (e.g. pages: "37") to render just that page to vision instead of the whole document.
For other skills
Import the functions instead of shelling out when you're already in bun TS:
import { extract, resolveLit } from "../doc-extract/scripts/extract";
const lit = resolveLit([myRoot]); // also checks myRoot/node_modules/.bin/lit
const text = extract(lit, "/path/to/file.pdf"); // string | null
The contracts skill consumes it this way (its ingest caching stays on the contracts side).
Other skills for the same job
different authors, same section of the catalogue
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.
Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions \"deck,\" \"slides,\" \"presentation,\" or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.
Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions wikilinks, callouts, frontmatter, tags, embeds, or Obsidian notes.
Phylogenetic tree toolkit (ETE). Tree manipulation (Newick/NHX), evolutionary event detection, orthology/paralogy, NCBI taxonomy, visualization (PDF/SVG), for phylogenomics.
Low-level plotting library for full customization. Use when you need fine-grained control over every plot element, creating novel plot types, or integrating with specific scientific workflows. Export to PNG/PDF/SVG for publication. For quick statistical plots use seaborn; for interactive plots use plotly; for publication-ready multi-panel figures with journal styling, use scientific-visualization.
PDF manipulation toolkit. Extract text/tables, create PDFs, merge/split, fill forms, for programmatic document processing and analysis.
Presentation toolkit (.pptx). Create/edit slides, layouts, content, speaker notes, comments, for programmatic presentation creation and modification.
How to use it
Take anthropics/doc-extract from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.