Our review
Converts files (PDF, DOCX, PPTX, XLSX, EPUB, CSV, JSON, images, audio, ZIP) and URLs, including GitHub links, into Markdown through an npx CLI or a TypeScript SDK.
Strengths
- Handles a very broad set of input formats with a single command
- Also covers web URLs and GitHub resources (repos, files, gists, issues, PRs)
- Two useful output modes: raw markdown with -q or a { markdown, title } object with --json
- Available both as a CLI and a TypeScript SDK for scripting
Limitations
- Requires Node.js and npm registry access to run npx @shiftlabs/markit
- Output is Markdown, so the source document's rich layout is flattened
- No mention of handling authenticated/private URLs or offline processing
Use it when you need to pull the content of a document or web page into Markdown that an agent or pipeline can work with.
Avoid it when you must preserve the document's exact visual formatting, or when the environment lacks Node.js or network access.
Security analysis
CautionThe skill is a straightforward document/URL-to-Markdown converter with no destructive, obfuscated, or exfiltration instructions. However, it relies on executing an unpinned third-party npm package and fetching arbitrary remote content, so it carries legitimate but notable network and supply-chain risk.
- •Invokes a third-party npm package via npx without a pinned version, introducing supply-chain and remote-code execution risk.
- •Converts arbitrary URLs and files, which may fetch untrusted network content or process sensitive local documents.
- •No declared allowed-tools, so execution permissions are implicit.
Examples
Convert ~/Downloads/quarterly-report.pdf to markdown and save it as quarterly-report.mdPull https://github.com/owner/repo/issues/42 as raw markdown so I can summarize itTurn https://en.wikipedia.org/wiki/Markdown into markdown and return it as JSON with the titlename: markit description: Convert files and URLs to Markdown. Supports PDF, DOCX, PPTX, XLSX, HTML, EPUB, CSV, JSON, GitHub URLs, images, audio, ZIP, and more. Use when you need to extract content from any document format.
markit
Convert anything to Markdown.
CLI
# Convert a file
npx @shiftlabs/markit report.pdf -q
# Convert a URL
npx @shiftlabs/markit https://en.wikipedia.org/wiki/Markdown -q
# GitHub URLs (repos, files, gists, issues, PRs)
npx @shiftlabs/markit https://github.com/owner/repo -q
npx @shiftlabs/markit https://github.com/owner/repo/issues/42 -q
npx @shiftlabs/markit https://gist.github.com/user/id -q
# Write to file
npx @shiftlabs/markit document.docx -q -o output.md
# See all options
npx @shiftlabs/markit --help
# See supported formats
npx @shiftlabs/markit formats
-q gives raw markdown. --json gives { markdown, title }.
SDK
import { Markit } from "@shiftlabs/markit";
const markit = new Markit();
const { markdown } = await markit.convertFile("report.pdf");
const { markdown } = await markit.convertUrl("https://example.com");
const { markdown } = await markit.convert(buffer, { extension: ".docx" });
Technical & On-Page SEO Audit
Content
Complete technical and on-page SEO audit with prioritized recommendations.
Page Conversion Optimization
Content
Analyze and optimize your web pages to maximize conversion rates.
Content Repurposer
Content
Transforms a single piece of content into platform-adapted publications.