Markdown Converter
- 259 installs
- 6.5k repo stars
- Updated August 3, 2026
- steipete/agent-scripts
This is a copy of markdown-converter by intellectronica - installs and ranking accrue to the original listing.
markdown-converter is an agent skill that converts PDF, Office, HTML, data, media, and archive files to Markdown using uvx markitdown without a local install.
About
markdown-converter is a steipete/agent-scripts skill that turns heterogeneous files into Markdown via the markitdown CLI run through uvx—no separate installation required. Basic usage covers stdout conversion, -o output paths, and stdin pipes: uvx markitdown input.pdf -o output.md. Supported inputs span documents (PDF, .docx, .pptx, .xlsx, .xls), web and data (HTML, CSV, JSON, XML), media with EXIF plus OCR or transcription, and archives including ZIP iteration, YouTube URLs, and EPub. Developers reach for markdown-converter when ingesting legacy Office specs, scraping HTML into repo docs, OCR-ing screenshots for RAG corpora, or batch-converting ZIP bundles before agent indexing. Because markitdown runs ephemerally through uvx, the skill suits CI snippets and one-off agent tasks alike. It complements hand-authored Markdown by normalizing external sources into a single parseable format coding agents can search, diff, and embed.
- markdown-converter
Markdown Converter by the numbers
- 259 all-time installs (skills.sh)
- +6 installs in the week ending Jul 11, 2026 (Skillselion tracking)
- Data as of Aug 3, 2026 (Skillselion catalog sync)
npx skills add https://github.com/steipete/agent-scripts --skill markdown-converterAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 259 |
|---|---|
| repo stars | ★ 6.5k |
| Last updated | August 3, 2026 |
| Repository | steipete/agent-scripts ↗ |
How do you convert PDF and Office files to Markdown?
Use markdown-converter for development tasks
Who is it for?
Developers ingesting legacy documents, specs, or media into Markdown-based docs pipelines, RAG corpora, or agent-readable knowledge bases.
Skip if: Hand-authoring original documentation or pixel-perfect layout preservation where Markdown structure is insufficient.
When should I use this skill?
User needs PDF, Word, PowerPoint, Excel, HTML, image OCR, audio transcription, ZIP, YouTube, or EPub converted to Markdown.
What you get
Markdown .md files extracted from PDFs, Office documents, HTML pages, spreadsheets, images, audio, ZIP archives, or YouTube URLs.
- markdown files
- stdout markdown output
By the numbers
- Supports 14 input format categories including PDF, Office, HTML, data, media, ZIP, YouTube, and EPub
Files
Markdown Converter
Convert files to Markdown using uvx markitdown — no installation required.
Basic Usage
# Convert to stdout
uvx markitdown input.pdf
# Save to file
uvx markitdown input.pdf -o output.md
uvx markitdown input.docx > output.md
# From stdin
cat input.pdf | uvx markitdownSupported Formats
- Documents: PDF, Word (.docx), PowerPoint (.pptx), Excel (.xlsx, .xls)
- Web/Data: HTML, CSV, JSON, XML
- Media: Images (EXIF + OCR), Audio (EXIF + transcription)
- Other: ZIP (iterates contents), YouTube URLs, EPub
Options
-o OUTPUT # Output file
-x EXTENSION # Hint file extension (for stdin)
-m MIME_TYPE # Hint MIME type
-c CHARSET # Hint charset (e.g., UTF-8)
-d # Use Azure Document Intelligence
-e ENDPOINT # Document Intelligence endpoint
--use-plugins # Enable 3rd-party plugins
--list-plugins # Show installed pluginsExamples
# Convert Word document
uvx markitdown report.docx -o report.md
# Convert Excel spreadsheet
uvx markitdown data.xlsx > data.md
# Convert PowerPoint presentation
uvx markitdown slides.pptx -o slides.md
# Convert with file type hint (for stdin)
cat document | uvx markitdown -x .pdf > output.md
# Use Azure Document Intelligence for better PDF extraction
uvx markitdown scan.pdf -d -e "https://your-resource.cognitiveservices.azure.com/"Notes
- Output preserves document structure: headings, tables, lists, links
- First run caches dependencies; subsequent runs are faster
- For complex PDFs with poor extraction, use
-dwith Azure Document Intelligence
Related skills
Lark Openapi ExplorerInstantly explore, test, and generate calls against the full Lark (Feishu) OpenAPI surface without leaving their agent workflow.493k
Lark EventConsume real-time events from Lark/Feishu as structured NDJSON streams inside AI agent workflows.387k16kLark Openapi ExplorerWhen an existing Lark/Feishu skill or CLI command cannot fulfill a specific requirement and they need to discover and invoke the exact native OpenAPI endpoint.386k16k
Just ScrapeQuickly search, crawl, extract structured JSON, or monitor web pages without writing custom scraping code.245k41Lark AppsQuery the current visibility and permission scope of a Lark (Feishu) app without writing HTTP client code.235k16k
Design An InterfaceGenerate multiple radically different interface or API designs in parallel before committing to one.188k198kHow it compares
Pick markdown-converter for quick uvx-based file-to-Markdown conversion; use pandoc when you need fine-grained format templating.
FAQ
How does markdown-converter run without installing markitdown?
markdown-converter invokes uvx markitdown, which downloads and runs markitdown ephemerally. Example: uvx markitdown input.pdf -o output.md or piping stdin through uvx markitdown for stdout Markdown.
What file formats does markdown-converter support?
markdown-converter supports PDF, Word (.docx), PowerPoint (.pptx), Excel (.xlsx, .xls), HTML, CSV, JSON, XML, images with OCR, audio with transcription, ZIP archives, YouTube URLs, and EPub via markitdown.