{"slug":"markitdown","title":"markitdown","summary":"Convert local documents to Markdown using Microsoft's markitdown CLI. Best for: PDF, Word, Excel, PowerPoint, images (OCR), audio. Can fetch URLs but Jina is faster for web. Triggers on: convert to markdown, read PDF, parse document, extract text from, docx, xlsx, pptx, OCR image","platform":"Claude","tags":[],"authorName":"LLM Mart","authorSlug":"llm-mart","score":0,"source":"github","price":null,"verified":false,"createdAt":"2026-09-30T19:36:48.672976Z","repo":{"url":"https://github.com/0xDarkMatter/claude-mods","stars":43,"forks":7,"license":"MIT","updatedAt":"2026-09-30T15:18:48Z"},"bodyHtml":"<hr>\n<h2>name: markitdown\ndescription: \"Convert local documents to Markdown using Microsoft's markitdown CLI. Best for: PDF, Word, Excel, PowerPoint, images (OCR), audio. Can fetch URLs but Jina is faster for web. Triggers on: convert to markdown, read PDF, parse document, extract text from, docx, xlsx, pptx, OCR image, local file.\"\nlicense: MIT\ncompatibility: \"Requires markitdown. Install: pip install markitdown\"\nallowed-tools: \"Bash\"\nmetadata:\nauthor: claude-mods</h2>\n<h1>markitdown - Document to Markdown</h1>\n<p>Convert local documents to clean Markdown. One tool for PDF, Word, Excel, PowerPoint, images, and more.</p>\n<h2>When to Use markitdown</h2>\n<table>\n<thead>\n<tr>\n<th>Use Case</th>\n<th>Recommendation</th>\n</tr>\n</thead>\n<tbody>\n<tr>\n<td><strong>Local files (PDF, Word, Excel)</strong></td>\n<td>✅ <strong>Use markitdown</strong> - unique capability</td>\n</tr>\n<tr>\n<td><strong>Web pages</strong></td>\n<td>❌ Use Jina (<code>r.jina.ai/</code>) - 5x faster</td>\n</tr>\n<tr>\n<td><strong>Blocked/anti-bot sites</strong></td>\n<td>❌ Use Firecrawl</td>\n</tr>\n<tr>\n<td><strong>OCR on images</strong></td>\n<td>✅ <strong>Use markitdown</strong></td>\n</tr>\n<tr>\n<td><strong>Audio transcription</strong></td>\n<td>✅ <strong>Use markitdown</strong></td>\n</tr>\n</tbody>\n</table>\n<h2>Basic Usage</h2>\n<pre><code># Local files (primary use case)\nmarkitdown document.pdf\nmarkitdown report.docx\nmarkitdown data.xlsx\nmarkitdown slides.pptx\nmarkitdown screenshot.png    # OCR\n\n# URLs (works, but Jina is faster)\nmarkitdown https://example.com\n\n# Save output\nmarkitdown document.pdf &gt; document.md\n</code></pre>\n<h2>Supported Formats</h2>\n<table>\n<thead>\n<tr>\n<th>Format</th>\n<th>Extensions</th>\n<th>Notes</th>\n</tr>\n</thead>\n<tbody>\n<tr>\n<td>PDF</td>\n<td><code>.pdf</code></td>\n<td>Text extraction, tables</td>\n</tr>\n<tr>\n<td>Word</td>\n<td><code>.docx</code></td>\n<td>Formatting preserved</td>\n</tr>\n<tr>\n<td>Excel</td>\n<td><code>.xlsx</code></td>\n<td>Tables to markdown</td>\n</tr>\n<tr>\n<td>PowerPoint</td>\n<td><code>.pptx</code></td>\n<td>Slides as sections</td>\n</tr>\n<tr>\n<td>Images</td>\n<td><code>.jpg</code>, <code>.png</code></td>\n<td>OCR text extraction</td>\n</tr>\n<tr>\n<td>HTML</td>\n<td><code>.html</code></td>\n<td>Clean conversion</td>\n</tr>\n<tr>\n<td>Audio</td>\n<td><code>.mp3</code>, <code>.wav</code></td>\n<td>Speech-to-text</td>\n</tr>\n<tr>\n<td>Text</td>\n<td><code>.txt</code>, <code>.csv</code>, <code>.json</code>, <code>.xml</code></td>\n<td>Pass-through/structure</td>\n</tr>\n<tr>\n<td>URLs</td>\n<td><code>https://...</code></td>\n<td>Works but slower than Jina</td>\n</tr>\n</tbody>\n</table>\n<h2>Benchmarked Performance (URLs)</h2>\n<table>\n<thead>\n<tr>\n<th>Tool</th>\n<th>Avg Speed</th>\n<th>Success Rate</th>\n</tr>\n</thead>\n<tbody>\n<tr>\n<td>Jina</td>\n<td><strong>0.5s</strong></td>\n<td>10/10</td>\n</tr>\n<tr>\n<td>markitdown</td>\n<td>2.5s</td>\n<td>9/10</td>\n</tr>\n<tr>\n<td>Firecrawl</td>\n<td>4.5s</td>\n<td>10/10</td>\n</tr>\n</tbody>\n</table>\n<p><strong>Verdict</strong>: For URLs, use Jina. For local files, markitdown is the only option.</p>\n<h2>Examples</h2>\n<pre><code># PDF to markdown (primary use case)\nmarkitdown report.pdf &gt; report.md\n\n# Excel spreadsheet\nmarkitdown financials.xlsx\n\n# Image with text (OCR)\nmarkitdown screenshot.png\n\n# PowerPoint deck\nmarkitdown presentation.pptx &gt; slides.md\n\n# Audio transcription\nmarkitdown meeting.mp3 &gt; transcript.md\n</code></pre>\n<h2>Comparison with Alternatives</h2>\n<table>\n<thead>\n<tr>\n<th>Task</th>\n<th>markitdown</th>\n<th>Alternative</th>\n</tr>\n</thead>\n<tbody>\n<tr>\n<td>PDF text</td>\n<td><code>markitdown file.pdf</code></td>\n<td>PyMuPDF, pdfplumber</td>\n</tr>\n<tr>\n<td>Word docs</td>\n<td><code>markitdown file.docx</code></td>\n<td>python-docx</td>\n</tr>\n<tr>\n<td>Excel</td>\n<td><code>markitdown file.xlsx</code></td>\n<td>pandas, openpyxl</td>\n</tr>\n<tr>\n<td>OCR</td>\n<td><code>markitdown image.png</code></td>\n<td>Tesseract</td>\n</tr>\n<tr>\n<td>Web pages</td>\n<td>Use Jina instead</td>\n<td><code>r.jina.ai/URL</code> (5x faster)</td>\n</tr>\n</tbody>\n</table>\n<p><strong>markitdown's advantage</strong>: One CLI for all local document formats. No code needed.</p>\n","files":[{"path":"assets/.gitkeep","sizeBytes":0,"isText":false},{"path":"references/.gitkeep","sizeBytes":0,"isText":false},{"path":"scripts/.gitkeep","sizeBytes":0,"isText":false},{"path":"SKILL.md","sizeBytes":2876,"isText":true}],"reviewScore":null,"reviewSummary":null,"trust":{"provenance":"trusted-source-unreviewed","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow.","bodySource":null},"bodyLocked":false,"purchaseUrl":null,"sourceUrl":null,"report":{"provenance":"trusted-source-unreviewed","screen":{"ran":true,"outcome":"clean","suspicious":0,"notes":0,"hiddenCharacters":false},"virusScan":{"engine":"clamav","status":"clean","scannedAt":"2026-09-30T19:38:03.3144Z","sha256":"183AA0F008A5D0796F268EB258F22E594D6153D38E790BCD5BE13F35DD097697","sizeBytes":1724},"review":null,"source":{"repositoryUrl":"https://github.com/0xDarkMatter/claude-mods","path":"skills/markitdown","license":"MIT","commit":"3dfaf0ba5753026a99ee13f9d9ed56b9793bb6e8","subtreeSha":"D15E9E1628901E27D960D125B9D089E51B96FABF16C55C328A5A5394D5933096","lastSyncedAt":"2026-09-30T19:37:28.226022Z"},"reviewedAt":"2026-09-30T19:40:17.841247Z","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow."},"install":[{"target":"skills-cli","command":"npx skills add https://github.com/0xDarkMatter/claude-mods/tree/main/skills/markitdown"},{"target":"claude-code","command":"claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install 0xdarkmatter-claude-mods@llmmart"},{"target":"git","command":"git clone https://github.com/0xDarkMatter/claude-mods.git"}]}