From dc7f3584bd7f30ce2d3b1948a14420447eb1ffce Mon Sep 17 00:00:00 2001 From: Peter Steinberger Date: Tue, 29 Sep 2026 17:49:28 -0700 Subject: [PATCH] fix(skills): install Markdown conversion extras Co-authored-by: pereponkin --- CHANGELOG.md | 2 ++ skills/markdown-converter/SKILL.md | 21 +++++++++++---------- 2 files changed, 13 insertions(+), 10 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 879affc4..2daeddf3 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -6,6 +6,8 @@ summary: Timeline of guardrail helper changes mirrored from Sweetistics and rela ## Unreleased +- Fix the Markdown converter commands to install PDF and Office extras, and document charset overrides for text files. Thanks @pereponkin! (#43) + - Update Puppeteer Core to 25.12.0 and youtube-transcript-plus to 2.0.3; run skill metadata validation and browser profile regression tests in CI. - Preserve release recovery state and remove temporary signing keys and notes after failures on Bash 5, matching macOS Bash behavior. diff --git a/skills/markdown-converter/SKILL.md b/skills/markdown-converter/SKILL.md index d846d8ba..ecb18b76 100644 --- a/skills/markdown-converter/SKILL.md +++ b/skills/markdown-converter/SKILL.md @@ -5,20 +5,20 @@ description: "Markdown conversion: PDF, Office, HTML, data, OCR, audio, ZIP, You # Markdown Converter -Convert files to Markdown using `uvx markitdown` — no installation required. +Convert files to Markdown using `uvx --from "markitdown[all]" markitdown` — no installation required. ## Basic Usage ```bash # Convert to stdout -uvx markitdown input.pdf +uvx --from "markitdown[all]" markitdown input.pdf # Save to file -uvx markitdown input.pdf -o output.md -uvx markitdown input.docx > output.md +uvx --from "markitdown[all]" markitdown input.pdf -o output.md +uvx --from "markitdown[all]" markitdown input.docx > output.md # From stdin -cat input.pdf | uvx markitdown +cat input.pdf | uvx --from "markitdown[all]" markitdown ``` ## Supported Formats @@ -45,19 +45,19 @@ cat input.pdf | uvx markitdown ```bash # Convert Word document -uvx markitdown report.docx -o report.md +uvx --from "markitdown[all]" markitdown report.docx -o report.md # Convert Excel spreadsheet -uvx markitdown data.xlsx > data.md +uvx --from "markitdown[all]" markitdown data.xlsx > data.md # Convert PowerPoint presentation -uvx markitdown slides.pptx -o slides.md +uvx --from "markitdown[all]" markitdown slides.pptx -o slides.md # Convert with file type hint (for stdin) -cat document | uvx markitdown -x .pdf > output.md +cat document | uvx --from "markitdown[all]" 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/" +uvx --from "markitdown[all]" markitdown scan.pdf -d -e "https://your-resource.cognitiveservices.azure.com/" ``` ## Notes @@ -65,3 +65,4 @@ uvx markitdown scan.pdf -d -e "https://your-resource.cognitiveservices.azure.com - Output preserves document structure: headings, tables, lists, links - First run caches dependencies; subsequent runs are faster - For complex PDFs with poor extraction, use `-d` with Azure Document Intelligence +- If automatic charset detection picks the wrong encoding for a text file, pass `-c UTF-8` (or the known charset)