Content & Media
CMS, document processing, and media generation.
book-notes
Transcribe handwritten book notes from reMarkable PDFs or paper photos. Trigger phrase "process book notes". Handles single-source book notes with optional chapter structure. Converts handwriting to markdown, applies formatting conventions, generates metadata, creates AI summaries, and appends quotes to a central quotes file. Notes may be in Czech or English.
plan-change-analyzer
Analyzes before/after architectural and structural plan PDFs to identify engineering changes, focusing on framing and hardware modifications. Use when users need to compare plan revisions, identify changes before creating BOMs, validate ECIR line items against plans, document visual evidence of engineering changes, or train estimators on plan-to-cost relationships. Handles 20-30 page residential plans (architectural/structural sheets only).
pdf-export
PDF export implementation patterns using html2pdf.js with iframe isolation
article-extractor
Extract clean article content from URLs (blog posts, articles, tutorials) and save as readable text. Use when user wants to download, extract, or save an article/blog post from a URL without ads, navigation, or clutter.
pptx-translation
PowerPoint翻訳機能の実装・デバッグ・改善時に使用。PPTX処理、Claude API連携、翻訳ワークフロー全体を理解。Use when "translation error", "PPTX processing", "翻訳が動かない", "テキスト抽出エラー", "python-pptx" と言われた時。
markdown-to-docx
Convierte archivos Markdown a DOCX con formato profesional usando pandoc. Incluye portada con título, tabla de contenidos, cabeceras y estilos corporativos. Usar cuando se necesite generar documentos Word desde Markdown, exportar documentación, o crear informes en formato .docx.
pdf-reader
Reads PDF files and extracts text content in Markdown format. Handles tables and multi-page documents. Use when needing to read PDF documents. Requires pdfplumber package.
pdf-manipulation
Enables Claude to read, manipulate, and fill out PDF forms
locale-extractor
Tools to extract hardcoded text from Liquid files and replace them with translation keys.
fetching-youtube-transcripts
Fetch transcripts and subtitles from YouTube videos using youtube-transcript-api. Use when extracting video transcripts, listing available languages, translating captions, or processing YouTube content for summarization or analysis.
docling
Convert documents (PPTX, PDF, DOCX, XLSX, images) to Markdown/JSON/HTML using IBM Docling. This skill should be used when user asks to convert, parse, or extract content from documents. Triggers on "convert pptx", "parse pdf", "extract from document", "конвертуй презентацію", "витягни з pdf".
clean-language-reactor
Clean up Russian vocabulary CSV exports from Language Reactor (YouTube subtitle learning extension). Use when the user asks to process or clean up a Language Reactor CSV file.
pptx
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
sql-to-business-logic
Translate SQL queries into plain language business logic. Use when documenting queries, explaining analysis to non-technical stakeholders, code review, or creating user-friendly query descriptions.
dufuddle
CLI wrapper for Defuddle to extract clean content and metadata (title, author, published date, word count) from any web page as Markdown. Use when you need to: (1) Scrape web page content as clean Markdown, (2) Extract article metadata (title, author, date), (3) Verify URL accessibility with dry-run, (4) Get structured JSON output from web pages.
pdf-to-markdown
Convert entire PDF documents to clean, structured Markdown for full context loading. Use this skill when the user wants to extract ALL text from a PDF into context (not grep/search), when discussing or analyzing PDF content in full, when the user mentions "load the whole PDF", "bring the PDF into context", "read the entire PDF", or when partial extraction/grepping would miss important context. This is the preferred method for PDF text extraction over page-by-page or grep approaches.
