kreuzberg-dev/plugins
6 skills6 installs156 starsGitHub
Install
npx skills add https://github.com/kreuzberg-dev/pluginsSkills in this repo
1Crawling A SiteGuides use of `kreuzcrawl crawl` to follow links across a domain with depth, page-cap, concurrency, rate-limit, domain-scope, and robots controls. A developer uses it to convert a docs site, blog, or full domain into Markdown for LLM ingestion or indexing.1installs2Extracting TablesCovers Kreuzberg's layout-aware table extraction from PDFs, spreadsheets, and images with selectable table models and Markdown or JSON cell output. A developer uses it to pull financial statements, invoices, or scientific tables into structured data.1installs3Extracting With OcrCovers Kreuzberg OCR for image-based documents, including Tesseract/PaddleOCR/EasyOCR backends, ISO 639-2 language packs, and force-OCR. A developer uses it when a PDF has no text layer or extraction returns empty or garbled text.1installs4Headless FallbackCovers kreuzcrawl's `--browser-mode auto|always|never`, external CDP endpoints, and symptoms of JS-only or WAF-blocked pages. A developer uses it when a static fetch returns nothing useful and the page needs a real browser to render.1installs5Picking A FormatExplains Kreuzberg's two orthogonal format knobs (--format and --content-format) plus token-reduction, with a decision tree by consumer. A developer uses it to choose text, markdown, djot, html, or JSON output for extracted documents.1installs6Scraping Html To MarkdownCovers `kreuzcrawl scrape <url>` for rendering one page to Markdown with a full JSON payload of metadata, links, images, and JSON-LD. A developer uses it to convert a single article or page into LLM context or structured data.1installs