my-own-pi-stuff

Allows to interact with web pages by performing actions such as clicking buttons, filling out forms, and navigating links. It works by remote controlling Google Chrome or Chromium browsers using the Chrome DevTools Protocol (CDP). When Claude needs to browse the web, it can use this skill to do so.

Fetch up-to-date, version-specific documentation for any library, framework, or tool from Context7 (context7.com) into context. Use whenever accurate API references, installation steps, or usage examples are needed instead of relying on training-data knowledge that may be outdated — e.g. "how do I bootstrap Laravel 13", "current options for X", "the correct signature for Y in version Z".

Web search using DuckDuckGo (primary) and Brave Search (fallback) via the web-browser skill. Use for searching documentation, facts, or any web content when API-based search is not available.

Converts a Markdown file to a professionally styled PDF with cover page, hierarchical headings, tables, links, blockquote callouts, and proper page breaks. Use when the user wants a polished PDF version of a markdown document (research reports, documentation, READMEs, briefs). Output is rendered via headless Chrome from a styled HTML intermediate.

Generates per-job-tailored ATS-friendly resumes and cover letters. Produces single-column HTML, PDF (via Chrome CDP), and DOCX (via python-docx). Reads a user-maintained content database for experiences/skills; extracts keywords from a target job description; outputs are named by {date}-{company}-{role}. Use when the user pastes a job description (or URL) and wants a tailored application package. Do NOT use for the dark-sidebar visual resumes (those are the existing chrisli-resume*.html files).

Renders one or more HTML files to PDF using Chrome's headless --print-to-pdf mode. Reliable and standalone — no pre-running Chrome or CDP connection required, and a throwaway user-data-dir means it never collides with the user's running browser. Use for ATS resumes, cover letters, or any local HTML→PDF conversion. By default it forces A4 with 10mm margins on every page; headers/footers are omitted.

Extract and analyze content from PDF files using vision AI. Supports single or multiple PDFs (batch), full text extraction, structured data extraction with Pydantic schemas, Markdown/HTML conversion, worksheet-clean modes, user-content extraction, and custom prompt extraction. Use when you need to extract, summarize, or analyze content from one or more PDF documents.