Loading...
Loading...
Found 1,443 Skills
Convert Markdown documents to professionally typeset PDF files with reportlab. Handles CJK/Latin mixed text, fenced code blocks, tables, blockquotes, cover pages, clickable TOC, PDF bookmarks, watermarks, and page numbers. Supports multiple color themes (Warm Academic, Nord, GitHub Light, Solarized, etc.) and is battle-tested for Chinese technical reports. Use this skill whenever the user wants to turn a .md file into a styled PDF, generate a report PDF from markdown, or create a print-ready document from markdown content — especially if CJK characters, code blocks, or tables are involved. Also trigger when the user mentions "markdown to PDF", "md2pdf", "any2pdf", "md转pdf", "报告生成", or asks for a "typeset" or "professionally formatted" PDF from markdown source.
Use this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help. This is especially useful when chaining or combining API calls or the task will be repeated/automated. This Skill creates a reusable script to fetch, enrich or process data.
Fetch any URL and convert to markdown using baoyu-fetch CLI (Chrome CDP with site-specific adapters). Built-in adapters for X/Twitter, YouTube transcripts, Hacker News threads, and generic pages via Defuddle. Handles login/CAPTCHA via interaction wait modes. Use when user wants to save a webpage as markdown.
Search the web and scrape pages using the local tool stack: SearXNG (meta-search), Lightpanda (fast headless fetch), and Agent-Browser (full browser automation). This is your DEFAULT web skill — use it whenever you need to look something up, research a topic, fetch a webpage, extract content from a URL, check current information, find documentation, do competitive research, or answer any question that benefits from live web data. Triggers on any form of: search for, look up, google, find out, research, what's the latest on, fetch this page, scrape this site, check this URL, pull info from, web search, or any task where current web information would improve your answer. Even if the user doesn't explicitly ask you to search — if answering well requires current info you don't have, use this skill. NOT for interactive browser automation like form filling or clicking (use [[agent-browser]] or [[browser-use]]).
Fast, zero-config AWS SSO login helper that discovers accounts and roles, configures AWS profiles, and auto-configures EKS Kubernetes contexts. Use when authenticating with AWS SSO, switching between AWS accounts or roles, setting up AWS profiles for CLI usage, configuring Kubernetes contexts for EKS clusters, or exporting AWS_PROFILE for tools that support named profiles.
Interactive chezmoi drift check and sync. TRIGGERS - chezmoi sync, sync dotfiles, dotfile drift, chezmoi guard, chezmoi check.
Run bean-check plus custom validation rules on the ledger. Ensures every entry balances, accounts exist, and no common errors are present. Use after any ledger modification to verify integrity. CLEAR step: L (Log)
LOAD THIS SKILL when: browsing OpenCode or Claude Code sessions, reading session history, or searching past conversations. Contains all session-tool commands.
Merge extract-rules output from multiple projects into a unified portable rule set. Promotes .local.md patterns shared across projects to Principles format.
Control tmux sessions, windows, and panes via the tmux CLI. Covers session management, window/pane operations, sending keys, reading output, and pane decoration.
Automate browser interactions, test web pages and work with Playwright tests.
Parse documents into clean markdown or structured JSON via the xparse-cli. Use this skill when the user provides a PDF, image, Office file, HTML, OFD, or other supported document and wants it read, converted, summarized, or prepared for downstream agent use. Handles encrypted PDFs, page ranges, markdown/text output, and detailed structured extraction. Prefer this skill whenever the task starts from a local file or document URL and the first step is to turn it into agent-friendly content rather than manually inspect the raw file.