skills

Search the web from the command line using duckduckgo-cli. Use this skill whenever you need current information, latest news, recent events, fact-checking, research, documentation lookups, or any answer that may have changed since training. Trigger this even when the user doesn't say "search" — phrases like "what's the latest...", "find out...", "look up...", "is X still true?", "who is the current...", "compare prices/options", or any question about recent things should activate it.

Google search from the command line using findweb. Use this skill whenever you need to search the web for information — looking up documentation, researching error messages, finding API references, checking current facts, comparing libraries, or answering questions that require up-to-date information. Trigger this proactively whenever a task would benefit from a web search, even if the user didn't explicitly ask you to search. Also use this when the user asks you to install or set up findweb.

Use when the user wants to scrape, crawl, or extract data from a website or URL. Triggers on: 'scrape this site', 'get data from this URL', 'crawl this page', 'extract data from the web', 'pull data from this link', 'download data from this website', 'I need data from [URL]', or any request involving collecting structured data from a web page. Also triggers when the user provides a URL and asks for its data in CSV, JSON, or other tabular formats. Always load the agent-browser skill alongside this one.

Install, configure, and use the wachi CLI to monitor any URL for new content and get notifications via 90+ services (Slack, Discord, Telegram, email, etc.). Use when the user wants to: (1) subscribe to web pages, blogs, YouTube channels, or RSS feeds for change notifications, (2) set up URL monitoring with wachi sub/check/ls commands, (3) configure notification channels via apprise URLs, (4) schedule periodic checks with cron, (5) troubleshoot wachi errors or configuration, or (6) understand how wachi detects changes (RSS auto-discovery, LLM-based CSS selectors).

Query and analyze data using the DuckDB CLI. Use when the user needs to run SQL queries, analyze CSV/Parquet/JSON files, create or query databases, export data, or perform any ad-hoc data analysis from the command line. Triggers include requests to "query a file", "analyze data", "run SQL", "read a CSV/Parquet/JSON", "create a database", "export to CSV/Parquet", or any data analysis task that benefits from SQL.

Analyze and process large CSV files (1M+ rows) using DuckDB and Polars. Use when the user asks to analyze, query, filter, aggregate, join, or transform CSV data. Triggers on requests like "analyze this CSV", "query CSV file", "filter large dataset", "aggregate CSV data", "join CSV files", "CSV statistics", or any data analysis task involving CSV/TSV/Parquet files.