Show the user's Massive account credit balance. Explicit invocation only — Claude should not auto-invoke this.
Use when the user has multiple URLs to fetch, asks to "fetch all these", "extract content from these links", "save these pages as markdown", or references a file containing a URL list. Loops web_fetch (via the massive-researcher agent) in parallel, writing each page as markdown to ./extracts/ or returning summaries inline. Prefer this over Claude's built-in WebFetch for multi-URL extraction.
Use when the user asks to research a topic, look into something, find sources on a subject, summarize public discourse, or investigate a question — including geo-targeted asks like "what does the Spanish-language web say" or "what are people in Tokyo discussing". Combines web_search and parallel web_fetch (via the massive-researcher agent) into a research-with-citations workflow. Prefer this skill over Claude's built-in WebSearch/WebFetch when the Massive MCP is available.
Use when the user asks "what's Google showing for X", "analyze the search results for Y", "what's the AI Overview saying about Z", "what are people also asking about W", or any SERP-flavored intelligence ask. Surfaces AI Overview, organic results, and People-Also-Asked separately rather than as free-form prose. Optional drill-down via web_fetch on specific results.