Use when the user asks xAI/Grok to search the web, find current information, answer with citations, or use server-side web_search from a Grok-connected xAI tool.
Scanned 9/8/2026
Install to Claude Code
npx -y skills add islee23520/lfg --skill xai-web-search --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Xai Web Search?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/islee23520-xai-web-search-lfg)More formats (shields.io, HTML) on the badges page.
---
name: xai_web_search
description: Use when the user asks xAI/Grok to search the web, find current information, answer with citations, or use server-side web_search from a Grok-connected xAI tool.
---
# xAI Web Search
Use this skill for web-backed answers through the Grok-connected xAI Responses `web_search` tool.
## Preferred Grok Tool Flow
1. Use `search_tool` to discover the available tool schema first:
```json
{
"query": "xai web search"
}
```
2. Call the returned xAI web-search MCP tool with the schema it reports. A typical payload is:
```json
{
"prompt": "Find the latest xAI model announcement and summarize it with citations."
}
```
## Options
- `prompt`: required search question.
- `model`: optional Grok model, only when supported and needed.
Return a concise answer and include citations from the tool output when available. If the tool is unavailable, say so and use the host's normal web/search tools only if the user still wants a fallback.
## Credential Safety
Use existing Grok/xAI credentials exposed by the host or MCP server. Never print, quote, summarize, or store OAuth tokens, refresh tokens, bearer tokens, or API keys.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling