一键导入
xai-x-search
Use when the user asks to search X, Twitter, posts, handles, tweets, or real-time social signal through Grok-connected xAI server-side x_search.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Use when the user asks to search X, Twitter, posts, handles, tweets, or real-time social signal through Grok-connected xAI server-side x_search.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | xai_x_search |
| description | Use when the user asks to search X, Twitter, posts, handles, tweets, or real-time social signal through Grok-connected xAI server-side x_search. |
Use this skill for X/Twitter search through the Grok-connected xAI Responses server-side x_search tool.
search_tool to discover the available tool schema first:{
"query": "xai x search"
}
{
"prompt": "Summarize recent posts from @xai about Grok releases.",
"allowed_x_handles": ["xai"]
}
prompt: required X search request.allowed_x_handles: optional handles to include.excluded_x_handles: optional handles to exclude.Do not pass both allowed_x_handles and excluded_x_handles in the same call.
Treat X posts as leads or primary-source statements only when the account identity matters. Corroborate factual claims with independent web/docs/repo evidence before presenting them as settled facts.
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.
Execute a Prometheus work plan in GrokBuild with `/goal` state, Boulder state, evidence ledger updates, worktree discipline, parallel subagents, and explicit continuation. Use after planning when the user says start work, execute plan, continue plan, resume plan, or asks to run a .omo/plans plan.
Goal-like loop that uses ultrawork mode to decompose work into systematic, evidence-bound steps.
MUST USE for planning before coding: 5+ steps, ambiguous scope, multiple modules, architecture decisions, a vague 'just make it good / figure out what to build' brief, or any request to plan, interview, or break work down. Explore-first planning consultant (Prometheus) that grounds in the codebase, asks only the forks exploration cannot resolve - or researches them to best practice when the intent is fuzzy - waits for explicit approval, then writes ONE decision-complete work plan a worker executes with zero further interview. Triggers: ulw-plan, plan this, make a plan, plan before coding, interview me, break this down, start planning, plan mode, just make it good, figure out what to build.
Execute a Prometheus work plan in GrokBuild with `/goal` state, Boulder state, evidence ledger updates, worktree discipline, parallel subagents, and explicit continuation. Use after planning when the user says start work, execute plan, continue plan, resume plan, or asks to run a .omo/plans plan.
Goal-like loop that uses ultrawork mode to decompose work into systematic, evidence-bound steps.
Persistent code-mode kernels (JS/Python) for incremental computation — omp/senpi eval analog on GrokBuild via lfg MCP. Use when multi-step code execution, data exploration, or stateful REPL beats one-shot bash.