القائمة
Use when the user asks to generate, draft, answer, rewrite, summarize, or reason with xAI/Grok text generation through the Grok-connected xAI text tool.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
| name | xai_generate_text |
| description | Use when the user asks to generate, draft, answer, rewrite, summarize, or reason with xAI/Grok text generation through the Grok-connected xAI text tool. |
Use this skill for text generation with Grok through the Grok-connected xAI Responses text tool.
search_tool to discover the available tool schema first:{
"query": "xai generate text"
}
{
"prompt": "Write a concise release note for artifact-backed image generation.",
"reasoning_effort": "medium"
}
prompt: required user request.model: optional Grok model, only when the user or task requires a specific one.reasoning_effort: low, medium, or high when supported by the tool schema.Use xai_web_search instead when the user asks for current web information. Use xai_x_search instead when the user asks to search X/Twitter.
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.