菜单
Drive a native macOS app via the cua-driver CLI (default) or MCP server — snapshot its AX tree, click/type/scroll by element_index, verify via re-snapshot. Use when the user (or an agent persona) asks to operate, drive, automate, or perform a GUI task in a real macOS application on the host.
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 | cua-driver |
| description | Drive a native macOS app via the cua-driver CLI (default) or MCP server — snapshot its AX tree, click/type/scroll by element_index, verify via re-snapshot. Use when the user (or an agent persona) asks to operate, drive, automate, or perform a GUI task in a real macOS application on the host. |
| metadata | {"provided-by":"@islee23520/lfg (Grok Build adapter)","requires":"cua-driver CLI + daemon on the host (Accessibility + Screen Recording permissions)"} |
Bundled by LFG for Grok Build. See the full version under the materialized plugin or the host's cua-driver skill for the complete guide.
Core contract: always snapshot (get_window_state) before and after every action. Prefer element_index over raw pixels. Never foreground the target unless the user explicitly asked for frontmost state.
This skill lets Grok agents drive real desktop apps (creative tools, Finder, browsers in controlled ways, etc.) while the user continues working in their foreground editor.
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.
