Menü
使用 Cursor CLI（agent）进行交互式与非交互式编码协作；包含模式切换、会话恢复、云代理、沙箱和模型参数说明，以及本机兼容性检查要点。
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
| name | cursor-cli |
| description | 使用 Cursor CLI（agent）进行交互式与非交互式编码协作；包含模式切换、会话恢复、云代理、沙箱和模型参数说明，以及本机兼容性检查要点。 |
基于官方文档（已按你提供的 overview 页面重新校对）：https://cursor.com/cn/docs/cli/overview
# Windows PowerShell
irm 'https://cursor.com/install?win32=true' | iex
agent
agent "重构认证模块以使用 JWT 令牌"
--plan 或 --mode=plan--mode=askagent -p "find and fix performance issues" --model "gpt-5.2"
agent -p "review these changes for security issues" --output-format text
agent -c "refactor the auth module and add comprehensive tests"
会话中也可用 & 前缀把任务交给云端。
agent ls
agent resume
agent --continue
agent --resume="chat-id-here"
agent --sandbox enabled
agent --sandbox disabled
在本机（Cursor 2.5.26）实测：
cursor --version 可用cursor --help 可用cursor agent --model gpt-5.4 "hello" 会提示：model 不是已知选项agent --help 当前不可用（命令未找到）当前环境更像是“编辑器 CLI”可用，但文档里的独立 agent CLI 工作流尚未就绪（或未在 PATH 中）。因此：
cursor ... --model gpt-5.4 来指定模型--model，需先确保 agent 命令本身可用Get-Command cursor -ErrorAction SilentlyContinue
Get-Command agent -ErrorAction SilentlyContinue
cursor --version
cursor --help
agent --help
agent 不存在，按文档重新安装 CLI，并重开终端irm 'https://cursor.com/install?win32=true' | iex
agent 可用后）agent -p "hello" --model "gpt-5.4"
agent ... --model ...（不是 cursor --model）agent 不在 PATH，先修安装/环境变量，再谈模型参数agent --help + agent -p "ping"Analyze Android accessibility trace logs and convert them into actionable permission-flow insights, click-step reconstruction, and builder-ready automation rules. Use when a user pastes trace content containing AccessibilityEvent logs, windows snapshots, node trees, permission dialogs, ROM-specific permission flows (Xiaomi/HyperOS, HONOR/MagicOS, ZTE/AOSP, etc.), or asks to identify what was clicked, reconstruct authorization steps, summarize a permission flow, or turn a trace into builder/automation logic.
Use the Agent Browser CLI (`agent-browser`) for web automation when the user explicitly asks for "agent-browser/agent-broswer" or wants browser actions executed through that CLI instead of OpenClaw browser tool. Includes install checks, session/profile usage, and stable snapshot-ref workflow.
Configure OpenClaw multi-agent communication with sessions_send routing, allowlists, sender tags, and async ack rules. Use when setting up or fixing agent-to-agent messaging, cross-session relays, or ambiguous sender identity.
Configure OpenClaw multi-agent communication with sessions_send routing, allowlists, sender tags, and async ack rules. Use when setting up or fixing agent-to-agent messaging, cross-session relays, or ambiguous sender identity.
Execute Android accessibility automation from natural language goals (open app, navigate UI, search, input text, and submit) using semantic UI understanding and stepwise planning with safety checks. Use when users ask to control Android apps by intent rather than fixed coordinates, especially for flows like entering search pages first and then typing.
Return a reverse-chronological shortlist of recent conversation records (messages), not sessions. Use when the user asks for 最近N条交流记录/聊天记录, including records across historical sessions, then drill into any selected item.