← 返回 Skills 市场
waldyrious

Cursor Tui

作者 waldyrious · GitHub ↗ · v1.0.1
cross-platform ✓ 安全检测通过
838
总下载
1
收藏
4
当前安装
2
版本数
在 OpenClaw 中安装
/install cursor-tui
功能描述
Spawn and relay Cursor Agent's CLI (`agent` binary) as an interactive passthrough. Use when the user wants to run Cursor Agent in a directory, ask it questio...
使用说明 (SKILL.md)

Cursor CLI Passthrough

Spawn Cursor's agent in a PTY background session and relay its output and the user's inputs as a silent passthrough.

Spawning

{ "tool": "exec", "command": "agent", "pty": true, "background": true, "workdir": "\x3Cproject-dir>", "yieldMs": 3000 }
  • Always set workdir to the project directory the user wants to work in (not the OpenClaw workspace).
  • If the user doesn't specify a directory, ask before spawning.
  • Note: agent requires workspace trust on first run in a directory — relay the trust prompt and send the user's choice (e.g. a, w, or q) via process send-keys.

Relaying output

After spawning or sending input, poll for output:

{ "tool": "process", "action": "poll", "sessionId": "\x3Cid>", "timeout": 15000 }
  • Strip ANSI escape codes mentally, but relay the content faithfully and verbatim.
  • Do not wrap output in code blocks or quote formatting.
  • Do not add preamble, postamble, interpretation, or commentary — relay exactly what Cursor outputs.
  • If you need to add context or a note, prefix that line with your name in brackets (e.g. [YourName]) so it's clearly distinguished from Cursor's output.
  • Permission prompts: When Cursor shows a "Run this command?" or any approval dialog, relay it verbatim to the user and wait for their response. Never approve or deny on the user's behalf.
  • After relaying the agent's response, append a single prompt line: cursor @ \x3Cworkdir> — use ~ in place of the user's home directory (e.g. ~/repos/myproject not /home/username/repos/myproject).

Sending user input

For single-line prompts:

{ "tool": "process", "action": "submit", "sessionId": "\x3Cid>", "data": "\x3Ctext>" }

For multi-line prompts:

{ "tool": "process", "action": "paste", "sessionId": "\x3Cid>", "text": "\x3Ctext>" }

Then submit with Enter:

{ "tool": "process", "action": "send-keys", "sessionId": "\x3Cid>", "keys": ["Enter"] }

For other special keys (arrow keys, Escape, etc.):

{ "tool": "process", "action": "send-keys", "sessionId": "\x3Cid>", "keys": ["ArrowUp"] }

Use @filename or @directory/ in interactive prompts to add more context.

Ending the session

Send /quit or Ctrl+D (double-press):

{ "tool": "process", "action": "submit", "sessionId": "\x3Cid>", "data": "/quit" }

Notes

  • agent is Cursor's CLI binary. cursor-agent is a backward-compatible alias.
  • The binary must be on PATH. If not found, check TOOLS.md for custom binary paths.
  • One session at a time is typical; use process list to check for orphaned sessions.
安全使用建议
This skill acts as a transparent proxy to a local Cursor 'agent' process — it will spawn the binary in whatever directory you specify and relay Cursor's output and permission prompts verbatim. Before using: ensure the cursor/cursor-agent binaries on your PATH are the authentic versions you trust; avoid running the agent in directories containing secrets you don't want echoed back; do not blindly accept workspace-trust or approval prompts relayed by the tool (the instructions correctly tell the skill to ask you). If you are uncomfortable with an automatic agent being spawned, don't invoke the skill or restrict autonomous invocation in your agent configuration.
功能分析
Type: OpenClaw Skill Name: cursor-tui Version: 1.0.1 The skill is designed to provide a transparent passthrough to the `cursor-agent` CLI. The `SKILL.md` instructions explicitly guide the OpenClaw agent to relay output verbatim, avoid interpretation, and critically, 'Never approve or deny on the user's behalf' for permission prompts. This demonstrates a strong intent to prevent unauthorized actions or prompt injection, aligning with a benign purpose of facilitating user interaction with another tool.
能力评估
Purpose & Capability
Name/description request the ability to spawn and relay Cursor's CLI; the skill only requires the cursor / cursor-agent binaries and no unrelated credentials or installs. The declared requirements match the stated purpose.
Instruction Scope
SKILL.md stays focused on spawning a PTY background session, polling output, and relaying user input. It does instruct the agent to run the Cursor binary in an arbitrary project directory and to relay Cursor output verbatim — this is consistent with a transparent passthrough but means any sensitive output produced by Cursor will be relayed to the user.
Install Mechanism
There is no install spec (instruction-only), so nothing is downloaded or written to disk by the skill itself.
Credentials
No environment variables, credentials, or config paths are requested. The absence of extra secrets is proportional to the skill's purpose.
Persistence & Privilege
always is false and the skill is user-invocable. Autonomous model invocation is allowed by platform default but not an additional privilege requested by the skill.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install cursor-tui
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /cursor-tui 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.1
- Improved output relaying instructions: now require verbatim, unaltered relaying of Cursor output with no added interpretation, wrapping, or commentary. - Specified how to add context: any assistant notes must be prefixed with the assistant's name in brackets. - Clarified handling of Cursor "permission prompts": relay them exactly as shown and await explicit user approval—never make choices on the user's behalf. - Updated prompt line guidance: show relative paths using `~` for home directories when displaying the session prompt (e.g. `~/repos/myproject`).
v1.0.0
Initial public release — adds a transparent relay for Cursor Agent's CLI.
元数据
Slug cursor-tui
版本 1.0.1
许可证
累计安装 4
当前安装数 4
历史版本数 2
常见问题

Cursor Tui 是什么?

Spawn and relay Cursor Agent's CLI (`agent` binary) as an interactive passthrough. Use when the user wants to run Cursor Agent in a directory, ask it questio... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 838 次。

如何安装 Cursor Tui?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install cursor-tui」即可一键安装,无需额外配置。

Cursor Tui 是免费的吗?

是的,Cursor Tui 完全免费(开源免费),可自由下载、安装和使用。

Cursor Tui 支持哪些平台?

Cursor Tui 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Cursor Tui?

由 waldyrious(@waldyrious)开发并维护,当前版本 v1.0.1。

💬 留言讨论