技能详情（站内镜像，无评论）
许可证：MIT-0
MIT-0 ·免费使用、修改和重新分发。无需归因。
统计：⭐ 0 · 458 · 2 current installs · 2 all-time installs
⭐ 0
安装量（当前） 2
🛡 VirusTotal ：可疑 · OpenClaw ：良性
Package：88901111hz-lang/nerve-bridge-skill
安全扫描（ClawHub）
- VirusTotal ：可疑
- OpenClaw ：良性
OpenClaw 评估
The skill's requirements, instructions, and included script are internally consistent with its stated goal of controlling Trae via macOS AppleScript and waiting for a completion signal.
目的
The name/description match the actual behavior: it automates Trae via AppleScript, uses the system clipboard, and waits for a feedback file. Required binaries (python3, osascript) and macOS Accessibility permission are expected for this purpose.
说明范围
Instructions and the Python script limit activity to copying payload to the clipboard, activating Trae, simulating keystrokes, and waiting for ~/.openclaw/workspace/trae_feedback.json. This is coherent, but note that the skill relies on Trae executing the injected payload (including arbitrary code you provide). Also, using pbcopy (clipboard) can leak clipboard contents if the payload includes sensitive data.
安装机制
No install spec — instruction-only with a single helper script. Nothing is downloaded or written to install locations beyond the script itself being included in the skill bundle.
证书
No environment variables, credentials, or unrelated config paths are requested. The only filesystem interaction is the feedback file under the user's home directory, which is consistent with the stated feedback mechanism.
持久
The skill does not request always:true, does not modify other skills, and only writes/reads its own feedback file path. It requires macOS Accessibility permissions for UI automation, which is expected for AppleScript-driven automation.
综合结论
This skill is coherent with its purpose, but it automates an editor/IDE to run whatever payload you send. Before installing or using it: (1) only send instructions you trust — the IDE will execute them; (2) avoid including secrets in the payload or clipboard; (3) confirm you are comfortable granting Accessibility permissions to enable the automation; (4) inspect the script (included) and consider running in a restricted environment if you are …
安装（复制给龙虾 AI）
将下方整段复制到龙虾中文库对话中，由龙虾按 SKILL.md 完成安装。
请把本段交给龙虾中文库（龙虾 AI）执行：为本机安装 OpenClaw 技能「Nerve Bridge Skill」。简介：Bi-directional control of Trae via macOS AppleScript with built-in feedback mec…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装：https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/88901111hz-lang/nerve-bridge-skill/SKILL.md
（来源：yingzhi8.cn 技能库）SKILL.md
---
name: nerve_bridge
description: Bi-directional control of Trae via macOS AppleScript with built-in feedback mechanism. Use when needing to execute code/commands in Trae IDE and wait for completion confirmation.
metadata:
{
"openclaw":
{
"emoji": "⚡️",
"requires": { "bins": ["python3", "osascript"] },
"install":
[
{
"id": "system",
"kind": "system",
"label": "macOS System Environment",
"description": "Depends on system Python and AppleScript. No extra installation required."
}
]
}
}
---
# Nerve Bridge (v2)
Direct neural link to Trae with closed-loop feedback via macOS AppleScript.
## Quick Start
Send instruction and wait for confirmation:
```bash
python3 nerve_bridge.py "<instruction>"
```
Example:
```bash
python3 nerve_bridge.py "Create a new Python file and add a simple 'Hello World' function. After creating, add a print statement to test it."
```
## How It Works
1. **Signal Injection**:
- Payload is copied to system clipboard via `pbcopy`
- AppleScript activates Trae and simulates: Space (wake) → Delete → Cmd+V → Enter
2. **Feedback Loop**:
- Instruction must include a Python hook that writes to `~/.openclaw/workspace/trae_feedback.json` when done
- Script waits up to 5 minutes (300 seconds) for the signal file
- Returns JSON feedback when received
## Required Hook Pattern
When crafting instructions, include this pattern at the end:
```python
import json, time
with open("~/.openclaw/workspace/trae_feedback.json", "w") as f:
json.dump({"status": "success", "timestamp": time.time()}, f)
```
## Environment
- **Platform**: macOS only
- **Dependencies**: System Python (`python3`), AppleScript (`osascript`)
- **Permissions**: System Events and Terminal must have "Accessibility" permissions
- **Output File**: `~/.openclaw/workspace/trae_feedback.json` (created by the script)
## Troubleshooting
- **No output from Trae**: Check if Trae window is active and input is focused
- **Timeout**: Trae didn't complete within 5 minutes
- **Permission denied**: macOS may need to grant Terminal System Events permission