ClawHub

TRAE指挥官

v1.0.0

Orchestrates TRAE IDE for automated software development with multi-agent collaboration. Invoke when user wants to develop software using TRAE or needs autom...

⭐ 1· 185·0 current·0 all-time
byWang Weicheng@vichard998
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description match the implementation: the package provides helpers to create project files, monitor progress via signal files, launch the TRAE executable, and send prompts via GUI automation. No unrelated credentials, binaries, or external services are requested.
ℹ
Instruction Scope
Runtime instructions and code operate on user-provided project directories and .trae-docs files (creating requirements.md, prompt files, progress.md, signal files). They also instruct TRAE to run autonomously (SOLO mode, no user confirmation). The skill uses pyautogui/pyperclip to paste/send prompts (i.e., it simulates keystrokes and clipboard actions). This is coherent with its purpose but means it will interact with the active desktop and can write files anywhere the user supplies; users should expect autonomous actions and review generated prompts before use.
✓
Install Mechanism
Instruction-only skill with bundled Python source files; there is no install/download step, no external URL fetches, and only optional Python dependencies (pyautogui, pyperclip) that are signaled at runtime if missing.
✓
Credentials
No credentials or privileged environment variables are requested. The code reads the USERNAME/USER env var only to help auto-detect common TRAE install paths — this is proportionate to the purpose.
✓
Persistence & Privilege
The skill does not request always:true and does not modify other skills. It persists a config.json next to the code (expected) and writes files to user-specified project directories. It can launch local executables and simulate keyboard input, which are normal for a desktop automation tool.
Assessment
This skill appears to do what it says: automate a locally-installed TRAE IDE by creating project files, monitoring .trae-docs, launching TRAE, and using GUI automation to paste/send prompts. Before installing/using: 1) Review and approve any prompts that will be sent to TRAE (the default prompts ask TRAE to work autonomously). 2) Run it on a non-production/sandbox project first — it will write files wherever you point project_dir. 3) Be aware that pyautogui simulates keystrokes and uses the clipboard; avoid running while other sensitive work is open. 4) Confirm the TRAE executable you provide is trusted. If you want stricter controls, require manual confirmation before the skill sends prompts or restrict the project directory to a sandbox.

Like a lobster shell, security has layers — review code before you run it.

latestvk9776600kbd255hdvd1g9mwk1s82sqnh

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments