native_window_control
native_window_control is a Browser & computer-use automation skill for AI agents, published by hyqibot in the token-free-openclaw repository on GitHub. Skillspace rates native_window_control C (79/100) and it passed the safety scan; the rating is based on static analysis only.
When the user needs to operate an already-open native desktop app window (not a browser): list windows, get control tree, click buttons/tabs, or type text into controls. Windows only; requires Python and pywinauto (pip install pywinauto). | 操作已打开的原生桌面窗口（非浏览器）：列举窗口、控件树、点击或输入；仅 Windows，需 pywinauto。
- Grade
- C
- Quality
- 79 / 100
- Safety
- Passed
- GitHub stars
- 98
Unproven: rated by static analysis only, not yet compared head-to-head.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 97 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- No issues found
- License
- Apache-2.0
- Adoption
- Adopted by 0 other repositories, in 0 collections
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.