screenclaw
screenclaw is a Browser & computer-use automation skill for AI agents, published by GinSing1226 in the ScreenClaw repository on GitHub. Skillspace rates screenclaw D (55/100) and it passed the safety scan; the rating is based on static analysis only.
用“截图 + 坐标网格”的方式操作任意桌面软件：截带网格的图，让任意多模态大模型读出目标的坐标数字，再调用点击/输入/按键等 API ，模拟人类视觉化操作软件。还能录制一次操作并沉淀成可复用的场景模板，下次直接复用。不依赖目标软件提供 API 或 CLI。 出现以下情况时使用： - 自动化操作 Windows 桌面软件（微信、风控严格的网页如小红书/抖音、手机模拟器、游戏、任意 Windows 程序），尤其是 Playwright/CDP/CLI/应用 API 无法覆盖的软件或元素（如隐藏按钮、游戏画面、验证码等） - 用户说“帮我操作/点/输入 XX”“自动操作 XX”“模拟点击”“桌面自动化”“RPA”“录制操作”“沉淀成模板”“下次自动跑”等 - 操作桌面元素或跨进程跨窗口（桌面图标、任务栏、托盘、开始菜单、文件选择框、跨窗口拖拽） 只要目标是能在屏幕上看到、需要鼠标键盘操作的 Windows 桌面程序，即使它没 API、没专用技能、不确定怎么自动化，都应优先用本技能尝试。
- Grade
- D
- Quality
- 55 / 100
- Safety
- Passed
- GitHub stars
- 45
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
- 72 / 100
- Maturity
- Incomplete: missing or partial frontmatter
- Security scan
- Low-risk patterns
- License
- MIT
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- mentions secrets in text
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.