Browser & automation
No visual example yet
Explore the skill
Midscene
web-infra-dev
AI-powered, vision-driven UI automation for every platform.
14.2KGitHub
OPENAGENTSKILL / DIRECTORY
AI Agent Skills
Find a skill for your next task. Explore tools for Codex, Claude Code, Cursor and more.
Find a skill for your next task. Preview examples where available.
Results · “vision-language”
1–7 / 7
Results: 7
Browser & automation
No visual example yet
Explore the skill
RPA
A9T9
Ui.Vision Open-Source RPA Software with Computer Vision, OCR, Anthropic Computer Use/LLM. Selenium IDE import/export.
2KGitHub
Browser & automation
No visual example yet
Explore the skill
Browser Use
browser-use
Give your AI agent a web browser
100.5KGitHub
Browser & automation
No visual example yet
Explore the skill
Page Agent
alibaba
Control web interfaces with natural language agents
28.6KGitHub
Browser & automation
No visual example yet
Explore the skill
Stagehand
browserbase
Build browser agents with natural language actions
23.5KGitHub
Browser & automation
No visual example yet
Explore the skill
Shortest
antiwork
QA via natural language AI tests
5.7KGitHub
Education
No visual example yet
Explore the skill
Learn Gdscript
GDQuest
Learn Godot's GDScript programming language from zero, right in your browser, for free.
2.7KGitHub
Guides & comparisons
- Frontend design skills ↗
- Remotion skills ↗
- Excel and XLSX skills ↗
- PDF and Word skills ↗
- AI agent skills library ↗
- Open source AI agent skills ↗
- Best Codex skills ↗
- Best AI agent skills for stock analysis ↗
- Best Codex skills for web scraping ↗
- Best Claude Code skills for PDF parsing ↗
- Best AI agent skills for football analytics ↗
- OpenAgentSkill vs skills.sh ↗
- OpenAgentSkill vs agentskills.io ↗