Vision-native browser eyes and hands via the tendo CLI - capture web page state (annotated screenshots, grounded element map, console/network errors) and execute deterministic actions by element id. Use whenever a task needs to see or drive a real web page in a browser: inspecting a rendered UI, filling forms, clicking through a flow, verifying something looks right, or checking canvas/visual state the DOM cannot describe.
Repository statistics
Indexed skills
2
Skill groups
1
GitHub stars
0
Forks
0
Skills
2 totalCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
Add to your README
The badge links readers to this page. It shows the skilld mark and no counts, and it follows the reader's light or dark GitHub theme.
<a href="https://skilld.dev/gh/ian-yeh/tendo">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://skilld.dev/b/ian-yeh/tendo?theme=dark">
<source media="(prefers-color-scheme: light)" srcset="https://skilld.dev/b/ian-yeh/tendo?theme=light">
<img alt="Skill repository on skilld.dev" src="https://skilld.dev/b/ian-yeh/tendo?theme=light">
</picture>
</a>