by sololabstr
Your AI can't see the screen. uisight gives it eyes: live mobile+desktop sessions, a measurement engine (contrast, touch targets, theme drift) reporting findings as text, and a shared panel for human+AI. MCP server included.
# Add to your Claude Code skills
git clone https://github.com/sololabstr/uisightuisight is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by sololabstr. Your AI can't see the screen. uisight gives it eyes: live mobile+desktop sessions, a measurement engine (contrast, touch targets, theme drift) reporting findings as text, and a shared panel for human+AI. MCP server included. It has 67 GitHub stars.
uisight's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.
Clone the repository with "git clone https://github.com/sololabstr/uisight" and add it to your Claude Code skills directory (see the Installation section above).
uisight is primarily written in JavaScript. It is open-source under sololabstr on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh uisight against similar tools.
No comments yet. Be the first to share your thoughts!
Unlocks once the catalog security scan passes (runs nightly).
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
The deep catalog scan for this skill is still queued. Run an instant dependency check now instead.
Your AI can't see the screen. You can't describe the bug. uisight fixes both.
uisight gives your AI coding agent (Claude Code, Cursor, Antigravity — anything that speaks MCP) real eyes on your web app: live mobile + desktop sessions running side by side, a measurement engine that reports numbers instead of vibes, and a shared panel where you and the AI look at the exact same screen.
Built by a solo founder who got tired of taking phone screenshots, pasting them into chat, and typing "the button looks broken, can you see it?"
The live panel: desktop + mobile sessions of the same site, URL-synced. Inspect runs on every screen; findings come back per device. Your AI sees this exact view through MCP.
| Multi-viewport browsers (Polypane etc.) | Browser-automation MCPs (Playwright MCP etc.) | uisight | |
|---|---|---|---|
| Human + AI share one live session | — | — | ✅ |
Measurement engine (reports 1.14:1, not "looks low") |
for humans | — | ✅ as text, for AI |
| Device × theme matrix (mobile/desktop, light/dark) | ✅ | — | ✅ |
| Human pins a bug → AI reads note + screenshot | — | — | ✅ |
The measurement engine is the heart: instead of your AI burning tokens squinting at screenshots, inspect returns findings like
[mobile · Pixel 7 · light] https://yourapp.com/
INVISIBLE TEXT 1.04:1 — span.bg-gradient-to-r "your headline" (text rgba(255,255,255,.5) / bg rgb(247,247,248))
BUTTON a.text-white "Get Started" → text/background contrast 3.35:1
touch target below 44px 180x23 — "read the guide"
Text findings are cheap, precise, and directly actionable — your AI fixes the exact selector instead of guessing.
# one-shot audit: PNGs + gallery + report for iPhone/Pixel/desktop, light+dark
npx uisight https://yourapp.com --theme both
# live panel: mobile + desktop side by side, you browse, AI watches (and vice versa)
npx uisight-panel http://localhost:3000
The one-shot audit produces a device × theme gallery with findings per card:

# Claude Code
claude mcp add --scope user uisight -- npx -y uisight-mcp
For Cursor / Antigravity / other MCP hosts, add to your MCP config:
{ "mcpServers": { "uisight": { "command": "npx", "args": ["-y", "uisight-mcp"] } } }
Then just tell your agent: "look at my app with uisight". The panel server starts automatically when needed.
| Tool | What it does |
|---|---|
see_screen |
Returns the current screen as an image — the exact frame the human sees in the panel |
inspect |
Runs contrast / touch-target / overflow / theme checks; returns measured findings as text |
goto |
Navigates all sessions to a URL (localhost included) |
tap / type_text / scroll |
Drives the page — the human watches it happen live |
set_device |
Switches device profile (iphone-15, iphone-se, pixel, galaxy, ipad, desktop, laptop) or light/dark theme |
status |
Open URL, sessions, recent console/network errors — first stop when hunting a bug |
marks |
Reads the notes the human pinned in the panel (📌 note + screenshot at that moment) |
Turkish tool names available with UISIGHT_LANG=tr (ekrani_gor, denetle, ...).
npx uisight-panel <url> opens a browser page at localhost:5055:
marks. No more "let me describe what I'm seeing."Works inside VS Code / Antigravity via Simple Browser: Show → http://localhost:5055.
oklab()/oklch() colors all handledAnd the honest limit: automated checks cannot see design mistakes — a collided header measures fine. That's why see_screen exists and why the report says "eyeball the PNGs."
npx playwright install chromium webkit if you want to pre-warm).MIT © SoloLabs