Browser validation

Skill NDDev-it-com/rldyour-antigravity-cli/.gemini/skills/browser-validation

Проверь browser/UI поведение только через управляемые Playwright CLI и Chrome DevTools MCP. EN: validate browser behavior through CloakBrowser.From its SKILL.md

Install

npx -y skills add NDDev-it-com/rldyour-antigravity-cli --skill browser-validation

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

3 things to look at

reads credentialsReads from 1 credential source: `RY_PROJECT_SLUG`.
1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
runs commandsInstructs the agent to run 6 commands, including `$HOME/.local/bin/cloakbrowser-cdp-health` and 5 more.

SKILL.md

2.7 KB, 596 tokens by cl100k_base, as published. Nobody here has run it

Purpose

Collect deterministic evidence for browser flows, UI behavior, screenshots, traces, runtime defects, and responsive states.

Native Antigravity Boundary

Mandatory CloakBrowser Boundary

This boundary applies before every browser action:

Run exactly:
```
$HOME/.local/bin/cloakbrowser-cdp-health
```
If the command is missing or exits nonzero, stop immediately and report NOT_PROVEN.
Browser execution is permitted only through:
- the exact $HOME/.local/bin/playwright-cli executable; run-code and --filename are forbidden;
- the approved Chrome DevTools MCP transport, exactly /bin/sh -c 'exec "$HOME/.local/bin/chrome-devtools-mcp" --headless --isolated --no-usage-statistics --no-performance-crux'.
Never execute the Webwright Python runtime, stock/raw/in-app Browser, browser_agent, node_repl, computer-use, Playwright MCP, raw Playwright, bunx, npx, direct package invocations, alternate CDP endpoints, alternate browser executables, alternate browser configs, or any fallback. No fallback is allowed.

webwright-task is compatibility intent routed to browser:validate; it never authorizes Webwright runtime execution.

When To Use

Use for browser flows, UI regressions, screenshots, traces, console/network diagnosis, responsive checks, and visual evidence.

Inputs

URL, preconditions, expected behavior, viewport matrix, and task objective.

Procedure

Use the managed Playwright CLI for flows, screenshots, snapshots, traces, responsive matrices, visual evidence, and long-horizon stepwise workflows. Use the managed Chrome DevTools MCP transport for console, network, runtime, DOM/layout, performance, Lighthouse, and memory diagnosis.

Run health again immediately before every browser action:

$HOME/.local/bin/cloakbrowser-cdp-health
$HOME/.local/bin/playwright-cli -s="${RY_PROJECT_SLUG:-rldyour}" open "$URL"
$HOME/.local/bin/cloakbrowser-cdp-health
$HOME/.local/bin/playwright-cli -s="${RY_PROJECT_SLUG:-rldyour}" snapshot
$HOME/.local/bin/cloakbrowser-cdp-health
$HOME/.local/bin/playwright-cli -s="${RY_PROJECT_SLUG:-rldyour}" screenshot

Evidence Required

Report provider, URL/state, viewport matrix, exact artifact paths, findings, confidence, and NOT_PROVEN gaps.

Forbidden Actions

Do not bypass, weaken, or fall back from the mandatory boundary.

Acceptance Checks

Run python3 scripts/validate_gemini_browser_routing.py --strict.

Failure Reporting

Separate proven defects from NOT_PROVEN provider, health, or auth gaps.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.