agentleFS
RidhuanDEVRidhuanDEV/claude-skills/shadow-browser/SKILL.md

shadow-browser

Skill1 starsChanged yesterdayMITView on GitHub

Live Web Browser E2E Verification. Use when running real Playwright browser tests, inspecting 375px mobile viewport overflow, checking browser console/network errors, or clicking through live web UI flows. Do NOT use for native mobile store gates (/shadow-mobile).

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this skill whenever the Monarch invokes /shadow-browser or wants live browser verification of a running Frontend web app.

    line 8
  2. Very specific:

    Verify zero horizontal overflow (document.documentElement.scrollWidth <= window.innerWidth) at mobile (375px), tablet (768px), and desktop …

    line 15

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/shadow-browser — Automated Browser E2E & Responsive UI Verification (Shadow Army)

Use this skill whenever the Monarch invokes /shadow-browser or wants live browser verification of a running Frontend web app. Connects to the official playwright MCP server (@playwright/mcp) and chrome-devtools-plugin.

Verification Checklist

  1. Desktop & Mobile Viewport Check (375x812 & 1440x900):
    • Navigate to the running local URL.
    • Verify zero horizontal overflow (document.documentElement.scrollWidth <= window.innerWidth) at mobile (375px), tablet (768px), and desktop (1440px) widths in compliance with antislop-layoutmobile.
  2. Console & Network Error Gate:
    • Inspect browser console logs and network requests; report any unhandled JS exceptions, React hydration errors, CORS failures, or 4xx/5xx API responses.
  3. Interactive Control Verification:
    • Click interactive buttons, modals, tabs, and forms to verify real behavior (antislop R-26).

Execution Approval & Intent Boundary (L1 vs L2)

  • Targeted Playwright/browser checks for explicitly modified UI routes on local/sandbox are L1_SAFE_VERIFICATION. Unrequested broad E2E suite runs (playwright test full repo suite during unit-test or minor edits) are L2: SCOPE_EXPANSION and require explicit Monarch approval (shadow-monarch/scripts/execution_approval_gate.py).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.