agentleFS
Sign inStart free
GabrieleDattileGabrieleDattile/agent-superpowers/skills/frontend/frontend-sentinel/SKILL.md

frontend-sentinel

Skill1 starsChanged 15 days agoMITView on GitHub

Production frontend & UI/UX auditor. Scans React, Vue, Svelte, and HTML templates for accessibility defects, mobile viewport breaks, unhandled loading states, and hydration traps.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run the Frontend Sentinel engine on target files or directories:

    line 29

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

🎨 Skill: Frontend Sentinel (Production UI/UX Auditor)

1. When to Trigger (Routing)

  • TRIGGER WHEN:
    • The user requests a review of frontend code, UI components, or web templates (.tsx, .jsx, .vue, .html, .css).
    • The user asks: "is this UI production ready?", "check accessibility (a11y)", "find mobile responsive issues", or "audit my frontend components".
  • DO NOT TRIGGER WHEN:
    • The task is purely backend database or infrastructure related with zero user interface components.

2. Fundamental Philosophy

"AI assistants often produce components that look visually acceptable in isolation, but fail miserably in production: images without alt text, inputs without labels, broken mobile viewports, and missing keyboard navigation. Frontend Sentinel acts as a clinical UI/UX inspector before deployment."

3. Operational Protocol

Phase 1: Automated Static Inspection

Run the Frontend Sentinel engine on target files or directories:

python skills/frontend/frontend-sentinel/scripts/auditor.py --path <src_or_component_path> --html-report ui-audit.html

The engine systematically checks for 6 critical production flaws:

  1. Accessibility (a11y): Images without alt, icon buttons without aria-label, inputs without <label>.
  2. Mobile Viewport & Overflow: Fixed pixel widths (e.g. width: 800px or w-[900px]) that trigger horizontal scrolling on mobile.
  3. Form & Input Resilience: <input> elements without required types, missing autofocus traps, forms missing onSubmit handlers.
  4. Hydration & SSR Traps: Premature references to window, document, or localStorage during initial component render.
  5. Interactive Element Semantics: Clickable <div> or <span> elements used instead of <button> or <a>.
  6. Error & Loading States: Network fetch calls lacking loading spinners or fallback error boundaries.

Phase 2: Interactive HTML Report

The engine outputs a standalone, graphical ui-audit.html file:

  • Health score (0 - 100%)
  • Ranked findings (Critical, Warning, Optimization)
  • Exact file paths and line numbers with ready-to-copy code fixes.

Phase 3: Remediation & Verification

  1. Review generated findings.
  2. Apply surgical component refactors.
  3. Re-run auditor.py until the health score reaches 100% PASS.

4. Guardrails & Negative Constraints

  • ❌ NEVER approve a component with interactive <div> tags lacking keyboard accessibility (onKeyDown + role="button").
  • ❌ NEVER ignore mobile layout breaks triggered by rigid pixel containers.

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.

Check your setup, free