agentleFS
OneDro1dOneDro1d/dark-factory/skills/frontend-auditor/SKILL.md

frontend-auditor

Skill4 starsChanged 2 months agoApache-2.0View on GitHub

Audit frontend code for security, UX regressions, performance, and accessibility issues. Use when reviewing React, Next.js, Vue, Svelte, or any frontend code changes. Triggers on "audit frontend", "review UI", "check accessibility", "a11y audit", "frontend security", "UX review", "performance audit", "review components", "audit React".

  • Reads credentials

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:

    Create a map of the touched areas:

    line 62

≈ “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

Frontend Auditor

Comprehensive auditor for frontend code focusing on security, correctness, UX regressions, performance, accessibility, and maintainability. All findings are grounded in actual code, components, routes, and state management patterns.

When to Use

  • Reviewing frontend code changes before merge
  • Auditing React/Next/Vue/Svelte components
  • Checking accessibility compliance
  • Performance auditing UI code
  • Security review of client-side code
  • UX regression testing after changes

Audit Workflow

On EVERY invocation, execute these steps in order:

Step 1: Detect Stack & Layout

Identify the frontend technology stack:

- Framework: React/Next.js/Vue/Svelte/Angular/etc.
- Router: React Router/Next.js App Router/Vue Router/etc.
- State management: Redux/Zustand/Jotai/Pinia/Context/etc.
- Styling: Tailwind/CSS Modules/Styled Components/Emotion/etc.
- Build tool: Vite/Webpack/Turbopack/etc.
- API layer: fetch/axios/React Query/SWR/tRPC/etc.

Identify key locations:

  • App entrypoints (main.tsx, App.tsx, _app.tsx)
  • Pages/routes directory structure
  • Shared components library
  • API client layer and hooks

Step 2: Scan Recent Changes

Review what has changed recently:

# Check working directory changes
git status
git diff --stat

# Review recent commits affecting frontend
git log --oneline -20 --all -- "src/" "app/" "pages/" "components/" "lib/"

Summarize:

  • What UI/behavior changes were introduced?
  • What components/routes were modified?
  • What possible regressions could occur?

Step 3: Build UI Map

Create a map of the touched areas:

ComponentDetails
Routes/ScreensPages affected, navigation flows
ComponentsUI components modified
Data FetchingAPI calls, queries, mutations
FormsForm handling, validation
StateLocal/global state changes

Step 4: Execute Audit Checklist

Audit touched components plus critical paths (auth flows, payments, user data display).

See CHECKLIST.md for the complete audit checklist covering:

  • Security (XSS, token storage, secrets leakage)
  • Correctness & UX (loading states, validation, edge cases)
  • Performance (bundle size, re-renders, network)
  • Accessibility (keyboard nav, ARIA, contrast)
  • Maintainability (types, tests, component design)

Output Format

Structure your audit report as follows:

A) Scope Scanned

Framework: [detected stack]
Routes reviewed: [list routes/pages]
Components analyzed: [count]
Commits analyzed: [range]

B) UI Map

Routes: [list affected routes]
Components: [key components modified]
Data flows: [API integrations touched]
State: [state management affected]

C) Findings by Category

Use severity levels:

SeverityIconMeaning
CRITICAL:red_circle:XSS, auth bypass, data exposure
HIGH:orange_circle:Security issue, major UX regression
MEDIUM:yellow_circle:Performance issue, a11y problem
LOW:white_circle:Minor issue, code smell
INFO:blue_circle:Observation, suggestion

For each finding:

### [SEVERITY] Title

**Location:** `components/Form.tsx:45`
**Category:** Security > XSS

**Issue:** [Describe the problem]

**Evidence:**
[Code snippet]

**Risk:** [What could go wrong]

**Fix:**
[Code showing the fix]

D) Summary Table

CategoryCriticalHighMediumLow
Security0101
UX/Correctness0021
Performance0012
Accessibility0110
Maintainability0002

E) Suggested Patches

Step-by-step fixes for critical and high-severity issues:

1. [First fix with code]
2. [Second fix with code]
3. ...

Quick Commands

# Check for vulnerable dependencies
npm audit
pnpm audit

# Find potential XSS vectors (React)
grep -rn "dangerouslySetInnerHTML\|innerHTML" --include="*.tsx" --include="*.jsx"

# Find hardcoded secrets
grep -rn "API_KEY\|SECRET\|password" --include="*.ts" --include="*.tsx"

# Check bundle size
npx vite-bundle-visualizer
npx @next/bundle-analyzer

# Lighthouse audit
npx lighthouse http://localhost:3000 --view

Resources

  • CHECKLIST.md - Complete audit checklist
  • PATTERNS.md - Framework-specific vulnerability patterns

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.