Visual Route Sweep

Inventory every safe visual route, capture authenticated light/dark desktop/tablet/mobile screenshots, detect responsive and browser-runtime failures, semantically review every image, and optionally remediate and rerun. Use when the user asks to screenshot or visually audit all endpoints without running the complete battle-test security, CRUD, and architecture cycle.

41 stars 1 forksSecurity

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add wolverin0/claude-skills --skill visual-route-sweep
Manual install
git clone --depth 1 https://github.com/wolverin0/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/skills/visual-route-sweep ~/.claude/skills/visual-route-sweep

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Visual Route Sweep

Run a fail-closed visual matrix without claiming the application is fully battle-tested.

## Invocation

```text
$visual-route-sweep <url>
$visual-route-sweep <url> --fix
$visual-route-sweep --resume
```

`--fix` authorizes owned UI/runtime remediation and exact-build reruns. It does not authorize
deployment unless the user separately requested deployment. Use credentials only through environment
variables or an existing saved browser state.

## Contract

1. Record repository SHA, running image/revision, URL, auth method, roles, themes, and viewports.
2. Inventory runtime routes plus reachable same-origin links. Classify every route as tested,
   nonvisual, destructive, superseded, unresolved-dynamic, or quarantined with a reason.
3. Authenticate before protected routes. A login page, error page, blank page, or fixture is not proof.
4. Capture viewport and full-page screenshots for every safe resolved route at desktop, tablet, and
   mobile widths in light and dark themes.
5. Record HTTP status, final URL, console errors, page errors, failed requests, bad responses,
   screenshot failures, document width, and responsive findings for every matrix cell.
6. Use `../validation/scripts/responsive-audit.js`. On mobile, nested horizontal scrolling is a high
   finding unless a semantically reviewed carousel explicitly has
   `data-validation-horizontal-scroll="allow"`. Tables and forms may not opt out.
Read the full skill on GitHub

Details

Skill name
visual-route-sweep
Path
skills/visual-route-sweep/SKILL.md
Repo updated
17 November 2026

FAQ

What does the Visual Route Sweep skill do?

Inventory every safe visual route, capture authenticated light/dark desktop/tablet/mobile screenshots, detect responsive and browser-runtime failures, semantically review every image, and optionally remediate and rerun. Use when the user asks to screenshot or visually audit all endpoints without running the complete battle-test security, CRUD, and architecture cycle.

How do I install the Visual Route Sweep skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add wolverin0/claude-skills --skill visual-route-sweep. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Visual Route Sweep popular?

It lives in wolverin0/claude-skills, which has 41 GitHub stars and 1 forks.

Related skills

UI UX Pro Max

41

wolverin0/claude-skills

UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, and check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, and mobile app. Elements: button, modal, navbar, sidebar, card, table, form, and chart. Styles: glassmorphism,

Frontend & Design

Audit Blind Spots

41

wolverin0/claude-skills

Walk the B1-B19 AI-to-AI blind-spot catalog systematically. Use during the audit pipeline AFTER hard-stops and Tambon hunt and BEFORE the 13 domain audits. Output: PRESENT / NOT PRESENT for each B-class with evidence. Findings flow into the appropriate domains.

AI, LLMs & Agents

Audit Decisions

41

wolverin0/claude-skills

Standardize remediation decisions, baseline-policy entries, and legal-review banners for accepted, deferred, or policy-blocked audit findings.

Marketing, Sales & Business

Creating Devcontainers

23

willvelida/code-minions

Create and review DevContainer configurations that follow organisational standards. Use when a user asks to set up a dev container, configure a development environment, create a devcontainer.json, add lifecycle hooks, review an existing DevContainer for compliance, or improve container security. Covers base images, features, extensions, lifecycle hooks, and security hardening.

Security

Security Review

41

wolverin0/claude-skills

Review security-sensitive code changes involving auth, user input, secrets, APIs, payments, files, RLS, or third-party integrations.

Security

FFUF Web Fuzzing

43

lifangda/claude-plugins

Integrates ffuf fuzzer for web vulnerability analysis. Expert guidance for penetration testing with authenticated fuzzing capabilities.

Security13

Browse the most popular Claude skills, all security skills, or write your own with the skills generator.