Vlmkit

Verify frontend changes with @mizchi/vlmkit: compare rendered HTML or screenshots, manage visual baselines, and inspect layout, accessibility or interaction defects. Use after visible UI changes or for a requested visual audit. Choose deterministic checks first, then use model-assisted modes when the task requires them.

423 stars 6 forksFrontend & Design

Install

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

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

From the SKILL.md

# vlmkit

Use Node 24+. The published `@mizchi/vlmkit@0.24.0` CLI was checked on
2026-11-16 with Playwright 1.65.1. Its bin is `vlmkit`.
`@mizchi/vrt@0.5.0` is an older package whose bin is `vrt`; installing it does
not provide the current command described here.

## Install in the project

```sh
pnpm add -D @mizchi/vlmkit
pnpm exec vlmkit --help
```

Resolve the CLI's Playwright peer requirements and install the matching browser
through that same project. A different global `playwright install` can download
a browser build the project does not use. The
[smoke fixture](assets/smoke/package.json) explicitly pins both Playwright packages.
Keep the project's package-manager version and lockfile.

## Select the operation

| Need | Entry point |
| --- | --- |
| Compare before/after HTML or URLs | `vlmkit diff html --help` |
| Summarize an existing diff for an agent | `vlmkit diff agent --help` |
| Keep a screenshot baseline across runs | `vlmkit snapshot --help` |
| Find defects without a baseline | `vlmkit check integrity --help` |
| Inspect layout, responsive behavior or accessibility | `vlmkit check --help`, then the selected gate |
| Explore behavior or inventory the page | `vlmkit inspect --help`, `vlmkit scan --help` |
| Use model-assisted generation or repair | Read that installed command's help and provider requirements |

These are distinct operations; do not assume they share flags or output schemas.
Read the full skill on GitHub

Details

Skill name
vlmkit
Repository
mizchi/skills
Path
vlmkit/SKILL.md
Repo updated
18 November 2026

FAQ

What does the Vlmkit skill do?

Verify frontend changes with @mizchi/vlmkit: compare rendered HTML or screenshots, manage visual baselines, and inspect layout, accessibility or interaction defects. Use after visible UI changes or for a requested visual audit. Choose deterministic checks first, then use model-assisted modes when the task requires them.

How do I install the Vlmkit skill?

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

Is Vlmkit popular?

It lives in mizchi/skills, which has 423 GitHub stars and 6 forks.

Related skills

Actions CI Tuning

423

mizchi/skills

Use when auditing or improving GitHub Actions workflows for a project. Covers cache setup (npm/pnpm/yarn), job parallelism, shard-based test splitting, artifact handling pitfalls, and Playwright-specific patterns. Trigger on: slow CI, cache miss, flaky shard jobs, merge-reports failures, or an explicit 'tune CI' request.

Testing & QA

AI Index

423

mizchi/skills

Method and tooling for measuring how AI-generated a piece of prose reads, in Japanese or English. Two layers — a deterministic lint for removable surface tells (scripts/slopscore.py, no API) and a judgment layer of typed probabilistic questions (Jev noul/score) for the tells that survive editing. Includes measured human/AI baselines, a gap-first calibration procedure, and labeled fixtures. Use when building or calibrating an AI-likeness score, or when a draft needs a defensible number rather than a vibe. For writing guidance use natural-writing-ja / natural-writing-en instead.

AI, LLMs & Agents

Apm Usage

423

mizchi/skills

Reference for APM manifests, installation, targeted updates, deployment paths and lockfiles. Invoke when the user explicitly asks about APM or apm.yml, or an unfamiliar APM command/error needs exact CLI details. Do not automatically invoke for every project that happens to have installed skills.

DevOps & Cloud

Wordpress Router

211

Automattic/agent-skills

Use when the user asks about WordPress codebases (plugins, themes, block themes, Gutenberg blocks, WP core checkouts) and you need to quickly classify the repo and route to the correct workflow/skill (blocks, theme.json, REST API, WP-CLI, performance, security, testing, release packaging).

Frontend & Design37

Storefront Best Practices

237

medusajs/medusa-agent-skills

ALWAYS use this skill when working on ecommerce storefronts, online stores, shopping sites. Use for ANY storefront component including checkout pages, cart, payment flows, product pages, product listings, navigation, homepage, or ANY page/component in a storefront. CRITICAL for adding checkout, implementing cart, integrating Medusa backend, making a store agent-friendly for AI shopping agents, or building any ecommerce functionality. Framework-agnostic (Next.js, SvelteKit, TanStack Start, React, Vue). Provides patterns, decision frameworks, backend integration guidance.

Frontend & Design29

Multica Artifact Frontend

279

it235/multica-best-practices

Frontend artifact sync—push the frontend deliverable set (page/component/state/style) and run-url to Multica frontend-artifact (product-requirement mapping); the preferred mount for @FrontendDev.

Frontend & Design33

Browse the most popular Claude skills, all frontend & design skills, or write your own with the skills generator.