Visual Playtest

Visually inspect a local or deployed site/app in a real browser and report concrete layout, responsive, or design regressions. Use when asked to visually check UI changes, reproduce a screenshot issue, compare a page with a reference, or playtest representative visual states. Do not use for code-only review or open-ended design ideation.

201 stars 12 forksDevOps & Cloud

Install

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

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 Playtest

Use the applicable browser-control skill. Match the effort to the request: a
static page review is not a full product certification.

For Chrome, follow [resilient-computer-use](../resilient-computer-use/SKILL.md#chrome-default-bind-to-a-tab): use a dedicated tab bound by stable ID for actions, screenshots, viewport changes, and console inspection. The user and other Codex chats may keep using Chrome concurrently; coordinate shared focus before any native desktop fallback.

## Choose the scope

Identify the few states that can materially change the result: named pages,
viewport ranges, theme, scroll position, navigation state, and persistent or
fixed UI. Reproduce the user's reported combination before exploring adjacent
states.

Load additional guidance only when it is in scope:

- Read [references/app-interactions.md](references/app-interactions.md) for
  functional QA of controls, dialogs, panels, keyboard flows, or app workspaces.
- Read [references/media-workflows.md](references/media-workflows.md) for audio,
  video, image-generation, asset-management, download, or media trust-state QA.
- Read neither reference for an ordinary static or content-site visual review.

Do not load both references automatically.

## Core pass

1. Open the target at one representative desktop width and one narrow mobile
   width. Add tablet or unusual wide states only when the design or report makes
   them material.
Read the full skill on GitHub

Details

Skill name
visual-playtest
Repository
swyxio/skills
Path
visual-playtest/SKILL.md
License
MIT
Repo updated
16 November 2026

FAQ

What does the Visual Playtest skill do?

Visually inspect a local or deployed site/app in a real browser and report concrete layout, responsive, or design regressions. Use when asked to visually check UI changes, reproduce a screenshot issue, compare a page with a reference, or playtest representative visual states. Do not use for code-only review or open-ended design ideation.

How do I install the Visual Playtest skill?

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

Is Visual Playtest popular?

It lives in swyxio/skills, which has 201 GitHub stars and 12 forks.

Related skills

Accelevents API

201

swyxio/skills

Use when reading or updating AI Engineer Europe speaker records through the Accelevents REST API, especially for full-record PUT updates, auth header quirks, and preserving existing speaker fields.

Software Development12

Accelevents Speaker Sync

201

swyxio/skills

Use when website speaker, session, schedule, room, track, or headshot changes must be synchronized back to Accelevents for AI Engineer Europe 2026.

AI, LLMs & Agents12

Agents SDK

201

swyxio/skills

Build or debug stateful applications that specifically use Cloudflare's `agents` package, including Agent classes, routing, callable methods, synchronized state, scheduling, AIChatAgent, durable execution, or Agents SDK client hooks. Do not trigger for generic AI-agent design, the OpenAI Agents SDK, or ordinary Durable Object work that does not use the Cloudflare Agents SDK.

AI, LLMs & Agents12

Workers Best Practices

201

swyxio/skills

Author or review Cloudflare Workers code for Workers-specific runtime, binding, streaming, concurrency, lifecycle, and configuration mistakes. Use when the user explicitly asks for Workers best-practice review or when implementing a new Worker entrypoint or binding boundary. Do not trigger for generic TypeScript review, ordinary application logic, deployment operations, or product selection.

DevOps & Cloud12

Vercel Production Cost Review

201

swyxio/skills

Audit a defined Vercel production cost question using billing and usage evidence, then recommend or verify bounded remediations. Use only when the user explicitly asks for a Vercel cost review, unexpected bill or usage spike investigation, Fast Data Transfer analysis, or post-remediation savings verification. Do not trigger for ordinary Vercel deployment, generic performance work, routine caching changes, or optimizing one route without a cost question.

DevOps & Cloud12

Wrangler

201

swyxio/skills

Resolve, construct, review, or run an exact Cloudflare Wrangler command or `wrangler.jsonc` change. Use when the user names Wrangler, asks for a Cloudflare CLI operation, or needs environment, binding, authentication, secret, migration, deployment, or resource-management syntax. Do not trigger for general Cloudflare architecture or application code that does not require Wrangler.

DevOps & Cloud12

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