---
title: "Anthropic Webapp Testing: review, setup & limitations · Undominated.ai"
canonical: https://undominated.ai/skills/anthropics-webapp-testing/
description: "Guides local browser checks with Playwright and includes a wrapper that starts development servers around an automation command."
---

# Anthropic Webapp Testing: review, setup & limitations · Undominated.ai

> Guides local browser checks with Playwright and includes a wrapper that starts development servers around an automation command.

[← Explore all skills](/skills/)

BROWSER TESTING / Anthropic

# Anthropic Webapp Testing

Guides local browser checks with Playwright and includes a wrapper that starts development servers around an automation command.

 [See setup guidance ↓](#setup)[Original source ↗](https://github.com/anthropics/skills/tree/34040c9c568585f6929bedeaad110ad08f079624/skills/webapp-testing)

SOURCE REVIEW

 Reviewed 2026-10-14
 Evidence 8 linked sources
 Publisher Anthropic
 Licence [Apache-2.0 ↗](https://github.com/anthropics/skills/blob/34040c9c568585f6929bedeaad110ad08f079624/skills/webapp-testing/LICENSE.txt)
 Revision 34040c9c5685
 [Read what was—and wasn’t—checked ↓](#review)

“Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.”

 [Anthropic · upstream description ↗](https://github.com/anthropics/skills/blob/34040c9c568585f6929bedeaad110ad08f079624/skills/webapp-testing/SKILL.md) Our analysis follows below.

01 / THE REASONING

## Why this made the selection.

 - Uses rendered-page reconnaissance before choosing selectors for dynamic applications.
- The inspected helper supports multiple server commands and forwards the automation command's exit result while attempting cleanup.

### A good fit for

 - Checking a local frontend against real browser interactions
- Capturing screenshots and browser-console observations during debugging
- Starting a local frontend and backend around a bounded browser script while retaining the script’s exit status
- Manage a frontend and backend while checking rendered browser state.

### Weigh up before choosing

 - The server helper checks only whether a TCP port accepts a connection, not whether the expected application is healthy.
- Server commands run through a shell; cleanup terminates the launched process, and descendant cleanup or noisy long-running servers was not exercised.
- An already occupied port can satisfy the helper’s readiness test; it does not establish HTTP health or prove that the newly launched process owns the port.
- Server commands run through a shell. Cleanup targets the Popen process, not a dedicated process group, so descendant cleanup was not established by source inspection.
- with_server.py checks only TCP readiness, launches shell commands, leaves output pipes unread and terminates the immediate process rather than a process group; noisy servers or child processes need care.
- The definition asks users to execute helpers with --help before inspecting their source; that execution sequence was not performed in this review.

02 / THE REVIEW RECORD

## What we actually inspected.

Source review has boundaries. A clear record is more useful than a “safe” badge.

### Material inspected

 - skills/webapp-testing/SKILL.md
- skills/webapp-testing/scripts/with_server.py
- skills/webapp-testing/examples/element_discovery.py
- skills/webapp-testing/LICENSE.txt

### Our findings

 - The helper validates matching server/port arguments and rejects a missing automation command.
- It starts server commands with shell=True and captures stdout/stderr without a reader, which matters for long or noisy runs.
- The skill encourages DOM inspection after load and includes examples for console logging and element discovery.
- with_server.py polls localhost with socket.create_connection, checks matching server/port counts, and returns the automation command’s exit code.
- Its finally block terminates and then kills timed-out server processes; it does not implement an HTTP health probe or process-group cleanup.
- The helper pairs server commands and ports, propagates the child command exit status and uses a finally block for cleanup; it neither validates HTTP readiness nor installs Playwright.

### Not established by this review

 - The helper and Playwright examples were read but not executed.
- Cross-platform process cleanup, browser installation and application-specific assertions were not tested.
- Not executed: it was not installed or run.

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

## Add a skill to your workflow.

[Upstream setup instructions ↗](https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md)

DOCUMENTED COMMAND

 npx skills add anthropics/skills --skill webapp-testing Copy command ↗

Run in your terminal to choose your AI tools, project or global scope, and installation method. This short command follows the current upstream version; the review covers the revision shown above.

 Optional: install the reviewed revision

Keeps the original source and installer version where recorded, while leaving your AI tools and installation scope for you to choose.

 npx skills add https://github.com/anthropics/skills/tree/34040c9c568585f6929bedeaad110ad08f079624/skills/webapp-testing Copy reviewed-revision command ↗ - Install the complete skill directory with its references and helpers; a copied SKILL.md alone may be incomplete.
- Choose your AI tools and project or global scope in the installer, then review its permissions before using the skill.

### Before you start

 - Node.js/npm for this installer
- An agent that supports the Agent Skills format
- Python and Playwright with an installed browser
- Authorized local development servers and their dependencies

### Compatibility

Claude Code · Python Playwright

### Local shell and browser automation

 - Launch and terminate development-server processes
- Execute a user-selected automation command
- Read rendered pages and write screenshots or logs
- Starts local shell processes and browser actions; screenshots and console logs can contain sensitive application data.

### Cost model

The example skill is Apache-licensed; browser compute, the consuming agent and any services contacted by the tested app have separate costs.

04 / FOLLOW THE EVIDENCE

## The source trail.

Our notes are separate from the original resource. Check upstream before adopting a new version.

 - [Skill definition at reviewed revision ↗](https://github.com/anthropics/skills/blob/34040c9c568585f6929bedeaad110ad08f079624/skills/webapp-testing/SKILL.md) Checked 2026-10-14 https://github.com/anthropics/skills/blob/34040c9c568585f6929bedeaad110ad08f079624/skills/webapp-testing/SKILL.md Supports: summary, upstreamDescription, whySelected, bestFor, limitations, review, compatibility, access
- [Reviewed reference or helper: scripts/with_server.py ↗](https://github.com/anthropics/skills/blob/34040c9c568585f6929bedeaad110ad08f079624/skills/webapp-testing/scripts/with_server.py) Checked 2026-10-14 https://github.com/anthropics/skills/blob/34040c9c568585f6929bedeaad110ad08f079624/skills/webapp-testing/scripts/with_server.py Supports: review, limitations, access
- [Reviewed reference or helper: examples/element_discovery.py ↗](https://github.com/anthropics/skills/blob/34040c9c568585f6929bedeaad110ad08f079624/skills/webapp-testing/examples/element_discovery.py) Checked 2026-10-14 https://github.com/anthropics/skills/blob/34040c9c568585f6929bedeaad110ad08f079624/skills/webapp-testing/examples/element_discovery.py Supports: review, limitations, access
- [Upstream license or licensing declaration ↗](https://github.com/anthropics/skills/blob/34040c9c568585f6929bedeaad110ad08f079624/skills/webapp-testing/LICENSE.txt) Checked 2026-10-14 https://github.com/anthropics/skills/blob/34040c9c568585f6929bedeaad110ad08f079624/skills/webapp-testing/LICENSE.txt Supports: license
- [Publisher installation and project documentation ↗](https://github.com/anthropics/skills/blob/34040c9c568585f6929bedeaad110ad08f079624/README.md) Checked 2026-10-14 https://github.com/anthropics/skills/blob/34040c9c568585f6929bedeaad110ad08f079624/README.md Supports: install, compatibility, access
- [Skills installer source formats and selective installation ↗](https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md) Checked 2026-10-14 https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md Supports: install
- [Installer implementation: full commit SHA fallback ↗](https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/src/git.ts) Checked 2026-10-14 https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/src/git.ts Supports: install
- [2026-10-15 W21 source re-review at the existing pin ↗](https://raw.githubusercontent.com/anthropics/skills/34040c9c568585f6929bedeaad110ad08f079624/skills/webapp-testing/SKILL.md) Checked 2026-10-15 https://raw.githubusercontent.com/anthropics/skills/34040c9c568585f6929bedeaad110ad08f079624/skills/webapp-testing/SKILL.md Supports: upstreamDescription, review.notTested, limitations

KEEP COMPARING

## Other approaches to consider.

Related by category or shared topics. These are alternatives to inspect, not a measured quality order.

 [### Undominated · A token is not PUBLIC_ ↗ Refuse a provider token in a PUBLIC_ variable or in browser code. A server environment is outside this refusal and is not approved by a pass.](/skills/undominated-public-not-secret/)[### Undominated · Browser code does not name loopback ↗ Refuse a browser script that names 127.0.0.1. That address is the visitor's machine. A server-side sidecar may name it.](/skills/undominated-loopback-not-browser/)[### Undominated · WebGPU browser inference audit ↗ Audits in-browser WebGPU execution shader compilation latency and first-token response times.](/skills/undominated-webgpu-browser-inference-audit/)

 [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)[Workflows ↗](/workflows/)

## Continue your investigation

 - [Choose a toolkit](/tools/)
- [Inspect execution hosts](/agents/)
- [Check tool access](/mcp-servers/)
- [Check project dependencies](/check-repo/)
