Skip to content
AI Dev Toolkit.
Esc
  • AI Token CounterCount tokens for GPT, Claude, Gemini, DeepSeek, Qwen and more.Tool
  • LLM API Cost CalculatorEstimate per-request, daily and monthly API costs.Tool
  • AI Model ComparisonCompare prices, context windows and features across models.Tool
  • AI Model Pricing PagesSpecs, real costs and cheaper alternatives for popular models.Tool
  • Context Window CheckerSee whether your text fits each model’s context window.Tool
  • Subscription vs API CalculatorFind out whether a chat plan or the API is cheaper for you.Tool
  • GPU / VRAM CalculatorCheck how much VRAM a local model needs and which GPUs fit.Tool
  • Prompt Caching CalculatorEstimate savings from prompt caching.Tool

Claude skill · Development · Anthropic

Web app testing skill for Claude

Tests local web apps with Python Playwright: start the servers, inspect the page, then act, with screenshots and browser logs.

Command
/webapp-testing
Licence
Apache-2.0, copying allowed with attribution
Folder
6 files, 22 KB
Runs code
4 scripts

Overview

What it does

The skill gives Claude a decision tree. For static HTML it reads the file to find selectors. For a dynamic app it starts the servers with scripts/with_server.py if they aren’t already running, waits for the page to settle, takes a screenshot or inspects the DOM, and only then writes the actions.

It tells Claude to run the helper script with --help rather than reading its source, which keeps helper scripts out of the context window: a good example of treating a bundled script as a black box.

Triggers

When Claude uses it

  • Checking that a local web app works, debugging UI behaviour, capturing screenshots or reading browser console logs.
Its description, which Claude matches against
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.

What it needs

  • Python with Playwright and its browsers installed.

Install

How to install it

Claude Code

Plugin (type in Claude Code)
/plugin marketplace add anthropics/skills
/plugin install example-skills@anthropic-agent-skills

The example-skills plugin installs 12 skills from this repository, including this one. Its skills are then namespaced, such as /example-skills:webapp-testing.

Or copy the folder (shell)
git clone --depth 1 https://github.com/anthropics/skills.git
mkdir -p ~/.claude/skills
cp -r skills/skills/webapp-testing ~/.claude/skills/

That makes it a personal skill, available as /webapp-testing in all your projects. Copy it into .claude/skills/ in a repository instead to share it with your team.

claude.ai and the Claude API

Zip the skill folder, then in claude.ai open Customize > Skills, choose + and Create skill, then Upload a skill. Code execution must be turned on.

Upload with the Python SDK
from anthropic import Anthropic
from anthropic.lib import files_from_dir

client = Anthropic()
skill = client.skills.create(files=files_from_dir("webapp-testing"))
print(skill.id)  # use as a custom skill_id with the code execution tool

Checks

SKILL.md validator results

Its SKILL.md (96 lines) run through our SKILL.md validator, with the folder’s file list, for both targets. These check the file’s format, not whether the skill works well.

Claude Code

0 errors, 1 warning, 0 tips

  • warningSay when to use it, e.g. “Use when the user asks for…”. Claude matches requests against the description, so it needs both what the skill does and when.

claude.ai and the API

0 errors, 1 warning, 1 tip

  • warningSay when to use it, e.g. “Use when the user asks for…”. Claude matches requests against the description, so it needs both what the skill does and when.
  • tipThe Claude Help Center’s upload guide gives a 200-character description limit for claude.ai, though the platform docs say 1,024. Keep it under 200 if you’ll upload it there.

Folder

What’s in the folder

  • LICENSE.txt11 KB
  • SKILL.md3.8 KB
  • examples/3 files, 3.4 KB
  • scripts/1 file, 3.6 KB

SKILL.md sections

  1. Web Application Testing
  2. Decision Tree: Choosing Your Approach
  3. Example: Using with_server.py
  4. Reconnaissance-Then-Action Pattern
  5. Common Pitfall
  6. Best Practices
  7. Reference Files

Source

Licence and source

Related

All Claude skillsWrite your own skillSlash command builderGuide: subagents, skills and commands