Web app testing with Playwright scripts

Tests a local web app with Python Playwright scripts: a helper starts and stops the servers, the agent inspects the rendered page, then clicks, fills, takes screenshots and reads console logs. Use when checking a frontend change or reproducing a UI bug.

TestingPack: Anthropic skills96 lineswebapp-testing
Author
Source
anthropics/skills/skills/webapp-testing @ e4bb5d9
License
Apache-2.0 · Copyright 2026 Anthropic, PBC.

About this skill

What it does

The skill has the agent test a local web app by writing small Python Playwright scripts (sync API, headless Chromium). A decision tree picks the approach. A static HTML file is read for selectors and opened through file://. A dynamic app gets "reconnaissance, then action": open the page, wait for networkidle, take a screenshot or dump the DOM, take selectors from what actually rendered, then click and fill. Inspecting before networkidle is the pitfall the skill warns about.

scripts/with_server.py runs the servers the app needs. It starts one or several commands, waits until each port accepts connections (30 seconds by default, --timeout), runs your script and stops the servers, so the Playwright script holds only browser logic. The agent calls it with --help and treats it as a black box. examples/ has three patterns: element_discovery.py lists buttons, links and inputs, static_html_automation.py fills a form in a local file, console_logging.py collects console messages. They save to /tmp/ and /mnt/user-data/outputs/, paths from Anthropic's sandbox; change them on your machine.

You need Python with the playwright package and its Chromium; the skill does not cover installing them.

When to use it, and when not

Use it to check that a frontend change works, reproduce a UI bug, take screenshots or read console errors in an app you can run locally.

It leaves throwaway scripts, not a test suite: no @playwright/test specs, nothing for CI.

How to run it

The install command below puts the whole folder in place. The agent picks the skill up when a UI needs checking; to call it yourself:

  • Claude Code: /webapp-testing, or ask for the skill by name.
  • Codex: $webapp-testing.
  • Cursor: type / in the Agent chat and pick webapp-testing.

Example: /webapp-testing Start the app with npm run dev on port 5173, log in as the demo user and check that the dashboard loads without console errors.

How it differs from similar skills

E2E tests with Playwright from our catalog writes @playwright/test specs that stay in the repository and run in CI. Browser automation with Playwright CLI drives the browser with playwright-cli commands and element refs from page snapshots, without writing scripts; it needs Node and npx. Browser testing with Chrome DevTools MCP inspects a live Chrome through an MCP server. This skill is one Python script per check plus a helper for the servers.

Install

Run one command — it saves SKILL.md and the files it uses into your agent's skills folder. Claude Code and Codex pick up a new skill without a restart; if it does not show up, restart the agent.

Claude Code — macOS, Linux
curl -fsSL --create-dirs -o ~/.claude/skills/webapp-testing/SKILL.md https://anymodel.org/en/skills/anthropic/webapp-testing/SKILL.md -o ~/.claude/skills/webapp-testing/LICENSE.txt https://anymodel.org/en/skills/anthropic/webapp-testing/LICENSE.txt -o ~/.claude/skills/webapp-testing/examples/console_logging.py https://anymodel.org/en/skills/anthropic/webapp-testing/examples/console_logging.py -o ~/.claude/skills/webapp-testing/examples/element_discovery.py https://anymodel.org/en/skills/anthropic/webapp-testing/examples/element_discovery.py -o ~/.claude/skills/webapp-testing/examples/static_html_automation.py https://anymodel.org/en/skills/anthropic/webapp-testing/examples/static_html_automation.py -o ~/.claude/skills/webapp-testing/scripts/with_server.py https://anymodel.org/en/skills/anthropic/webapp-testing/scripts/with_server.py && chmod +x ~/.claude/skills/webapp-testing/scripts/with_server.py
Codex, Cursor — macOS, Linux
curl -fsSL --create-dirs -o ~/.agents/skills/webapp-testing/SKILL.md https://anymodel.org/en/skills/anthropic/webapp-testing/SKILL.md -o ~/.agents/skills/webapp-testing/LICENSE.txt https://anymodel.org/en/skills/anthropic/webapp-testing/LICENSE.txt -o ~/.agents/skills/webapp-testing/examples/console_logging.py https://anymodel.org/en/skills/anthropic/webapp-testing/examples/console_logging.py -o ~/.agents/skills/webapp-testing/examples/element_discovery.py https://anymodel.org/en/skills/anthropic/webapp-testing/examples/element_discovery.py -o ~/.agents/skills/webapp-testing/examples/static_html_automation.py https://anymodel.org/en/skills/anthropic/webapp-testing/examples/static_html_automation.py -o ~/.agents/skills/webapp-testing/scripts/with_server.py https://anymodel.org/en/skills/anthropic/webapp-testing/scripts/with_server.py && chmod +x ~/.agents/skills/webapp-testing/scripts/with_server.py
Claude Code — Windows PowerShell
foreach ($f in 'SKILL.md','LICENSE.txt','examples/console_logging.py','examples/element_discovery.py','examples/static_html_automation.py','scripts/with_server.py') { $p = Join-Path "$HOME\.claude\skills\webapp-testing" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/anthropic/webapp-testing/$f" -UseBasicParsing -OutFile $p }
Codex, Cursor — Windows PowerShell
foreach ($f in 'SKILL.md','LICENSE.txt','examples/console_logging.py','examples/element_discovery.py','examples/static_html_automation.py','scripts/with_server.py') { $p = Join-Path "$HOME\.agents\skills\webapp-testing" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/anthropic/webapp-testing/$f" -UseBasicParsing -OutFile $p }

Any other agent: save the file into its skills folder, or give it the link to the file: https://anymodel.org/en/skills/anthropic/webapp-testing/SKILL.md

SKILL.md

Raw

Web Application Testing

To test local web applications, write native Python Playwright scripts.

Helper Scripts Available:

  • scripts/with_server.py - Manages server lifecycle (supports multiple servers)

Always run scripts with --help first to see usage. DO NOT read the source until you try running the script first and find that a customized solution is abslutely necessary. These scripts can be very large and thus pollute your context window. They exist to be called directly as black-box scripts rather than ingested into your context window.

Decision Tree: Choosing Your Approach

User task → Is it static HTML?
    ├─ Yes → Read HTML file directly to identify selectors
    │         ├─ Success → Write Playwright script using selectors
    │         └─ Fails/Incomplete → Treat as dynamic (below)
    │
    └─ No (dynamic webapp) → Is the server already running?
        ├─ No → Run: python scripts/with_server.py --help
        │        Then use the helper + write simplified Playwright script
        │
        └─ Yes → Reconnaissance-then-action:
            1. Navigate and wait for networkidle
            2. Take screenshot or inspect DOM
            3. Identify selectors from rendered state
            4. Execute actions with discovered selectors

Example: Using with_server.py

To start a server, run --help first, then use the helper:

Single server:

python scripts/with_server.py --server "npm run dev" --port 5173 -- python your_automation.py

Multiple servers (e.g., backend + frontend):

python scripts/with_server.py \
  --server "cd backend && python server.py" --port 3000 \
  --server "cd frontend && npm run dev" --port 5173 \
  -- python your_automation.py

To create an automation script, include only Playwright logic (servers are managed automatically):

from playwright.sync_api import sync_playwright

with sync_playwright() as p:
    browser = p.chromium.launch(headless=True) # Always launch chromium in headless mode
    page = browser.new_page()
    page.goto('http://localhost:5173') # Server already running and ready
    page.wait_for_load_state('networkidle') # CRITICAL: Wait for JS to execute
    # ... your automation logic
    browser.close()

Reconnaissance-Then-Action Pattern

  1. Inspect rendered DOM:

    page.screenshot(path='/tmp/inspect.png', full_page=True)
    content = page.content()
    page.locator('button').all()
    
  2. Identify selectors from inspection results

  3. Execute actions using discovered selectors

Common Pitfall

❌ Don't inspect the DOM before waiting for networkidle on dynamic apps ✅ Do wait for page.wait_for_load_state('networkidle') before inspection

Best Practices

  • Use bundled scripts as black boxes - To accomplish a task, consider whether one of the scripts available in scripts/ can help. These scripts handle common, complex workflows reliably without cluttering the context window. Use --help to see usage, then invoke directly.
  • Use sync_playwright() for synchronous scripts
  • Always close the browser when done
  • Use descriptive selectors: text=, role=, CSS selectors, or IDs
  • Add appropriate waits: page.wait_for_selector() or page.wait_for_timeout()

Reference Files

  • examples/ - Examples showing common patterns:
    • element_discovery.py - Discovering buttons, links, and inputs on a page
    • static_html_automation.py - Using file:// URLs for local HTML
    • console_logging.py - Capturing console logs during automation

Connect through AnyModel API

This skill runs on whatever model your agent uses. Point Claude Code, Codex or Cursor at AnyModel to run it on Claude, GPT, Gemini and more with one key — pay per token, no subscription.

More from the pack Anthropic skills

MCP server builder

Guides the agent through building an MCP server for an external API in TypeScript or Python: tool design, schemas, pagination, errors, testing and an evaluation run with Claude. Use when wrapping an API or service as MCP tools.

Skill creator with evals

Drafts or revises an agent skill, tests it with subagents against a baseline, shows results and benchmarks on a review page and tunes the description for triggering. Use when a new or edited skill has to be measured, not just written.

Distinctive frontend design

Gives new UI a visual direction drawn from its subject: a short plan of colours, type and layout, checked against the brief and against common AI-generated looks before any code. Use when a page or product screen should not look templated.

PDF files: read, fill, create

Extracts text and tables, merges, splits, encrypts and OCRs PDFs with pypdf, pdfplumber, reportlab and qpdf, and fills forms through bundled scripts that check fields and boxes. Use when a task reads, fills or produces a PDF file.

Word documents (.docx)

Creates Word files with docx-js, edits existing ones as unpacked XML, adds tracked changes and comments through bundled scripts, then validates and renders the result. Use when the deliverable or input is a .docx or .dotx file.

Excel spreadsheets (.xlsx)

Builds and edits Excel workbooks with openpyxl, keeps real formulas, recalculates them in LibreOffice with a JSON error report and follows financial-model conventions. Use when the deliverable is a spreadsheet file such as .xlsx, .xlsm or .csv.

PowerPoint decks (.pptx)

Creates themed decks with pptxgenjs, edits templates as unpacked XML with scripts for slide text, thumbnails, duplication and validation, and checks every slide as an image. Use when a task creates, edits or reads a .pptx or .potx file.

Claude API reference for agents

Anthropic's reference for code that calls Claude: SDKs in seven languages and cURL, current models and prices, tool use, caching, Managed Agents, plus migration, cost and eval procedures. Use when writing or changing code that uses the Claude API.

Algorithmic art with p5.js

Creates generative art in p5.js: a short manifesto for the piece, then a seeded algorithm in one HTML page with sliders, seed navigation and PNG download. Use when asked for flow fields, particle systems or other art made with code.

Document co-authoring workflow

Guides the user through writing a document in three stages: context gathering with numbered questions, section-by-section drafting with brainstormed options, and a test on a subagent that sees only the text. Use when drafting a spec, proposal or decision doc.